diff options
76 files changed, 2514 insertions, 1343 deletions
diff --git a/.github/workflows/run_tests.yaml b/.github/workflows/run_tests.yaml index e9370cc0..3dafaf8d 100644 --- a/.github/workflows/run_tests.yaml +++ b/.github/workflows/run_tests.yaml @@ -41,6 +41,7 @@ jobs: --skip-prepare-environment --skip-torch-cuda-test --test-server + --do-not-download-clip --no-half --disable-opt-split-attention --use-cpu all diff --git a/CHANGELOG.md b/CHANGELOG.md index 30783d9d..b18c6867 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,9 +1,35 @@ +## 1.5.1
+
+### Minor:
+ * support parsing text encoder blocks in some new LoRAs
+ * delete scale checker script due to user demand
+
+### Extensions and API:
+ * add postprocess_batch_list script callback
+
+### Bug Fixes:
+ * fix TI training for SD1
+ * fix reload altclip model error
+ * prepend the pythonpath instead of overriding it
+ * fix typo in SD_WEBUI_RESTARTING
+ * if txt2img/img2img raises an exception, finally call state.end()
+ * fix composable diffusion weight parsing
+ * restyle Startup profile for black users
+ * fix webui not launching with --nowebui
+ * catch exception for non git extensions
+ * fix some options missing from /sdapi/v1/options
+ * fix for extension update status always saying "unknown"
+ * fix display of extra network cards that have `<>` in the name
+ * update lora extension to work with python 3.8
+
+
## 1.5.0
### Features:
* SD XL support
* user metadata system for custom networks
* extended Lora metadata editor: set activation text, default weight, view tags, training info
+ * Lora extension rework to include other types of networks (all that were previously handled by LyCORIS extension)
* show github stars for extenstions
* img2img batch mode can read extra stuff from png info
* img2img batch works with subdirectories
@@ -11,6 +37,9 @@ * restyle time taken/VRAM display
* add textual inversion hashes to infotext
* optimization: cache git extension repo information
+ * move generate button next to the generated picture for mobile clients
+ * hide cards for networks of incompatible Stable Diffusion version in Lora extra networks interface
+ * skip installing packages with pip if they all are already installed - startup speedup of about 2 seconds
### Minor:
* checkbox to check/uncheck all extensions in the Installed tab
@@ -25,6 +54,8 @@ * speedup extra networks listing
* added `[none]` filename token.
* removed thumbs extra networks view mode (use settings tab to change width/height/scale to get thumbs)
+ * add always_discard_next_to_last_sigma option to XYZ plot
+ * automatically switch to 32-bit float VAE if the generated picture has NaNs without the need for `--no-half-vae` commandline flag.
### Extensions and API:
* api endpoints: /sdapi/v1/server-kill, /sdapi/v1/server-restart, /sdapi/v1/server-stop
@@ -53,9 +84,8 @@ * fix: check fill size none zero when resize (fixes #11425)
* use submit and blur for quick settings textbox
* save img2img batch with images.save_image()
- *
-
-
+ * prevent running preload.py for disabled extensions
+ * fix: previously, model name was added together with directory name to infotext and to [model_name] filename pattern; directory name is now not included
## 1.4.1
@@ -88,7 +88,7 @@ A browser interface based on Gradio library for Stable Diffusion. - [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
- Now without any bad letters!
- Load checkpoints in safetensors format
-- Eased resolution restriction: generated image's domension must be a multiple of 8 rather than 64
+- Eased resolution restriction: generated image's dimension must be a multiple of 8 rather than 64
- Now with a license!
- Reorder elements in the UI from settings screen
@@ -168,5 +168,7 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al - Security advice - RyotaK
- UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
+- LyCORIS - KohakuBlueleaf
+- Restart sampling - lambertae - https://github.com/Newbeeer/diffusion_restart_sampling
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- (You)
diff --git a/extensions-builtin/Lora/extra_networks_lora.py b/extensions-builtin/Lora/extra_networks_lora.py index 66ee9c85..ba2945c6 100644 --- a/extensions-builtin/Lora/extra_networks_lora.py +++ b/extensions-builtin/Lora/extra_networks_lora.py @@ -1,5 +1,5 @@ from modules import extra_networks, shared
-import lora
+import networks
class ExtraNetworkLora(extra_networks.ExtraNetwork):
@@ -9,24 +9,38 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork): def activate(self, p, params_list):
additional = shared.opts.sd_lora
- if additional != "None" and additional in lora.available_loras and not any(x for x in params_list if x.items[0] == additional):
+ if additional != "None" and additional in networks.available_networks and not any(x for x in params_list if x.items[0] == additional):
p.all_prompts = [x + f"<lora:{additional}:{shared.opts.extra_networks_default_multiplier}>" for x in p.all_prompts]
params_list.append(extra_networks.ExtraNetworkParams(items=[additional, shared.opts.extra_networks_default_multiplier]))
names = []
- multipliers = []
+ te_multipliers = []
+ unet_multipliers = []
+ dyn_dims = []
for params in params_list:
assert params.items
- names.append(params.items[0])
- multipliers.append(float(params.items[1]) if len(params.items) > 1 else 1.0)
+ names.append(params.positional[0])
- lora.load_loras(names, multipliers)
+ te_multiplier = float(params.positional[1]) if len(params.positional) > 1 else 1.0
+ te_multiplier = float(params.named.get("te", te_multiplier))
+
+ unet_multiplier = float(params.positional[2]) if len(params.positional) > 2 else te_multiplier
+ unet_multiplier = float(params.named.get("unet", unet_multiplier))
+
+ dyn_dim = int(params.positional[3]) if len(params.positional) > 3 else None
+ dyn_dim = int(params.named["dyn"]) if "dyn" in params.named else dyn_dim
+
+ te_multipliers.append(te_multiplier)
+ unet_multipliers.append(unet_multiplier)
+ dyn_dims.append(dyn_dim)
+
+ networks.load_networks(names, te_multipliers, unet_multipliers, dyn_dims)
if shared.opts.lora_add_hashes_to_infotext:
- lora_hashes = []
- for item in lora.loaded_loras:
- shorthash = item.lora_on_disk.shorthash
+ network_hashes = []
+ for item in networks.loaded_networks:
+ shorthash = item.network_on_disk.shorthash
if not shorthash:
continue
@@ -36,10 +50,10 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork): alias = alias.replace(":", "").replace(",", "")
- lora_hashes.append(f"{alias}: {shorthash}")
+ network_hashes.append(f"{alias}: {shorthash}")
- if lora_hashes:
- p.extra_generation_params["Lora hashes"] = ", ".join(lora_hashes)
+ if network_hashes:
+ p.extra_generation_params["Lora hashes"] = ", ".join(network_hashes)
def deactivate(self, p):
pass
diff --git a/extensions-builtin/Lora/lora.py b/extensions-builtin/Lora/lora.py index 9cdff6ed..9365aa74 100644 --- a/extensions-builtin/Lora/lora.py +++ b/extensions-builtin/Lora/lora.py @@ -1,537 +1,9 @@ -import os
-import re
-import torch
-from typing import Union
+import networks
-from modules import shared, devices, sd_models, errors, scripts, sd_hijack, hashes, cache
+list_available_loras = networks.list_available_networks
-metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20}
-
-re_digits = re.compile(r"\d+")
-re_x_proj = re.compile(r"(.*)_([qkv]_proj)$")
-re_compiled = {}
-
-suffix_conversion = {
- "attentions": {},
- "resnets": {
- "conv1": "in_layers_2",
- "conv2": "out_layers_3",
- "time_emb_proj": "emb_layers_1",
- "conv_shortcut": "skip_connection",
- }
-}
-
-
-def convert_diffusers_name_to_compvis(key, is_sd2):
- def match(match_list, regex_text):
- regex = re_compiled.get(regex_text)
- if regex is None:
- regex = re.compile(regex_text)
- re_compiled[regex_text] = regex
-
- r = re.match(regex, key)
- if not r:
- return False
-
- match_list.clear()
- match_list.extend([int(x) if re.match(re_digits, x) else x for x in r.groups()])
- return True
-
- m = []
-
- if match(m, r"lora_unet_down_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
- suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
- return f"diffusion_model_input_blocks_{1 + m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
-
- if match(m, r"lora_unet_mid_block_(attentions|resnets)_(\d+)_(.+)"):
- suffix = suffix_conversion.get(m[0], {}).get(m[2], m[2])
- return f"diffusion_model_middle_block_{1 if m[0] == 'attentions' else m[1] * 2}_{suffix}"
-
- if match(m, r"lora_unet_up_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
- suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
- return f"diffusion_model_output_blocks_{m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
-
- if match(m, r"lora_unet_down_blocks_(\d+)_downsamplers_0_conv"):
- return f"diffusion_model_input_blocks_{3 + m[0] * 3}_0_op"
-
- if match(m, r"lora_unet_up_blocks_(\d+)_upsamplers_0_conv"):
- return f"diffusion_model_output_blocks_{2 + m[0] * 3}_{2 if m[0]>0 else 1}_conv"
-
- if match(m, r"lora_te_text_model_encoder_layers_(\d+)_(.+)"):
- if is_sd2:
- if 'mlp_fc1' in m[1]:
- return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc1', 'mlp_c_fc')}"
- elif 'mlp_fc2' in m[1]:
- return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc2', 'mlp_c_proj')}"
- else:
- return f"model_transformer_resblocks_{m[0]}_{m[1].replace('self_attn', 'attn')}"
-
- return f"transformer_text_model_encoder_layers_{m[0]}_{m[1]}"
-
- if match(m, r"lora_te2_text_model_encoder_layers_(\d+)_(.+)"):
- if 'mlp_fc1' in m[1]:
- return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc1', 'mlp_c_fc')}"
- elif 'mlp_fc2' in m[1]:
- return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc2', 'mlp_c_proj')}"
- else:
- return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('self_attn', 'attn')}"
-
- return key
-
-
-class LoraOnDisk:
- def __init__(self, name, filename):
- self.name = name
- self.filename = filename
- self.metadata = {}
- self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
-
- def read_metadata():
- metadata = sd_models.read_metadata_from_safetensors(filename)
- metadata.pop('ssmd_cover_images', None) # those are cover images, and they are too big to display in UI as text
-
- return metadata
-
- if self.is_safetensors:
- try:
- self.metadata = cache.cached_data_for_file('safetensors-metadata', "lora/" + self.name, filename, read_metadata)
- except Exception as e:
- errors.display(e, f"reading lora {filename}")
-
- if self.metadata:
- m = {}
- for k, v in sorted(self.metadata.items(), key=lambda x: metadata_tags_order.get(x[0], 999)):
- m[k] = v
-
- self.metadata = m
-
- self.alias = self.metadata.get('ss_output_name', self.name)
-
- self.hash = None
- self.shorthash = None
- self.set_hash(
- self.metadata.get('sshs_model_hash') or
- hashes.sha256_from_cache(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or
- ''
- )
-
- def set_hash(self, v):
- self.hash = v
- self.shorthash = self.hash[0:12]
-
- if self.shorthash:
- available_lora_hash_lookup[self.shorthash] = self
-
- def read_hash(self):
- if not self.hash:
- self.set_hash(hashes.sha256(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or '')
-
- def get_alias(self):
- if shared.opts.lora_preferred_name == "Filename" or self.alias.lower() in forbidden_lora_aliases:
- return self.name
- else:
- return self.alias
-
-
-class LoraModule:
- def __init__(self, name, lora_on_disk: LoraOnDisk):
- self.name = name
- self.lora_on_disk = lora_on_disk
- self.multiplier = 1.0
- self.modules = {}
- self.mtime = None
-
- self.mentioned_name = None
- """the text that was used to add lora to prompt - can be either name or an alias"""
-
-
-class LoraUpDownModule:
- def __init__(self):
- self.up = None
- self.down = None
- self.alpha = None
-
-
-def assign_lora_names_to_compvis_modules(sd_model):
- lora_layer_mapping = {}
-
- if shared.sd_model.is_sdxl:
- for i, embedder in enumerate(shared.sd_model.conditioner.embedders):
- if not hasattr(embedder, 'wrapped'):
- continue
-
- for name, module in embedder.wrapped.named_modules():
- lora_name = f'{i}_{name.replace(".", "_")}'
- lora_layer_mapping[lora_name] = module
- module.lora_layer_name = lora_name
- else:
- for name, module in shared.sd_model.cond_stage_model.wrapped.named_modules():
- lora_name = name.replace(".", "_")
- lora_layer_mapping[lora_name] = module
- module.lora_layer_name = lora_name
-
- for name, module in shared.sd_model.model.named_modules():
- lora_name = name.replace(".", "_")
- lora_layer_mapping[lora_name] = module
- module.lora_layer_name = lora_name
-
- sd_model.lora_layer_mapping = lora_layer_mapping
-
-
-def load_lora(name, lora_on_disk):
- lora = LoraModule(name, lora_on_disk)
- lora.mtime = os.path.getmtime(lora_on_disk.filename)
-
- sd = sd_models.read_state_dict(lora_on_disk.filename)
-
- # this should not be needed but is here as an emergency fix for an unknown error people are experiencing in 1.2.0
- if not hasattr(shared.sd_model, 'lora_layer_mapping'):
- assign_lora_names_to_compvis_modules(shared.sd_model)
-
- keys_failed_to_match = {}
- is_sd2 = 'model_transformer_resblocks' in shared.sd_model.lora_layer_mapping
-
- for key_lora, weight in sd.items():
- key_lora_without_lora_parts, lora_key = key_lora.split(".", 1)
-
- key = convert_diffusers_name_to_compvis(key_lora_without_lora_parts, is_sd2)
- sd_module = shared.sd_model.lora_layer_mapping.get(key, None)
-
- if sd_module is None:
- m = re_x_proj.match(key)
- if m:
- sd_module = shared.sd_model.lora_layer_mapping.get(m.group(1), None)
-
- # SDXL loras seem to already have correct compvis keys, so only need to replace "lora_unet" with "diffusion_model"
- if sd_module is None and "lora_unet" in key_lora_without_lora_parts:
- key = key_lora_without_lora_parts.replace("lora_unet", "diffusion_model")
- sd_module = shared.sd_model.lora_layer_mapping.get(key, None)
- elif sd_module is None and "lora_te1_text_model" in key_lora_without_lora_parts:
- key = key_lora_without_lora_parts.replace("lora_te1_text_model", "0_transformer_text_model")
- sd_module = shared.sd_model.lora_layer_mapping.get(key, None)
-
- if sd_module is None:
- keys_failed_to_match[key_lora] = key
- continue
-
- lora_module = lora.modules.get(key, None)
- if lora_module is None:
- lora_module = LoraUpDownModule()
- lora.modules[key] = lora_module
-
- if lora_key == "alpha":
- lora_module.alpha = weight.item()
- continue
-
- if type(sd_module) == torch.nn.Linear:
- module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
- elif type(sd_module) == torch.nn.modules.linear.NonDynamicallyQuantizableLinear:
- module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
- elif type(sd_module) == torch.nn.MultiheadAttention:
- module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
- elif type(sd_module) == torch.nn.Conv2d and weight.shape[2:] == (1, 1):
- module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
- elif type(sd_module) == torch.nn.Conv2d and weight.shape[2:] == (3, 3):
- module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (3, 3), bias=False)
- else:
- print(f'Lora layer {key_lora} matched a layer with unsupported type: {type(sd_module).__name__}')
- continue
- raise AssertionError(f"Lora layer {key_lora} matched a layer with unsupported type: {type(sd_module).__name__}")
-
- with torch.no_grad():
- module.weight.copy_(weight)
-
- module.to(device=devices.cpu, dtype=devices.dtype)
-
- if lora_key == "lora_up.weight":
- lora_module.up = module
- elif lora_key == "lora_down.weight":
- lora_module.down = module
- else:
- raise AssertionError(f"Bad Lora layer name: {key_lora} - must end in lora_up.weight, lora_down.weight or alpha")
-
- if keys_failed_to_match:
- print(f"Failed to match keys when loading Lora {lora_on_disk.filename}: {keys_failed_to_match}")
-
- return lora
-
-
-def load_loras(names, multipliers=None):
- already_loaded = {}
-
- for lora in loaded_loras:
- if lora.name in names:
- already_loaded[lora.name] = lora
-
- loaded_loras.clear()
-
- loras_on_disk = [available_lora_aliases.get(name, None) for name in names]
- if any(x is None for x in loras_on_disk):
- list_available_loras()
-
- loras_on_disk = [available_lora_aliases.get(name, None) for name in names]
-
- failed_to_load_loras = []
-
- for i, name in enumerate(names):
- lora = already_loaded.get(name, None)
-
- lora_on_disk = loras_on_disk[i]
-
- if lora_on_disk is not None:
- if lora is None or os.path.getmtime(lora_on_disk.filename) > lora.mtime:
- try:
- lora = load_lora(name, lora_on_disk)
- except Exception as e:
- errors.display(e, f"loading Lora {lora_on_disk.filename}")
- continue
-
- lora.mentioned_name = name
-
- lora_on_disk.read_hash()
-
- if lora is None:
- failed_to_load_loras.append(name)
- print(f"Couldn't find Lora with name {name}")
- continue
-
- lora.multiplier = multipliers[i] if multipliers else 1.0
- loaded_loras.append(lora)
-
- if failed_to_load_loras:
- sd_hijack.model_hijack.comments.append("Failed to find Loras: " + ", ".join(failed_to_load_loras))
-
-
-def lora_calc_updown(lora, module, target):
- with torch.no_grad():
- up = module.up.weight.to(target.device, dtype=target.dtype)
- down = module.down.weight.to(target.device, dtype=target.dtype)
-
- if up.shape[2:] == (1, 1) and down.shape[2:] == (1, 1):
- updown = (up.squeeze(2).squeeze(2) @ down.squeeze(2).squeeze(2)).unsqueeze(2).unsqueeze(3)
- elif up.shape[2:] == (3, 3) or down.shape[2:] == (3, 3):
- updown = torch.nn.functional.conv2d(down.permute(1, 0, 2, 3), up).permute(1, 0, 2, 3)
- else:
- updown = up @ down
-
- updown = updown * lora.multiplier * (module.alpha / module.up.weight.shape[1] if module.alpha else 1.0)
-
- return updown
-
-
-def lora_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]):
- weights_backup = getattr(self, "lora_weights_backup", None)
-
- if weights_backup is None:
- return
-
- if isinstance(self, torch.nn.MultiheadAttention):
- self.in_proj_weight.copy_(weights_backup[0])
- self.out_proj.weight.copy_(weights_backup[1])
- else:
- self.weight.copy_(weights_backup)
-
-
-def lora_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]):
- """
- Applies the currently selected set of Loras to the weights of torch layer self.
- If weights already have this particular set of loras applied, does nothing.
- If not, restores orginal weights from backup and alters weights according to loras.
- """
-
- lora_layer_name = getattr(self, 'lora_layer_name', None)
- if lora_layer_name is None:
- return
-
- current_names = getattr(self, "lora_current_names", ())
- wanted_names = tuple((x.name, x.multiplier) for x in loaded_loras)
-
- weights_backup = getattr(self, "lora_weights_backup", None)
- if weights_backup is None:
- if isinstance(self, torch.nn.MultiheadAttention):
- weights_backup = (self.in_proj_weight.to(devices.cpu, copy=True), self.out_proj.weight.to(devices.cpu, copy=True))
- else:
- weights_backup = self.weight.to(devices.cpu, copy=True)
-
- self.lora_weights_backup = weights_backup
-
- if current_names != wanted_names:
- lora_restore_weights_from_backup(self)
-
- for lora in loaded_loras:
- module = lora.modules.get(lora_layer_name, None)
- if module is not None and hasattr(self, 'weight'):
- self.weight += lora_calc_updown(lora, module, self.weight)
- continue
-
- module_q = lora.modules.get(lora_layer_name + "_q_proj", None)
- module_k = lora.modules.get(lora_layer_name + "_k_proj", None)
- module_v = lora.modules.get(lora_layer_name + "_v_proj", None)
- module_out = lora.modules.get(lora_layer_name + "_out_proj", None)
-
- if isinstance(self, torch.nn.MultiheadAttention) and module_q and module_k and module_v and module_out:
- updown_q = lora_calc_updown(lora, module_q, self.in_proj_weight)
- updown_k = lora_calc_updown(lora, module_k, self.in_proj_weight)
- updown_v = lora_calc_updown(lora, module_v, self.in_proj_weight)
- updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
-
- self.in_proj_weight += updown_qkv
- self.out_proj.weight += lora_calc_updown(lora, module_out, self.out_proj.weight)
- continue
-
- if module is None:
- continue
-
- print(f'failed to calculate lora weights for layer {lora_layer_name}')
-
- self.lora_current_names = wanted_names
-
-
-def lora_forward(module, input, original_forward):
- """
- Old way of applying Lora by executing operations during layer's forward.
- Stacking many loras this way results in big performance degradation.
- """
-
- if len(loaded_loras) == 0:
- return original_forward(module, input)
-
- input = devices.cond_cast_unet(input)
-
- lora_restore_weights_from_backup(module)
- lora_reset_cached_weight(module)
-
- res = original_forward(module, input)
-
- lora_layer_name = getattr(module, 'lora_layer_name', None)
- for lora in loaded_loras:
- module = lora.modules.get(lora_layer_name, None)
- if module is None:
- continue
-
- module.up.to(device=devices.device)
- module.down.to(device=devices.device)
-
- res = res + module.up(module.down(input)) * lora.multiplier * (module.alpha / module.up.weight.shape[1] if module.alpha else 1.0)
-
- return res
-
-
-def lora_reset_cached_weight(self: Union[torch.nn.Conv2d, torch.nn.Linear]):
- self.lora_current_names = ()
- self.lora_weights_backup = None
-
-
-def lora_Linear_forward(self, input):
- if shared.opts.lora_functional:
- return lora_forward(self, input, torch.nn.Linear_forward_before_lora)
-
- lora_apply_weights(self)
-
- return torch.nn.Linear_forward_before_lora(self, input)
-
-
-def lora_Linear_load_state_dict(self, *args, **kwargs):
- lora_reset_cached_weight(self)
-
- return torch.nn.Linear_load_state_dict_before_lora(self, *args, **kwargs)
-
-
-def lora_Conv2d_forward(self, input):
- if shared.opts.lora_functional:
- return lora_forward(self, input, torch.nn.Conv2d_forward_before_lora)
-
- lora_apply_weights(self)
-
- return torch.nn.Conv2d_forward_before_lora(self, input)
-
-
-def lora_Conv2d_load_state_dict(self, *args, **kwargs):
- lora_reset_cached_weight(self)
-
- return torch.nn.Conv2d_load_state_dict_before_lora(self, *args, **kwargs)
-
-
-def lora_MultiheadAttention_forward(self, *args, **kwargs):
- lora_apply_weights(self)
-
- return torch.nn.MultiheadAttention_forward_before_lora(self, *args, **kwargs)
-
-
-def lora_MultiheadAttention_load_state_dict(self, *args, **kwargs):
- lora_reset_cached_weight(self)
-
- return torch.nn.MultiheadAttention_load_state_dict_before_lora(self, *args, **kwargs)
-
-
-def list_available_loras():
- available_loras.clear()
- available_lora_aliases.clear()
- forbidden_lora_aliases.clear()
- available_lora_hash_lookup.clear()
- forbidden_lora_aliases.update({"none": 1, "Addams": 1})
-
- os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
-
- candidates = list(shared.walk_files(shared.cmd_opts.lora_dir, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
- for filename in candidates:
- if os.path.isdir(filename):
- continue
-
- name = os.path.splitext(os.path.basename(filename))[0]
- try:
- entry = LoraOnDisk(name, filename)
- except OSError: # should catch FileNotFoundError and PermissionError etc.
- errors.report(f"Failed to load LoRA {name} from {filename}", exc_info=True)
- continue
-
- available_loras[name] = entry
-
- if entry.alias in available_lora_aliases:
- forbidden_lora_aliases[entry.alias.lower()] = 1
-
- available_lora_aliases[name] = entry
- available_lora_aliases[entry.alias] = entry
-
-
-re_lora_name = re.compile(r"(.*)\s*\([0-9a-fA-F]+\)")
-
-
-def infotext_pasted(infotext, params):
- if "AddNet Module 1" in [x[1] for x in scripts.scripts_txt2img.infotext_fields]:
- return # if the other extension is active, it will handle those fields, no need to do anything
-
- added = []
-
- for k in params:
- if not k.startswith("AddNet Model "):
- continue
-
- num = k[13:]
-
- if params.get("AddNet Module " + num) != "LoRA":
- continue
-
- name = params.get("AddNet Model " + num)
- if name is None:
- continue
-
- m = re_lora_name.match(name)
- if m:
- name = m.group(1)
-
- multiplier = params.get("AddNet Weight A " + num, "1.0")
-
- added.append(f"<lora:{name}:{multiplier}>")
-
- if added:
- params["Prompt"] += "\n" + "".join(added)
-
-
-available_loras = {}
-available_lora_aliases = {}
-available_lora_hash_lookup = {}
-forbidden_lora_aliases = {}
-loaded_loras = []
-
-list_available_loras()
+available_loras = networks.available_networks
+available_lora_aliases = networks.available_network_aliases
+available_lora_hash_lookup = networks.available_network_hash_lookup
+forbidden_lora_aliases = networks.forbidden_network_aliases
+loaded_loras = networks.loaded_networks
diff --git a/extensions-builtin/Lora/lyco_helpers.py b/extensions-builtin/Lora/lyco_helpers.py new file mode 100644 index 00000000..279b34bc --- /dev/null +++ b/extensions-builtin/Lora/lyco_helpers.py @@ -0,0 +1,21 @@ +import torch
+
+
+def make_weight_cp(t, wa, wb):
+ temp = torch.einsum('i j k l, j r -> i r k l', t, wb)
+ return torch.einsum('i j k l, i r -> r j k l', temp, wa)
+
+
+def rebuild_conventional(up, down, shape, dyn_dim=None):
+ up = up.reshape(up.size(0), -1)
+ down = down.reshape(down.size(0), -1)
+ if dyn_dim is not None:
+ up = up[:, :dyn_dim]
+ down = down[:dyn_dim, :]
+ return (up @ down).reshape(shape)
+
+
+def rebuild_cp_decomposition(up, down, mid):
+ up = up.reshape(up.size(0), -1)
+ down = down.reshape(down.size(0), -1)
+ return torch.einsum('n m k l, i n, m j -> i j k l', mid, up, down)
diff --git a/extensions-builtin/Lora/network.py b/extensions-builtin/Lora/network.py new file mode 100644 index 00000000..0a18d69e --- /dev/null +++ b/extensions-builtin/Lora/network.py @@ -0,0 +1,155 @@ +from __future__ import annotations
+import os
+from collections import namedtuple
+import enum
+
+from modules import sd_models, cache, errors, hashes, shared
+
+NetworkWeights = namedtuple('NetworkWeights', ['network_key', 'sd_key', 'w', 'sd_module'])
+
+metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20}
+
+
+class SdVersion(enum.Enum):
+ Unknown = 1
+ SD1 = 2
+ SD2 = 3
+ SDXL = 4
+
+
+class NetworkOnDisk:
+ def __init__(self, name, filename):
+ self.name = name
+ self.filename = filename
+ self.metadata = {}
+ self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
+
+ def read_metadata():
+ metadata = sd_models.read_metadata_from_safetensors(filename)
+ metadata.pop('ssmd_cover_images', None) # those are cover images, and they are too big to display in UI as text
+
+ return metadata
+
+ if self.is_safetensors:
+ try:
+ self.metadata = cache.cached_data_for_file('safetensors-metadata', "lora/" + self.name, filename, read_metadata)
+ except Exception as e:
+ errors.display(e, f"reading lora {filename}")
+
+ if self.metadata:
+ m = {}
+ for k, v in sorted(self.metadata.items(), key=lambda x: metadata_tags_order.get(x[0], 999)):
+ m[k] = v
+
+ self.metadata = m
+
+ self.alias = self.metadata.get('ss_output_name', self.name)
+
+ self.hash = None
+ self.shorthash = None
+ self.set_hash(
+ self.metadata.get('sshs_model_hash') or
+ hashes.sha256_from_cache(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or
+ ''
+ )
+
+ self.sd_version = self.detect_version()
+
+ def detect_version(self):
+ if str(self.metadata.get('ss_base_model_version', "")).startswith("sdxl_"):
+ return SdVersion.SDXL
+ elif str(self.metadata.get('ss_v2', "")) == "True":
+ return SdVersion.SD2
+ elif len(self.metadata):
+ return SdVersion.SD1
+
+ return SdVersion.Unknown
+
+ def set_hash(self, v):
+ self.hash = v
+ self.shorthash = self.hash[0:12]
+
+ if self.shorthash:
+ import networks
+ networks.available_network_hash_lookup[self.shorthash] = self
+
+ def read_hash(self):
+ if not self.hash:
+ self.set_hash(hashes.sha256(self.filename, "lora/" + self.name, use_addnet_hash=self.is_safetensors) or '')
+
+ def get_alias(self):
+ import networks
+ if shared.opts.lora_preferred_name == "Filename" or self.alias.lower() in networks.forbidden_network_aliases:
+ return self.name
+ else:
+ return self.alias
+
+
+class Network: # LoraModule
+ def __init__(self, name, network_on_disk: NetworkOnDisk):
+ self.name = name
+ self.network_on_disk = network_on_disk
+ self.te_multiplier = 1.0
+ self.unet_multiplier = 1.0
+ self.dyn_dim = None
+ self.modules = {}
+ self.mtime = None
+
+ self.mentioned_name = None
+ """the text that was used to add the network to prompt - can be either name or an alias"""
+
+
+class ModuleType:
+ def create_module(self, net: Network, weights: NetworkWeights) -> Network | None:
+ return None
+
+
+class NetworkModule:
+ def __init__(self, net: Network, weights: NetworkWeights):
+ self.network = net
+ self.network_key = weights.network_key
+ self.sd_key = weights.sd_key
+ self.sd_module = weights.sd_module
+
+ if hasattr(self.sd_module, 'weight'):
+ self.shape = self.sd_module.weight.shape
+
+ self.dim = None
+ self.bias = weights.w.get("bias")
+ self.alpha = weights.w["alpha"].item() if "alpha" in weights.w else None
+ self.scale = weights.w["scale"].item() if "scale" in weights.w else None
+
+ def multiplier(self):
+ if 'transformer' in self.sd_key[:20]:
+ return self.network.te_multiplier
+ else:
+ return self.network.unet_multiplier
+
+ def calc_scale(self):
+ if self.scale is not None:
+ return self.scale
+ if self.dim is not None and self.alpha is not None:
+ return self.alpha / self.dim
+
+ return 1.0
+
+ def finalize_updown(self, updown, orig_weight, output_shape):
+ if self.bias is not None:
+ updown = updown.reshape(self.bias.shape)
+ updown += self.bias.to(orig_weight.device, dtype=orig_weight.dtype)
+ updown = updown.reshape(output_shape)
+
+ if len(output_shape) == 4:
+ updown = updown.reshape(output_shape)
+
+ if orig_weight.size().numel() == updown.size().numel():
+ updown = updown.reshape(orig_weight.shape)
+
+ return updown * self.calc_scale() * self.multiplier()
+
+ def calc_updown(self, target):
+ raise NotImplementedError()
+
+ def forward(self, x, y):
+ raise NotImplementedError()
+
diff --git a/extensions-builtin/Lora/network_full.py b/extensions-builtin/Lora/network_full.py new file mode 100644 index 00000000..109b4c2c --- /dev/null +++ b/extensions-builtin/Lora/network_full.py @@ -0,0 +1,22 @@ +import network
+
+
+class ModuleTypeFull(network.ModuleType):
+ def create_module(self, net: network.Network, weights: network.NetworkWeights):
+ if all(x in weights.w for x in ["diff"]):
+ return NetworkModuleFull(net, weights)
+
+ return None
+
+
+class NetworkModuleFull(network.NetworkModule):
+ def __init__(self, net: network.Network, weights: network.NetworkWeights):
+ super().__init__(net, weights)
+
+ self.weight = weights.w.get("diff")
+
+ def calc_updown(self, orig_weight):
+ output_shape = self.weight.shape
+ updown = self.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+
+ return self.finalize_updown(updown, orig_weight, output_shape)
diff --git a/extensions-builtin/Lora/network_hada.py b/extensions-builtin/Lora/network_hada.py new file mode 100644 index 00000000..5fcb0695 --- /dev/null +++ b/extensions-builtin/Lora/network_hada.py @@ -0,0 +1,55 @@ +import lyco_helpers
+import network
+
+
+class ModuleTypeHada(network.ModuleType):
+ def create_module(self, net: network.Network, weights: network.NetworkWeights):
+ if all(x in weights.w for x in ["hada_w1_a", "hada_w1_b", "hada_w2_a", "hada_w2_b"]):
+ return NetworkModuleHada(net, weights)
+
+ return None
+
+
+class NetworkModuleHada(network.NetworkModule):
+ def __init__(self, net: network.Network, weights: network.NetworkWeights):
+ super().__init__(net, weights)
+
+ if hasattr(self.sd_module, 'weight'):
+ self.shape = self.sd_module.weight.shape
+
+ self.w1a = weights.w["hada_w1_a"]
+ self.w1b = weights.w["hada_w1_b"]
+ self.dim = self.w1b.shape[0]
+ self.w2a = weights.w["hada_w2_a"]
+ self.w2b = weights.w["hada_w2_b"]
+
+ self.t1 = weights.w.get("hada_t1")
+ self.t2 = weights.w.get("hada_t2")
+
+ def calc_updown(self, orig_weight):
+ w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
+ w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
+ w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
+ w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+
+ output_shape = [w1a.size(0), w1b.size(1)]
+
+ if self.t1 is not None:
+ output_shape = [w1a.size(1), w1b.size(1)]
+ t1 = self.t1.to(orig_weight.device, dtype=orig_weight.dtype)
+ updown1 = lyco_helpers.make_weight_cp(t1, w1a, w1b)
+ output_shape += t1.shape[2:]
+ else:
+ if len(w1b.shape) == 4:
+ output_shape += w1b.shape[2:]
+ updown1 = lyco_helpers.rebuild_conventional(w1a, w1b, output_shape)
+
+ if self.t2 is not None:
+ t2 = self.t2.to(orig_weight.device, dtype=orig_weight.dtype)
+ updown2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
+ else:
+ updown2 = lyco_helpers.rebuild_conventional(w2a, w2b, output_shape)
+
+ updown = updown1 * updown2
+
+ return self.finalize_updown(updown, orig_weight, output_shape)
diff --git a/extensions-builtin/Lora/network_ia3.py b/extensions-builtin/Lora/network_ia3.py new file mode 100644 index 00000000..7edc4249 --- /dev/null +++ b/extensions-builtin/Lora/network_ia3.py @@ -0,0 +1,30 @@ +import network
+
+
+class ModuleTypeIa3(network.ModuleType):
+ def create_module(self, net: network.Network, weights: network.NetworkWeights):
+ if all(x in weights.w for x in ["weight"]):
+ return NetworkModuleIa3(net, weights)
+
+ return None
+
+
+class NetworkModuleIa3(network.NetworkModule):
+ def __init__(self, net: network.Network, weights: network.NetworkWeights):
+ super().__init__(net, weights)
+
+ self.w = weights.w["weight"]
+ self.on_input = weights.w["on_input"].item()
+
+ def calc_updown(self, orig_weight):
+ w = self.w.to(orig_weight.device, dtype=orig_weight.dtype)
+
+ output_shape = [w.size(0), orig_weight.size(1)]
+ if self.on_input:
+ output_shape.reverse()
+ else:
+ w = w.reshape(-1, 1)
+
+ updown = orig_weight * w
+
+ return self.finalize_updown(updown, orig_weight, output_shape)
diff --git a/extensions-builtin/Lora/network_lokr.py b/extensions-builtin/Lora/network_lokr.py new file mode 100644 index 00000000..340acdab --- /dev/null +++ b/extensions-builtin/Lora/network_lokr.py @@ -0,0 +1,64 @@ +import torch
+
+import lyco_helpers
+import network
+
+
+class ModuleTypeLokr(network.ModuleType):
+ def create_module(self, net: network.Network, weights: network.NetworkWeights):
+ has_1 = "lokr_w1" in weights.w or ("lokr_w1_a" in weights.w and "lokr_w1_b" in weights.w)
+ has_2 = "lokr_w2" in weights.w or ("lokr_w2_a" in weights.w and "lokr_w2_b" in weights.w)
+ if has_1 and has_2:
+ return NetworkModuleLokr(net, weights)
+
+ return None
+
+
+def make_kron(orig_shape, w1, w2):
+ if len(w2.shape) == 4:
+ w1 = w1.unsqueeze(2).unsqueeze(2)
+ w2 = w2.contiguous()
+ return torch.kron(w1, w2).reshape(orig_shape)
+
+
+class NetworkModuleLokr(network.NetworkModule):
+ def __init__(self, net: network.Network, weights: network.NetworkWeights):
+ super().__init__(net, weights)
+
+ self.w1 = weights.w.get("lokr_w1")
+ self.w1a = weights.w.get("lokr_w1_a")
+ self.w1b = weights.w.get("lokr_w1_b")
+ self.dim = self.w1b.shape[0] if self.w1b is not None else self.dim
+ self.w2 = weights.w.get("lokr_w2")
+ self.w2a = weights.w.get("lokr_w2_a")
+ self.w2b = weights.w.get("lokr_w2_b")
+ self.dim = self.w2b.shape[0] if self.w2b is not None else self.dim
+ self.t2 = weights.w.get("lokr_t2")
+
+ def calc_updown(self, orig_weight):
+ if self.w1 is not None:
+ w1 = self.w1.to(orig_weight.device, dtype=orig_weight.dtype)
+ else:
+ w1a = self.w1a.to(orig_weight.device, dtype=orig_weight.dtype)
+ w1b = self.w1b.to(orig_weight.device, dtype=orig_weight.dtype)
+ w1 = w1a @ w1b
+
+ if self.w2 is not None:
+ w2 = self.w2.to(orig_weight.device, dtype=orig_weight.dtype)
+ elif self.t2 is None:
+ w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
+ w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+ w2 = w2a @ w2b
+ else:
+ t2 = self.t2.to(orig_weight.device, dtype=orig_weight.dtype)
+ w2a = self.w2a.to(orig_weight.device, dtype=orig_weight.dtype)
+ w2b = self.w2b.to(orig_weight.device, dtype=orig_weight.dtype)
+ w2 = lyco_helpers.make_weight_cp(t2, w2a, w2b)
+
+ output_shape = [w1.size(0) * w2.size(0), w1.size(1) * w2.size(1)]
+ if len(orig_weight.shape) == 4:
+ output_shape = orig_weight.shape
+
+ updown = make_kron(output_shape, w1, w2)
+
+ return self.finalize_updown(updown, orig_weight, output_shape)
diff --git a/extensions-builtin/Lora/network_lora.py b/extensions-builtin/Lora/network_lora.py new file mode 100644 index 00000000..26c0a72c --- /dev/null +++ b/extensions-builtin/Lora/network_lora.py @@ -0,0 +1,86 @@ +import torch
+
+import lyco_helpers
+import network
+from modules import devices
+
+
+class ModuleTypeLora(network.ModuleType):
+ def create_module(self, net: network.Network, weights: network.NetworkWeights):
+ if all(x in weights.w for x in ["lora_up.weight", "lora_down.weight"]):
+ return NetworkModuleLora(net, weights)
+
+ return None
+
+
+class NetworkModuleLora(network.NetworkModule):
+ def __init__(self, net: network.Network, weights: network.NetworkWeights):
+ super().__init__(net, weights)
+
+ self.up_model = self.create_module(weights.w, "lora_up.weight")
+ self.down_model = self.create_module(weights.w, "lora_down.weight")
+ self.mid_model = self.create_module(weights.w, "lora_mid.weight", none_ok=True)
+
+ self.dim = weights.w["lora_down.weight"].shape[0]
+
+ def create_module(self, weights, key, none_ok=False):
+ weight = weights.get(key)
+
+ if weight is None and none_ok:
+ return None
+
+ is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear, torch.nn.MultiheadAttention]
+ is_conv = type(self.sd_module) in [torch.nn.Conv2d]
+
+ if is_linear:
+ weight = weight.reshape(weight.shape[0], -1)
+ module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
+ elif is_conv and key == "lora_down.weight" or key == "dyn_up":
+ if len(weight.shape) == 2:
+ weight = weight.reshape(weight.shape[0], -1, 1, 1)
+
+ if weight.shape[2] != 1 or weight.shape[3] != 1:
+ module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], self.sd_module.kernel_size, self.sd_module.stride, self.sd_module.padding, bias=False)
+ else:
+ module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
+ elif is_conv and key == "lora_mid.weight":
+ module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], self.sd_module.kernel_size, self.sd_module.stride, self.sd_module.padding, bias=False)
+ elif is_conv and key == "lora_up.weight" or key == "dyn_down":
+ module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
+ else:
+ raise AssertionError(f'Lora layer {self.network_key} matched a layer with unsupported type: {type(self.sd_module).__name__}')
+
+ with torch.no_grad():
+ if weight.shape != module.weight.shape:
+ weight = weight.reshape(module.weight.shape)
+ module.weight.copy_(weight)
+
+ module.to(device=devices.cpu, dtype=devices.dtype)
+ module.weight.requires_grad_(False)
+
+ return module
+
+ def calc_updown(self, orig_weight):
+ up = self.up_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+ down = self.down_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+
+ output_shape = [up.size(0), down.size(1)]
+ if self.mid_model is not None:
+ # cp-decomposition
+ mid = self.mid_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
+ updown = lyco_helpers.rebuild_cp_decomposition(up, down, mid)
+ output_shape += mid.shape[2:]
+ else:
+ if len(down.shape) == 4:
+ output_shape += down.shape[2:]
+ updown = lyco_helpers.rebuild_conventional(up, down, output_shape, self.network.dyn_dim)
+
+ return self.finalize_updown(updown, orig_weight, output_shape)
+
+ def forward(self, x, y):
+ self.up_model.to(device=devices.device)
+ self.down_model.to(device=devices.device)
+
+ return y + self.up_model(self.down_model(x)) * self.multiplier() * self.calc_scale()
+
+
diff --git a/extensions-builtin/Lora/networks.py b/extensions-builtin/Lora/networks.py new file mode 100644 index 00000000..17cbe1bb --- /dev/null +++ b/extensions-builtin/Lora/networks.py @@ -0,0 +1,468 @@ +import os
+import re
+
+import network
+import network_lora
+import network_hada
+import network_ia3
+import network_lokr
+import network_full
+
+import torch
+from typing import Union
+
+from modules import shared, devices, sd_models, errors, scripts, sd_hijack
+
+module_types = [
+ network_lora.ModuleTypeLora(),
+ network_hada.ModuleTypeHada(),
+ network_ia3.ModuleTypeIa3(),
+ network_lokr.ModuleTypeLokr(),
+ network_full.ModuleTypeFull(),
+]
+
+
+re_digits = re.compile(r"\d+")
+re_x_proj = re.compile(r"(.*)_([qkv]_proj)$")
+re_compiled = {}
+
+suffix_conversion = {
+ "attentions": {},
+ "resnets": {
+ "conv1": "in_layers_2",
+ "conv2": "out_layers_3",
+ "time_emb_proj": "emb_layers_1",
+ "conv_shortcut": "skip_connection",
+ }
+}
+
+
+def convert_diffusers_name_to_compvis(key, is_sd2):
+ def match(match_list, regex_text):
+ regex = re_compiled.get(regex_text)
+ if regex is None:
+ regex = re.compile(regex_text)
+ re_compiled[regex_text] = regex
+
+ r = re.match(regex, key)
+ if not r:
+ return False
+
+ match_list.clear()
+ match_list.extend([int(x) if re.match(re_digits, x) else x for x in r.groups()])
+ return True
+
+ m = []
+
+ if match(m, r"lora_unet_conv_in(.*)"):
+ return f'diffusion_model_input_blocks_0_0{m[0]}'
+
+ if match(m, r"lora_unet_conv_out(.*)"):
+ return f'diffusion_model_out_2{m[0]}'
+
+ if match(m, r"lora_unet_time_embedding_linear_(\d+)(.*)"):
+ return f"diffusion_model_time_embed_{m[0] * 2 - 2}{m[1]}"
+
+ if match(m, r"lora_unet_down_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
+ suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
+ return f"diffusion_model_input_blocks_{1 + m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
+
+ if match(m, r"lora_unet_mid_block_(attentions|resnets)_(\d+)_(.+)"):
+ suffix = suffix_conversion.get(m[0], {}).get(m[2], m[2])
+ return f"diffusion_model_middle_block_{1 if m[0] == 'attentions' else m[1] * 2}_{suffix}"
+
+ if match(m, r"lora_unet_up_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
+ suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
+ return f"diffusion_model_output_blocks_{m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
+
+ if match(m, r"lora_unet_down_blocks_(\d+)_downsamplers_0_conv"):
+ return f"diffusion_model_input_blocks_{3 + m[0] * 3}_0_op"
+
+ if match(m, r"lora_unet_up_blocks_(\d+)_upsamplers_0_conv"):
+ return f"diffusion_model_output_blocks_{2 + m[0] * 3}_{2 if m[0]>0 else 1}_conv"
+
+ if match(m, r"lora_te_text_model_encoder_layers_(\d+)_(.+)"):
+ if is_sd2:
+ if 'mlp_fc1' in m[1]:
+ return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc1', 'mlp_c_fc')}"
+ elif 'mlp_fc2' in m[1]:
+ return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc2', 'mlp_c_proj')}"
+ else:
+ return f"model_transformer_resblocks_{m[0]}_{m[1].replace('self_attn', 'attn')}"
+
+ return f"transformer_text_model_encoder_layers_{m[0]}_{m[1]}"
+
+ if match(m, r"lora_te2_text_model_encoder_layers_(\d+)_(.+)"):
+ if 'mlp_fc1' in m[1]:
+ return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc1', 'mlp_c_fc')}"
+ elif 'mlp_fc2' in m[1]:
+ return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc2', 'mlp_c_proj')}"
+ else:
+ return f"1_model_transformer_resblocks_{m[0]}_{m[1].replace('self_attn', 'attn')}"
+
+ return key
+
+
+def assign_network_names_to_compvis_modules(sd_model):
+ network_layer_mapping = {}
+
+ if shared.sd_model.is_sdxl:
+ for i, embedder in enumerate(shared.sd_model.conditioner.embedders):
+ if not hasattr(embedder, 'wrapped'):
+ continue
+
+ for name, module in embedder.wrapped.named_modules():
+ network_name = f'{i}_{name.replace(".", "_")}'
+ network_layer_mapping[network_name] = module
+ module.network_layer_name = network_name
+ else:
+ for name, module in shared.sd_model.cond_stage_model.wrapped.named_modules():
+ network_name = name.replace(".", "_")
+ network_layer_mapping[network_name] = module
+ module.network_layer_name = network_name
+
+ for name, module in shared.sd_model.model.named_modules():
+ network_name = name.replace(".", "_")
+ network_layer_mapping[network_name] = module
+ module.network_layer_name = network_name
+
+ sd_model.network_layer_mapping = network_layer_mapping
+
+
+def load_network(name, network_on_disk):
+ net = network.Network(name, network_on_disk)
+ net.mtime = os.path.getmtime(network_on_disk.filename)
+
+ sd = sd_models.read_state_dict(network_on_disk.filename)
+
+ # this should not be needed but is here as an emergency fix for an unknown error people are experiencing in 1.2.0
+ if not hasattr(shared.sd_model, 'network_layer_mapping'):
+ assign_network_names_to_compvis_modules(shared.sd_model)
+
+ keys_failed_to_match = {}
+ is_sd2 = 'model_transformer_resblocks' in shared.sd_model.network_layer_mapping
+
+ matched_networks = {}
+
+ for key_network, weight in sd.items():
+ key_network_without_network_parts, network_part = key_network.split(".", 1)
+
+ key = convert_diffusers_name_to_compvis(key_network_without_network_parts, is_sd2)
+ sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
+ if sd_module is None:
+ m = re_x_proj.match(key)
+ if m:
+ sd_module = shared.sd_model.network_layer_mapping.get(m.group(1), None)
+
+ # SDXL loras seem to already have correct compvis keys, so only need to replace "lora_unet" with "diffusion_model"
+ if sd_module is None and "lora_unet" in key_network_without_network_parts:
+ key = key_network_without_network_parts.replace("lora_unet", "diffusion_model")
+ sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+ elif sd_module is None and "lora_te1_text_model" in key_network_without_network_parts:
+ key = key_network_without_network_parts.replace("lora_te1_text_model", "0_transformer_text_model")
+ sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
+ # some SD1 Loras also have correct compvis keys
+ if sd_module is None:
+ key = key_network_without_network_parts.replace("lora_te1_text_model", "transformer_text_model")
+ sd_module = shared.sd_model.network_layer_mapping.get(key, None)
+
+ if sd_module is None:
+ keys_failed_to_match[key_network] = key
+ continue
+
+ if key not in matched_networks:
+ matched_networks[key] = network.NetworkWeights(network_key=key_network, sd_key=key, w={}, sd_module=sd_module)
+
+ matched_networks[key].w[network_part] = weight
+
+ for key, weights in matched_networks.items():
+ net_module = None
+ for nettype in module_types:
+ net_module = nettype.create_module(net, weights)
+ if net_module is not None:
+ break
+
+ if net_module is None:
+ raise AssertionError(f"Could not find a module type (out of {', '.join([x.__class__.__name__ for x in module_types])}) that would accept those keys: {', '.join(weights.w)}")
+
+ net.modules[key] = net_module
+
+ if keys_failed_to_match:
+ print(f"Failed to match keys when loading network {network_on_disk.filename}: {keys_failed_to_match}")
+
+ return net
+
+
+def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=None):
+ already_loaded = {}
+
+ for net in loaded_networks:
+ if net.name in names:
+ already_loaded[net.name] = net
+
+ loaded_networks.clear()
+
+ networks_on_disk = [available_network_aliases.get(name, None) for name in names]
+ if any(x is None for x in networks_on_disk):
+ list_available_networks()
+
+ networks_on_disk = [available_network_aliases.get(name, None) for name in names]
+
+ failed_to_load_networks = []
+
+ for i, name in enumerate(names):
+ net = already_loaded.get(name, None)
+
+ network_on_disk = networks_on_disk[i]
+
+ if network_on_disk is not None:
+ if net is None or os.path.getmtime(network_on_disk.filename) > net.mtime:
+ try:
+ net = load_network(name, network_on_disk)
+ except Exception as e:
+ errors.display(e, f"loading network {network_on_disk.filename}")
+ continue
+
+ net.mentioned_name = name
+
+ network_on_disk.read_hash()
+
+ if net is None:
+ failed_to_load_networks.append(name)
+ print(f"Couldn't find network with name {name}")
+ continue
+
+ net.te_multiplier = te_multipliers[i] if te_multipliers else 1.0
+ net.unet_multiplier = unet_multipliers[i] if unet_multipliers else 1.0
+ net.dyn_dim = dyn_dims[i] if dyn_dims else 1.0
+ loaded_networks.append(net)
+
+ if failed_to_load_networks:
+ sd_hijack.model_hijack.comments.append("Failed to find networks: " + ", ".join(failed_to_load_networks))
+
+
+def network_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]):
+ weights_backup = getattr(self, "network_weights_backup", None)
+
+ if weights_backup is None:
+ return
+
+ if isinstance(self, torch.nn.MultiheadAttention):
+ self.in_proj_weight.copy_(weights_backup[0])
+ self.out_proj.weight.copy_(weights_backup[1])
+ else:
+ self.weight.copy_(weights_backup)
+
+
+def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]):
+ """
+ Applies the currently selected set of networks to the weights of torch layer self.
+ If weights already have this particular set of networks applied, does nothing.
+ If not, restores orginal weights from backup and alters weights according to networks.
+ """
+
+ network_layer_name = getattr(self, 'network_layer_name', None)
+ if network_layer_name is None:
+ return
+
+ current_names = getattr(self, "network_current_names", ())
+ wanted_names = tuple((x.name, x.te_multiplier, x.unet_multiplier, x.dyn_dim) for x in loaded_networks)
+
+ weights_backup = getattr(self, "network_weights_backup", None)
+ if weights_backup is None:
+ if isinstance(self, torch.nn.MultiheadAttention):
+ weights_backup = (self.in_proj_weight.to(devices.cpu, copy=True), self.out_proj.weight.to(devices.cpu, copy=True))
+ else:
+ weights_backup = self.weight.to(devices.cpu, copy=True)
+
+ self.network_weights_backup = weights_backup
+
+ if current_names != wanted_names:
+ network_restore_weights_from_backup(self)
+
+ for net in loaded_networks:
+ module = net.modules.get(network_layer_name, None)
+ if module is not None and hasattr(self, 'weight'):
+ with torch.no_grad():
+ updown = module.calc_updown(self.weight)
+
+ if len(self.weight.shape) == 4 and self.weight.shape[1] == 9:
+ # inpainting model. zero pad updown to make channel[1] 4 to 9
+ updown = torch.nn.functional.pad(updown, (0, 0, 0, 0, 0, 5))
+
+ self.weight += updown
+ continue
+
+ module_q = net.modules.get(network_layer_name + "_q_proj", None)
+ module_k = net.modules.get(network_layer_name + "_k_proj", None)
+ module_v = net.modules.get(network_layer_name + "_v_proj", None)
+ module_out = net.modules.get(network_layer_name + "_out_proj", None)
+
+ if isinstance(self, torch.nn.MultiheadAttention) and module_q and module_k and module_v and module_out:
+ with torch.no_grad():
+ updown_q = module_q.calc_updown(self.in_proj_weight)
+ updown_k = module_k.calc_updown(self.in_proj_weight)
+ updown_v = module_v.calc_updown(self.in_proj_weight)
+ updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
+ updown_out = module_out.calc_updown(self.out_proj.weight)
+
+ self.in_proj_weight += updown_qkv
+ self.out_proj.weight += updown_out
+ continue
+
+ if module is None:
+ continue
+
+ print(f'failed to calculate network weights for layer {network_layer_name}')
+
+ self.network_current_names = wanted_names
+
+
+def network_forward(module, input, original_forward):
+ """
+ Old way of applying Lora by executing operations during layer's forward.
+ Stacking many loras this way results in big performance degradation.
+ """
+
+ if len(loaded_networks) == 0:
+ return original_forward(module, input)
+
+ input = devices.cond_cast_unet(input)
+
+ network_restore_weights_from_backup(module)
+ network_reset_cached_weight(module)
+
+ y = original_forward(module, input)
+
+ network_layer_name = getattr(module, 'network_layer_name', None)
+ for lora in loaded_networks:
+ module = lora.modules.get(network_layer_name, None)
+ if module is None:
+ continue
+
+ y = module.forward(y, input)
+
+ return y
+
+
+def network_reset_cached_weight(self: Union[torch.nn.Conv2d, torch.nn.Linear]):
+ self.network_current_names = ()
+ self.network_weights_backup = None
+
+
+def network_Linear_forward(self, input):
+ if shared.opts.lora_functional:
+ return network_forward(self, input, torch.nn.Linear_forward_before_network)
+
+ network_apply_weights(self)
+
+ return torch.nn.Linear_forward_before_network(self, input)
+
+
+def network_Linear_load_state_dict(self, *args, **kwargs):
+ network_reset_cached_weight(self)
+
+ return torch.nn.Linear_load_state_dict_before_network(self, *args, **kwargs)
+
+
+def network_Conv2d_forward(self, input):
+ if shared.opts.lora_functional:
+ return network_forward(self, input, torch.nn.Conv2d_forward_before_network)
+
+ network_apply_weights(self)
+
+ return torch.nn.Conv2d_forward_before_network(self, input)
+
+
+def network_Conv2d_load_state_dict(self, *args, **kwargs):
+ network_reset_cached_weight(self)
+
+ return torch.nn.Conv2d_load_state_dict_before_network(self, *args, **kwargs)
+
+
+def network_MultiheadAttention_forward(self, *args, **kwargs):
+ network_apply_weights(self)
+
+ return torch.nn.MultiheadAttention_forward_before_network(self, *args, **kwargs)
+
+
+def network_MultiheadAttention_load_state_dict(self, *args, **kwargs):
+ network_reset_cached_weight(self)
+
+ return torch.nn.MultiheadAttention_load_state_dict_before_network(self, *args, **kwargs)
+
+
+def list_available_networks():
+ available_networks.clear()
+ available_network_aliases.clear()
+ forbidden_network_aliases.clear()
+ available_network_hash_lookup.clear()
+ forbidden_network_aliases.update({"none": 1, "Addams": 1})
+
+ os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
+
+ candidates = list(shared.walk_files(shared.cmd_opts.lora_dir, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
+ candidates += list(shared.walk_files(shared.cmd_opts.lyco_dir_backcompat, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
+ for filename in candidates:
+ if os.path.isdir(filename):
+ continue
+
+ name = os.path.splitext(os.path.basename(filename))[0]
+ try:
+ entry = network.NetworkOnDisk(name, filename)
+ except OSError: # should catch FileNotFoundError and PermissionError etc.
+ errors.report(f"Failed to load network {name} from {filename}", exc_info=True)
+ continue
+
+ available_networks[name] = entry
+
+ if entry.alias in available_network_aliases:
+ forbidden_network_aliases[entry.alias.lower()] = 1
+
+ available_network_aliases[name] = entry
+ available_network_aliases[entry.alias] = entry
+
+
+re_network_name = re.compile(r"(.*)\s*\([0-9a-fA-F]+\)")
+
+
+def infotext_pasted(infotext, params):
+ if "AddNet Module 1" in [x[1] for x in scripts.scripts_txt2img.infotext_fields]:
+ return # if the other extension is active, it will handle those fields, no need to do anything
+
+ added = []
+
+ for k in params:
+ if not k.startswith("AddNet Model "):
+ continue
+
+ num = k[13:]
+
+ if params.get("AddNet Module " + num) != "LoRA":
+ continue
+
+ name = params.get("AddNet Model " + num)
+ if name is None:
+ continue
+
+ m = re_network_name.match(name)
+ if m:
+ name = m.group(1)
+
+ multiplier = params.get("AddNet Weight A " + num, "1.0")
+
+ added.append(f"<lora:{name}:{multiplier}>")
+
+ if added:
+ params["Prompt"] += "\n" + "".join(added)
+
+
+available_networks = {}
+available_network_aliases = {}
+loaded_networks = []
+available_network_hash_lookup = {}
+forbidden_network_aliases = {}
+
+list_available_networks()
diff --git a/extensions-builtin/Lora/preload.py b/extensions-builtin/Lora/preload.py index 863dc5c0..50961be3 100644 --- a/extensions-builtin/Lora/preload.py +++ b/extensions-builtin/Lora/preload.py @@ -4,3 +4,4 @@ from modules import paths def preload(parser):
parser.add_argument("--lora-dir", type=str, help="Path to directory with Lora networks.", default=os.path.join(paths.models_path, 'Lora'))
+ parser.add_argument("--lyco-dir-backcompat", type=str, help="Path to directory with LyCORIS networks (for backawards compatibility; can also use --lyco-dir).", default=os.path.join(paths.models_path, 'LyCORIS'))
diff --git a/extensions-builtin/Lora/scripts/lora_script.py b/extensions-builtin/Lora/scripts/lora_script.py index e650f469..cd28afc9 100644 --- a/extensions-builtin/Lora/scripts/lora_script.py +++ b/extensions-builtin/Lora/scripts/lora_script.py @@ -4,69 +4,76 @@ import torch import gradio as gr
from fastapi import FastAPI
-import lora
+import network
+import networks
+import lora # noqa:F401
import extra_networks_lora
import ui_extra_networks_lora
from modules import script_callbacks, ui_extra_networks, extra_networks, shared
def unload():
- torch.nn.Linear.forward = torch.nn.Linear_forward_before_lora
- torch.nn.Linear._load_from_state_dict = torch.nn.Linear_load_state_dict_before_lora
- torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_lora
- torch.nn.Conv2d._load_from_state_dict = torch.nn.Conv2d_load_state_dict_before_lora
- torch.nn.MultiheadAttention.forward = torch.nn.MultiheadAttention_forward_before_lora
- torch.nn.MultiheadAttention._load_from_state_dict = torch.nn.MultiheadAttention_load_state_dict_before_lora
+ torch.nn.Linear.forward = torch.nn.Linear_forward_before_network
+ torch.nn.Linear._load_from_state_dict = torch.nn.Linear_load_state_dict_before_network
+ torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_network
+ torch.nn.Conv2d._load_from_state_dict = torch.nn.Conv2d_load_state_dict_before_network
+ torch.nn.MultiheadAttention.forward = torch.nn.MultiheadAttention_forward_before_network
+ torch.nn.MultiheadAttention._load_from_state_dict = torch.nn.MultiheadAttention_load_state_dict_before_network
def before_ui():
ui_extra_networks.register_page(ui_extra_networks_lora.ExtraNetworksPageLora())
- extra_networks.register_extra_network(extra_networks_lora.ExtraNetworkLora())
+ extra_network = extra_networks_lora.ExtraNetworkLora()
+ extra_networks.register_extra_network(extra_network)
+ extra_networks.register_extra_network_alias(extra_network, "lyco")
-if not hasattr(torch.nn, 'Linear_forward_before_lora'):
- torch.nn.Linear_forward_before_lora = torch.nn.Linear.forward
-if not hasattr(torch.nn, 'Linear_load_state_dict_before_lora'):
- torch.nn.Linear_load_state_dict_before_lora = torch.nn.Linear._load_from_state_dict
+if not hasattr(torch.nn, 'Linear_forward_before_network'):
+ torch.nn.Linear_forward_before_network = torch.nn.Linear.forward
-if not hasattr(torch.nn, 'Conv2d_forward_before_lora'):
- torch.nn.Conv2d_forward_before_lora = torch.nn.Conv2d.forward
+if not hasattr(torch.nn, 'Linear_load_state_dict_before_network'):
+ torch.nn.Linear_load_state_dict_before_network = torch.nn.Linear._load_from_state_dict
-if not hasattr(torch.nn, 'Conv2d_load_state_dict_before_lora'):
- torch.nn.Conv2d_load_state_dict_before_lora = torch.nn.Conv2d._load_from_state_dict
+if not hasattr(torch.nn, 'Conv2d_forward_before_network'):
+ torch.nn.Conv2d_forward_before_network = torch.nn.Conv2d.forward
-if not hasattr(torch.nn, 'MultiheadAttention_forward_before_lora'):
- torch.nn.MultiheadAttention_forward_before_lora = torch.nn.MultiheadAttention.forward
+if not hasattr(torch.nn, 'Conv2d_load_state_dict_before_network'):
+ torch.nn.Conv2d_load_state_dict_before_network = torch.nn.Conv2d._load_from_state_dict
-if not hasattr(torch.nn, 'MultiheadAttention_load_state_dict_before_lora'):
- torch.nn.MultiheadAttention_load_state_dict_before_lora = torch.nn.MultiheadAttention._load_from_state_dict
+if not hasattr(torch.nn, 'MultiheadAttention_forward_before_network'):
+ torch.nn.MultiheadAttention_forward_before_network = torch.nn.MultiheadAttention.forward
-torch.nn.Linear.forward = lora.lora_Linear_forward
-torch.nn.Linear._load_from_state_dict = lora.lora_Linear_load_state_dict
-torch.nn.Conv2d.forward = lora.lora_Conv2d_forward
-torch.nn.Conv2d._load_from_state_dict = lora.lora_Conv2d_load_state_dict
-torch.nn.MultiheadAttention.forward = lora.lora_MultiheadAttention_forward
-torch.nn.MultiheadAttention._load_from_state_dict = lora.lora_MultiheadAttention_load_state_dict
+if not hasattr(torch.nn, 'MultiheadAttention_load_state_dict_before_network'):
+ torch.nn.MultiheadAttention_load_state_dict_before_network = torch.nn.MultiheadAttention._load_from_state_dict
-script_callbacks.on_model_loaded(lora.assign_lora_names_to_compvis_modules)
+torch.nn.Linear.forward = networks.network_Linear_forward
+torch.nn.Linear._load_from_state_dict = networks.network_Linear_load_state_dict
+torch.nn.Conv2d.forward = networks.network_Conv2d_forward
+torch.nn.Conv2d._load_from_state_dict = networks.network_Conv2d_load_state_dict
+torch.nn.MultiheadAttention.forward = networks.network_MultiheadAttention_forward
+torch.nn.MultiheadAttention._load_from_state_dict = networks.network_MultiheadAttention_load_state_dict
+
+script_callbacks.on_model_loaded(networks.assign_network_names_to_compvis_modules)
script_callbacks.on_script_unloaded(unload)
script_callbacks.on_before_ui(before_ui)
-script_callbacks.on_infotext_pasted(lora.infotext_pasted)
+script_callbacks.on_infotext_pasted(networks.infotext_pasted)
shared.options_templates.update(shared.options_section(('extra_networks', "Extra Networks"), {
- "sd_lora": shared.OptionInfo("None", "Add Lora to prompt", gr.Dropdown, lambda: {"choices": ["None", *lora.available_loras]}, refresh=lora.list_available_loras),
+ "sd_lora": shared.OptionInfo("None", "Add network to prompt", gr.Dropdown, lambda: {"choices": ["None", *networks.available_networks]}, refresh=networks.list_available_networks),
"lora_preferred_name": shared.OptionInfo("Alias from file", "When adding to prompt, refer to Lora by", gr.Radio, {"choices": ["Alias from file", "Filename"]}),
"lora_add_hashes_to_infotext": shared.OptionInfo(True, "Add Lora hashes to infotext"),
+ "lora_show_all": shared.OptionInfo(False, "Always show all networks on the Lora page").info("otherwise, those detected as for incompatible version of Stable Diffusion will be hidden"),
+ "lora_hide_unknown_for_versions": shared.OptionInfo([], "Hide networks of unknown versions for model versions", gr.CheckboxGroup, {"choices": ["SD1", "SD2", "SDXL"]}),
}))
shared.options_templates.update(shared.options_section(('compatibility', "Compatibility"), {
- "lora_functional": shared.OptionInfo(False, "Lora: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension"),
+ "lora_functional": shared.OptionInfo(False, "Lora/Networks: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension"),
}))
-def create_lora_json(obj: lora.LoraOnDisk):
+def create_lora_json(obj: network.NetworkOnDisk):
return {
"name": obj.name,
"alias": obj.alias,
@@ -75,17 +82,17 @@ def create_lora_json(obj: lora.LoraOnDisk): }
-def api_loras(_: gr.Blocks, app: FastAPI):
+def api_networks(_: gr.Blocks, app: FastAPI):
@app.get("/sdapi/v1/loras")
async def get_loras():
- return [create_lora_json(obj) for obj in lora.available_loras.values()]
+ return [create_lora_json(obj) for obj in networks.available_networks.values()]
@app.post("/sdapi/v1/refresh-loras")
async def refresh_loras():
- return lora.list_available_loras()
+ return networks.list_available_networks()
-script_callbacks.on_app_started(api_loras)
+script_callbacks.on_app_started(api_networks)
re_lora = re.compile("<lora:([^:]+):")
@@ -98,19 +105,19 @@ def infotext_pasted(infotext, d): hashes = [x.strip().split(':', 1) for x in hashes.split(",")]
hashes = {x[0].strip().replace(",", ""): x[1].strip() for x in hashes}
- def lora_replacement(m):
+ def network_replacement(m):
alias = m.group(1)
shorthash = hashes.get(alias)
if shorthash is None:
return m.group(0)
- lora_on_disk = lora.available_lora_hash_lookup.get(shorthash)
- if lora_on_disk is None:
+ network_on_disk = networks.available_network_hash_lookup.get(shorthash)
+ if network_on_disk is None:
return m.group(0)
- return f'<lora:{lora_on_disk.get_alias()}:'
+ return f'<lora:{network_on_disk.get_alias()}:'
- d["Prompt"] = re.sub(re_lora, lora_replacement, d["Prompt"])
+ d["Prompt"] = re.sub(re_lora, network_replacement, d["Prompt"])
script_callbacks.on_infotext_pasted(infotext_pasted)
diff --git a/extensions-builtin/Lora/ui_edit_user_metadata.py b/extensions-builtin/Lora/ui_edit_user_metadata.py index 354a1d68..390d9dde 100644 --- a/extensions-builtin/Lora/ui_edit_user_metadata.py +++ b/extensions-builtin/Lora/ui_edit_user_metadata.py @@ -1,3 +1,4 @@ +import datetime
import html
import random
@@ -46,14 +47,17 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) def __init__(self, ui, tabname, page):
super().__init__(ui, tabname, page)
+ self.select_sd_version = None
+
self.taginfo = None
self.edit_activation_text = None
self.slider_preferred_weight = None
self.edit_notes = None
- def save_lora_user_metadata(self, name, desc, activation_text, preferred_weight, notes):
+ def save_lora_user_metadata(self, name, desc, sd_version, activation_text, preferred_weight, notes):
user_metadata = self.get_user_metadata(name)
user_metadata["description"] = desc
+ user_metadata["sd version"] = sd_version
user_metadata["activation text"] = activation_text
user_metadata["preferred weight"] = preferred_weight
user_metadata["notes"] = notes
@@ -68,6 +72,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) keys = {
'ss_sd_model_name': "Model:",
'ss_clip_skip': "Clip skip:",
+ 'ss_network_module': "Kohya module:",
}
for key, label in keys.items():
@@ -75,6 +80,10 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) if value is not None and str(value) != "None":
table.append((label, html.escape(value)))
+ ss_training_started_at = metadata.get('ss_training_started_at')
+ if ss_training_started_at:
+ table.append(("Date trained:", datetime.datetime.utcfromtimestamp(float(ss_training_started_at)).strftime('%Y-%m-%d %H:%M')))
+
ss_bucket_info = metadata.get("ss_bucket_info")
if ss_bucket_info and "buckets" in ss_bucket_info:
resolutions = {}
@@ -112,11 +121,11 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) gradio_tags = [(tag, str(count)) for tag, count in tags[0:24]]
return [
- *values[0:4],
+ *values[0:5],
+ item.get("sd_version", "Unknown"),
gr.HighlightedText.update(value=gradio_tags, visible=True if tags else False),
user_metadata.get('activation text', ''),
float(user_metadata.get('preferred weight', 0.0)),
- user_metadata.get('notes', ''),
gr.update(visible=True if tags else False),
gr.update(value=self.generate_random_prompt_from_tags(tags), visible=True if tags else False),
]
@@ -141,10 +150,15 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) return ", ".join(sorted(res))
+ def create_extra_default_items_in_left_column(self):
+
+ # this would be a lot better as gr.Radio but I can't make it work
+ self.select_sd_version = gr.Dropdown(['SD1', 'SD2', 'SDXL', 'Unknown'], value='Unknown', label='Stable Diffusion version', interactive=True)
+
def create_editor(self):
self.create_default_editor_elems()
- self.taginfo = gr.HighlightedText(label="Tags")
+ self.taginfo = gr.HighlightedText(label="Training dataset tags")
self.edit_activation_text = gr.Text(label='Activation text', info="Will be added to prompt along with Lora")
self.slider_preferred_weight = gr.Slider(label='Preferred weight', info="Set to 0 to disable", minimum=0.0, maximum=2.0, step=0.01)
@@ -153,7 +167,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) random_prompt = gr.Textbox(label='Random prompt', lines=4, max_lines=4, interactive=False)
with gr.Column(scale=1, min_width=120):
- generate_random_prompt = gr.Button('Generate').style(full_width=True, size="lg")
+ generate_random_prompt = gr.Button('Generate', size="lg", scale=1)
self.edit_notes = gr.TextArea(label='Notes', lines=4)
@@ -178,10 +192,11 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) self.edit_description,
self.html_filedata,
self.html_preview,
+ self.edit_notes,
+ self.select_sd_version,
self.taginfo,
self.edit_activation_text,
self.slider_preferred_weight,
- self.edit_notes,
row_random_prompt,
random_prompt,
]
@@ -192,6 +207,7 @@ class LoraUserMetadataEditor(ui_extra_networks_user_metadata.UserMetadataEditor) edited_components = [
self.edit_description,
+ self.select_sd_version,
self.edit_activation_text,
self.slider_preferred_weight,
self.edit_notes,
diff --git a/extensions-builtin/Lora/ui_extra_networks_lora.py b/extensions-builtin/Lora/ui_extra_networks_lora.py index b2bc1810..3629e5c0 100644 --- a/extensions-builtin/Lora/ui_extra_networks_lora.py +++ b/extensions-builtin/Lora/ui_extra_networks_lora.py @@ -1,5 +1,7 @@ import os
-import lora
+
+import network
+import networks
from modules import shared, ui_extra_networks
from modules.ui_extra_networks import quote_js
@@ -11,16 +13,15 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage): super().__init__('Lora')
def refresh(self):
- lora.list_available_loras()
+ networks.list_available_networks()
- def create_item(self, name, index=None):
- lora_on_disk = lora.available_loras.get(name)
+ def create_item(self, name, index=None, enable_filter=True):
+ lora_on_disk = networks.available_networks.get(name)
path, ext = os.path.splitext(lora_on_disk.filename)
alias = lora_on_disk.get_alias()
- # in 1.5 filename changes to be full filename instead of path without extension, and metadata is dict instead of json string
item = {
"name": name,
"filename": lora_on_disk.filename,
@@ -30,6 +31,7 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage): "local_preview": f"{path}.{shared.opts.samples_format}",
"metadata": lora_on_disk.metadata,
"sort_keys": {'default': index, **self.get_sort_keys(lora_on_disk.filename)},
+ "sd_version": lora_on_disk.sd_version.name,
}
self.read_user_metadata(item)
@@ -40,15 +42,37 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage): if activation_text:
item["prompt"] += " + " + quote_js(" " + activation_text)
+ sd_version = item["user_metadata"].get("sd version")
+ if sd_version in network.SdVersion.__members__:
+ item["sd_version"] = sd_version
+ sd_version = network.SdVersion[sd_version]
+ else:
+ sd_version = lora_on_disk.sd_version
+
+ if shared.opts.lora_show_all or not enable_filter:
+ pass
+ elif sd_version == network.SdVersion.Unknown:
+ model_version = network.SdVersion.SDXL if shared.sd_model.is_sdxl else network.SdVersion.SD2 if shared.sd_model.is_sd2 else network.SdVersion.SD1
+ if model_version.name in shared.opts.lora_hide_unknown_for_versions:
+ return None
+ elif shared.sd_model.is_sdxl and sd_version != network.SdVersion.SDXL:
+ return None
+ elif shared.sd_model.is_sd2 and sd_version != network.SdVersion.SD2:
+ return None
+ elif shared.sd_model.is_sd1 and sd_version != network.SdVersion.SD1:
+ return None
+
return item
def list_items(self):
- for index, name in enumerate(lora.available_loras):
+ for index, name in enumerate(networks.available_networks):
item = self.create_item(name, index)
- yield item
+
+ if item is not None:
+ yield item
def allowed_directories_for_previews(self):
- return [shared.cmd_opts.lora_dir]
+ return [shared.cmd_opts.lora_dir, shared.cmd_opts.lyco_dir_backcompat]
def create_user_metadata_editor(self, ui, tabname):
return LoraUserMetadataEditor(ui, tabname, self)
diff --git a/html/extra-networks-card.html b/html/extra-networks-card.html index eb8b1a67..39674666 100644 --- a/html/extra-networks-card.html +++ b/html/extra-networks-card.html @@ -1,8 +1,8 @@ <div class='card' style={style} onclick={card_clicked} data-name="{name}" {sort_keys}> {background_image} <div class="button-row"> - {edit_button} {metadata_button} + {edit_button} </div> <div class='actions'> <div class='additional'> diff --git a/javascript/badScaleChecker.js b/javascript/badScaleChecker.js deleted file mode 100644 index 625ad309..00000000 --- a/javascript/badScaleChecker.js +++ /dev/null @@ -1,108 +0,0 @@ -(function() { - var ignore = localStorage.getItem("bad-scale-ignore-it") == "ignore-it"; - - function getScale() { - var ratio = 0, - screen = window.screen, - ua = navigator.userAgent.toLowerCase(); - - if (window.devicePixelRatio !== undefined) { - ratio = window.devicePixelRatio; - } else if (~ua.indexOf('msie')) { - if (screen.deviceXDPI && screen.logicalXDPI) { - ratio = screen.deviceXDPI / screen.logicalXDPI; - } - } else if (window.outerWidth !== undefined && window.innerWidth !== undefined) { - ratio = window.outerWidth / window.innerWidth; - } - - return ratio == 0 ? 0 : Math.round(ratio * 100); - } - - var showing = false; - - var div = document.createElement("div"); - div.style.position = "fixed"; - div.style.top = "0px"; - div.style.left = "0px"; - div.style.width = "100vw"; - div.style.backgroundColor = "firebrick"; - div.style.textAlign = "center"; - div.style.zIndex = 99; - - var b = document.createElement("b"); - b.innerHTML = 'Bad Scale: ??% '; - - div.appendChild(b); - - var note1 = document.createElement("p"); - note1.innerHTML = "Change your browser or your computer settings!"; - note1.title = 'Just make sure "computer-scale" * "browser-scale" = 100% ,\n' + - "you can keep your computer-scale and only change this page's scale,\n" + - "for example: your computer-scale is 125%, just use [\"CTRL\"+\"-\"] to make your browser-scale of this page to 80%."; - div.appendChild(note1); - - var note2 = document.createElement("p"); - note2.innerHTML = " Otherwise, it will cause this page to not function properly!"; - note2.title = "When you click \"Copy image to: [inpaint sketch]\" in some img2img's tab,\n" + - "if scale<100% the canvas will be invisible,\n" + - "else if scale>100% this page will take large amount of memory and CPU performance."; - div.appendChild(note2); - - var btn = document.createElement("button"); - btn.innerHTML = "Click here to ignore"; - - div.appendChild(btn); - - function tryShowTopBar(scale) { - if (showing) return; - - b.innerHTML = 'Bad Scale: ' + scale + '% '; - - var updateScaleTimer = setInterval(function() { - var newScale = getScale(); - b.innerHTML = 'Bad Scale: ' + newScale + '% '; - if (newScale == 100) { - var p = div.parentNode; - if (p != null) p.removeChild(div); - showing = false; - clearInterval(updateScaleTimer); - check(); - } - }, 999); - - btn.onclick = function() { - clearInterval(updateScaleTimer); - var p = div.parentNode; - if (p != null) p.removeChild(div); - ignore = true; - showing = false; - localStorage.setItem("bad-scale-ignore-it", "ignore-it"); - }; - - document.body.appendChild(div); - } - - function check() { - if (!ignore) { - var timer = setInterval(function() { - var scale = getScale(); - if (scale != 100 && !ignore) { - tryShowTopBar(scale); - clearInterval(timer); - } - if (ignore) { - clearInterval(timer); - } - }, 999); - } - } - - if (document.readyState != "complete") { - document.onreadystatechange = function() { - if (document.readyState != "complete") check(); - }; - } else { - check(); - } -})(); diff --git a/javascript/extraNetworks.js b/javascript/extraNetworks.js index e453094a..5582a6e5 100644 --- a/javascript/extraNetworks.js +++ b/javascript/extraNetworks.js @@ -213,7 +213,7 @@ function popup(contents) { globalPopupInner.classList.add('global-popup-inner'); globalPopup.appendChild(globalPopupInner); - gradioApp().appendChild(globalPopup); + gradioApp().querySelector('.main').appendChild(globalPopup); } globalPopupInner.innerHTML = ''; diff --git a/javascript/hints.js b/javascript/hints.js index 4167cb28..6de9372e 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -190,3 +190,14 @@ onUiUpdate(function(mutationRecords) { tooltipCheckTimer = setTimeout(processTooltipCheckNodes, 1000); } }); + +onUiLoaded(function() { + for (var comp of window.gradio_config.components) { + if (comp.props.webui_tooltip && comp.props.elem_id) { + var elem = gradioApp().getElementById(comp.props.elem_id); + if (elem) { + elem.title = comp.props.webui_tooltip; + } + } + } +}); diff --git a/javascript/ui.js b/javascript/ui.js index d70a681b..abf23a78 100644 --- a/javascript/ui.js +++ b/javascript/ui.js @@ -152,7 +152,11 @@ function submit() { showSubmitButtons('txt2img', false); var id = randomId(); - localStorage.setItem("txt2img_task_id", id); + try { + localStorage.setItem("txt2img_task_id", id); + } catch (e) { + console.warn(`Failed to save txt2img task id to localStorage: ${e}`); + } requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() { showSubmitButtons('txt2img', true); @@ -171,7 +175,11 @@ function submit_img2img() { showSubmitButtons('img2img', false); var id = randomId(); - localStorage.setItem("img2img_task_id", id); + try { + localStorage.setItem("img2img_task_id", id); + } catch (e) { + console.warn(`Failed to save img2img task id to localStorage: ${e}`); + } requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() { showSubmitButtons('img2img', true); @@ -191,8 +199,6 @@ function restoreProgressTxt2img() { showRestoreProgressButton("txt2img", false); var id = localStorage.getItem("txt2img_task_id"); - id = localStorage.getItem("txt2img_task_id"); - if (id) { requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() { showSubmitButtons('txt2img', true); @@ -1,6 +1,5 @@ from modules import launch_utils
-
args = launch_utils.args
python = launch_utils.python
git = launch_utils.git
@@ -18,6 +17,7 @@ run_pip = launch_utils.run_pip check_run_python = launch_utils.check_run_python
git_clone = launch_utils.git_clone
git_pull_recursive = launch_utils.git_pull_recursive
+list_extensions = launch_utils.list_extensions
run_extension_installer = launch_utils.run_extension_installer
prepare_environment = launch_utils.prepare_environment
configure_for_tests = launch_utils.configure_for_tests
@@ -25,8 +25,11 @@ start = launch_utils.start def main():
- if not args.skip_prepare_environment:
- prepare_environment()
+ launch_utils.startup_timer.record("initial startup")
+
+ with launch_utils.startup_timer.subcategory("prepare environment"):
+ if not args.skip_prepare_environment:
+ prepare_environment()
if args.test_server:
configure_for_tests()
diff --git a/modules/api/api.py b/modules/api/api.py index 2a4cd8a2..908c4514 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -15,7 +15,7 @@ from fastapi.encoders import jsonable_encoder from secrets import compare_digest import modules.shared as shared -from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart +from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items from modules.api import models from modules.shared import opts from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images @@ -197,6 +197,7 @@ class Api: self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[models.PromptStyleItem]) self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse) self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"]) + self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"]) self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse) self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse) self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse) @@ -333,14 +334,17 @@ class Api: p.outpath_grids = opts.outdir_txt2img_grids p.outpath_samples = opts.outdir_txt2img_samples - shared.state.begin(job="scripts_txt2img") - if selectable_scripts is not None: - p.script_args = script_args - processed = scripts.scripts_txt2img.run(p, *p.script_args) # Need to pass args as list here - else: - p.script_args = tuple(script_args) # Need to pass args as tuple here - processed = process_images(p) - shared.state.end() + try: + shared.state.begin(job="scripts_txt2img") + if selectable_scripts is not None: + p.script_args = script_args + processed = scripts.scripts_txt2img.run(p, *p.script_args) # Need to pass args as list here + else: + p.script_args = tuple(script_args) # Need to pass args as tuple here + processed = process_images(p) + finally: + shared.state.end() + shared.total_tqdm.clear() b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else [] @@ -390,14 +394,17 @@ class Api: p.outpath_grids = opts.outdir_img2img_grids p.outpath_samples = opts.outdir_img2img_samples - shared.state.begin(job="scripts_img2img") - if selectable_scripts is not None: - p.script_args = script_args - processed = scripts.scripts_img2img.run(p, *p.script_args) # Need to pass args as list here - else: - p.script_args = tuple(script_args) # Need to pass args as tuple here - processed = process_images(p) - shared.state.end() + try: + shared.state.begin(job="scripts_img2img") + if selectable_scripts is not None: + p.script_args = script_args + processed = scripts.scripts_img2img.run(p, *p.script_args) # Need to pass args as list here + else: + p.script_args = tuple(script_args) # Need to pass args as tuple here + processed = process_images(p) + finally: + shared.state.end() + shared.total_tqdm.clear() b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else [] @@ -604,6 +611,10 @@ class Api: with self.queue_lock: shared.refresh_checkpoints() + def refresh_vae(self): + with self.queue_lock: + shared_items.refresh_vae_list() + def create_embedding(self, args: dict): try: shared.state.begin(job="create_embedding") @@ -720,9 +731,9 @@ class Api: cuda = {'error': f'{err}'} return models.MemoryResponse(ram=ram, cuda=cuda) - def launch(self, server_name, port): + def launch(self, server_name, port, root_path): self.app.include_router(self.router) - uvicorn.run(self.app, host=server_name, port=port, timeout_keep_alive=shared.cmd_opts.timeout_keep_alive) + uvicorn.run(self.app, host=server_name, port=port, timeout_keep_alive=shared.cmd_opts.timeout_keep_alive, root_path=root_path) def kill_webui(self): restart.stop_program() diff --git a/modules/api/models.py b/modules/api/models.py index b5683071..800c9b93 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -1,4 +1,5 @@ import inspect + from pydantic import BaseModel, Field, create_model from typing import Any, Optional from typing_extensions import Literal @@ -207,11 +208,10 @@ class PreprocessResponse(BaseModel): fields = {} for key, metadata in opts.data_labels.items(): value = opts.data.get(key) - optType = opts.typemap.get(type(metadata.default), type(value)) + optType = opts.typemap.get(type(metadata.default), type(metadata.default)) if metadata.default else Any - if (metadata is not None): - fields.update({key: (Optional[optType], Field( - default=metadata.default ,description=metadata.label))}) + if metadata is not None: + fields.update({key: (Optional[optType], Field(default=metadata.default, description=metadata.label))}) else: fields.update({key: (Optional[optType], Field())}) diff --git a/modules/call_queue.py b/modules/call_queue.py index 61aa240f..f2eb17d6 100644 --- a/modules/call_queue.py +++ b/modules/call_queue.py @@ -3,7 +3,7 @@ import html import threading
import time
-from modules import shared, progress, errors
+from modules import shared, progress, errors, devices
queue_lock = threading.Lock()
@@ -75,6 +75,8 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False): error_message = f'{type(e).__name__}: {e}'
res = extra_outputs_array + [f"<div class='error'>{html.escape(error_message)}</div>"]
+ devices.torch_gc()
+
shared.state.skipped = False
shared.state.interrupted = False
shared.state.job_count = 0
diff --git a/modules/cmd_args.py b/modules/cmd_args.py index ae78f469..64f21e01 100644 --- a/modules/cmd_args.py +++ b/modules/cmd_args.py @@ -13,8 +13,10 @@ parser.add_argument("--reinstall-xformers", action='store_true', help="launch.py parser.add_argument("--reinstall-torch", action='store_true', help="launch.py argument: install the appropriate version of torch even if you have some version already installed")
parser.add_argument("--update-check", action='store_true', help="launch.py argument: check for updates at startup")
parser.add_argument("--test-server", action='store_true', help="launch.py argument: configure server for testing")
+parser.add_argument("--log-startup", action='store_true', help="launch.py argument: print a detailed log of what's happening at startup")
parser.add_argument("--skip-prepare-environment", action='store_true', help="launch.py argument: skip all environment preparation")
parser.add_argument("--skip-install", action='store_true', help="launch.py argument: skip installation of packages")
+parser.add_argument("--do-not-download-clip", action='store_true', help="do not download CLIP model even if it's not included in the checkpoint")
parser.add_argument("--data-dir", type=str, default=os.path.dirname(os.path.dirname(os.path.realpath(__file__))), help="base path where all user data is stored")
parser.add_argument("--config", type=str, default=sd_default_config, help="path to config which constructs model",)
parser.add_argument("--ckpt", type=str, default=sd_model_file, help="path to checkpoint of stable diffusion model; if specified, this checkpoint will be added to the list of checkpoints and loaded",)
@@ -65,6 +67,7 @@ parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="pre parser.add_argument("--disable-opt-split-attention", action='store_true', help="prefer no cross-attention layer optimization for automatic choice of optimization")
parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
+parser.add_argument("--disable-model-loading-ram-optimization", action='store_true', help="disable an optimization that reduces RAM use when loading a model")
parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
parser.add_argument("--show-negative-prompt", action='store_true', help="does not do anything", default=False)
@@ -109,3 +112,5 @@ parser.add_argument('--subpath', type=str, help='customize the subpath for gradi parser.add_argument('--add-stop-route', action='store_true', help='add /_stop route to stop server')
parser.add_argument('--api-server-stop', action='store_true', help='enable server stop/restart/kill via api')
parser.add_argument('--timeout-keep-alive', type=int, default=30, help='set timeout_keep_alive for uvicorn')
+parser.add_argument("--disable-all-extensions", action='store_true', help="prevent all extensions from running regardless of any other settings", default=False)
+parser.add_argument("--disable-extra-extensions", action='store_true', help=" prevent all extensions except built-in from running regardless of any other settings", default=False)
diff --git a/modules/devices.py b/modules/devices.py index 57e51da3..00a00b18 100644 --- a/modules/devices.py +++ b/modules/devices.py @@ -3,7 +3,7 @@ import contextlib from functools import lru_cache import torch -from modules import errors +from modules import errors, rng_philox if sys.platform == "darwin": from modules import mac_specific @@ -71,14 +71,17 @@ def enable_tf32(): torch.backends.cudnn.allow_tf32 = True - errors.run(enable_tf32, "Enabling TF32") -cpu = torch.device("cpu") -device = device_interrogate = device_gfpgan = device_esrgan = device_codeformer = None -dtype = torch.float16 -dtype_vae = torch.float16 -dtype_unet = torch.float16 +cpu: torch.device = torch.device("cpu") +device: torch.device = None +device_interrogate: torch.device = None +device_gfpgan: torch.device = None +device_esrgan: torch.device = None +device_codeformer: torch.device = None +dtype: torch.dtype = torch.float16 +dtype_vae: torch.dtype = torch.float16 +dtype_unet: torch.dtype = torch.float16 unet_needs_upcast = False @@ -90,23 +93,87 @@ def cond_cast_float(input): return input.float() if unet_needs_upcast else input +nv_rng = None + + def randn(seed, shape): + """Generate a tensor with random numbers from a normal distribution using seed. + + Uses the seed parameter to set the global torch seed; to generate more with that seed, use randn_like/randn_without_seed.""" + from modules.shared import opts - torch.manual_seed(seed) + manual_seed(seed) + + if opts.randn_source == "NV": + return torch.asarray(nv_rng.randn(shape), device=device) + if opts.randn_source == "CPU" or device.type == 'mps': return torch.randn(shape, device=cpu).to(device) + return torch.randn(shape, device=device) +def randn_local(seed, shape): + """Generate a tensor with random numbers from a normal distribution using seed. + + Does not change the global random number generator. You can only generate the seed's first tensor using this function.""" + + from modules.shared import opts + + if opts.randn_source == "NV": + rng = rng_philox.Generator(seed) + return torch.asarray(rng.randn(shape), device=device) + + local_device = cpu if opts.randn_source == "CPU" or device.type == 'mps' else device + local_generator = torch.Generator(local_device).manual_seed(int(seed)) + return torch.randn(shape, device=local_device, generator=local_generator).to(device) + + +def randn_like(x): + """Generate a tensor with random numbers from a normal distribution using the previously initialized genrator. + + Use either randn() or manual_seed() to initialize the generator.""" + + from modules.shared import opts + + if opts.randn_source == "NV": + return torch.asarray(nv_rng.randn(x.shape), device=x.device, dtype=x.dtype) + + if opts.randn_source == "CPU" or x.device.type == 'mps': + return torch.randn_like(x, device=cpu).to(x.device) + + return torch.randn_like(x) + + def randn_without_seed(shape): + """Generate a tensor with random numbers from a normal distribution using the previously initialized genrator. + + Use either randn() or manual_seed() to initialize the generator.""" + from modules.shared import opts + if opts.randn_source == "NV": + return torch.asarray(nv_rng.randn(shape), device=device) + if opts.randn_source == "CPU" or device.type == 'mps': return torch.randn(shape, device=cpu).to(device) + return torch.randn(shape, device=device) +def manual_seed(seed): + """Set up a global random number generator using the specified seed.""" + from modules.shared import opts + + if opts.randn_source == "NV": + global nv_rng + nv_rng = rng_philox.Generator(seed) + return + + torch.manual_seed(seed) + + def autocast(disable=False): from modules import shared diff --git a/modules/errors.py b/modules/errors.py index 5271a9fe..192cd8ff 100644 --- a/modules/errors.py +++ b/modules/errors.py @@ -14,7 +14,8 @@ def record_exception(): if exception_records and exception_records[-1] == e:
return
- exception_records.append((e, tb))
+ from modules import sysinfo
+ exception_records.append(sysinfo.format_exception(e, tb))
if len(exception_records) > 5:
exception_records.pop(0)
@@ -83,3 +84,53 @@ def run(code, task): code()
except Exception as e:
display(task, e)
+
+
+def check_versions():
+ from packaging import version
+ from modules import shared
+
+ import torch
+ import gradio
+
+ expected_torch_version = "2.0.0"
+ expected_xformers_version = "0.0.20"
+ expected_gradio_version = "3.39.0"
+
+ if version.parse(torch.__version__) < version.parse(expected_torch_version):
+ print_error_explanation(f"""
+You are running torch {torch.__version__}.
+The program is tested to work with torch {expected_torch_version}.
+To reinstall the desired version, run with commandline flag --reinstall-torch.
+Beware that this will cause a lot of large files to be downloaded, as well as
+there are reports of issues with training tab on the latest version.
+
+Use --skip-version-check commandline argument to disable this check.
+ """.strip())
+
+ if shared.xformers_available:
+ import xformers
+
+ if version.parse(xformers.__version__) < version.parse(expected_xformers_version):
+ print_error_explanation(f"""
+You are running xformers {xformers.__version__}.
+The program is tested to work with xformers {expected_xformers_version}.
+To reinstall the desired version, run with commandline flag --reinstall-xformers.
+
+Use --skip-version-check commandline argument to disable this check.
+ """.strip())
+
+ if gradio.__version__ != expected_gradio_version:
+ print_error_explanation(f"""
+You are running gradio {gradio.__version__}.
+The program is designed to work with gradio {expected_gradio_version}.
+Using a different version of gradio is extremely likely to break the program.
+
+Reasons why you have the mismatched gradio version can be:
+ - you use --skip-install flag.
+ - you use webui.py to start the program instead of launch.py.
+ - an extension installs the incompatible gradio version.
+
+Use --skip-version-check commandline argument to disable this check.
+ """.strip())
+
diff --git a/modules/extensions.py b/modules/extensions.py index c561159a..e4633af4 100644 --- a/modules/extensions.py +++ b/modules/extensions.py @@ -11,9 +11,9 @@ os.makedirs(extensions_dir, exist_ok=True) def active():
- if shared.opts.disable_all_extensions == "all":
+ if shared.cmd_opts.disable_all_extensions or shared.opts.disable_all_extensions == "all":
return []
- elif shared.opts.disable_all_extensions == "extra":
+ elif shared.cmd_opts.disable_extra_extensions or shared.opts.disable_all_extensions == "extra":
return [x for x in extensions if x.enabled and x.is_builtin]
else:
return [x for x in extensions if x.enabled]
@@ -56,10 +56,12 @@ class Extension: self.do_read_info_from_repo()
return self.to_dict()
-
- d = cache.cached_data_for_file('extensions-git', self.name, os.path.join(self.path, ".git"), read_from_repo)
- self.from_dict(d)
- self.status = 'unknown'
+ try:
+ d = cache.cached_data_for_file('extensions-git', self.name, os.path.join(self.path, ".git"), read_from_repo)
+ self.from_dict(d)
+ except FileNotFoundError:
+ pass
+ self.status = 'unknown' if self.status == '' else self.status
def do_read_info_from_repo(self):
repo = None
@@ -139,8 +141,12 @@ def list_extensions(): if not os.path.isdir(extensions_dir):
return
- if shared.opts.disable_all_extensions == "all":
+ if shared.cmd_opts.disable_all_extensions:
+ print("*** \"--disable-all-extensions\" arg was used, will not load any extensions ***")
+ elif shared.opts.disable_all_extensions == "all":
print("*** \"Disable all extensions\" option was set, will not load any extensions ***")
+ elif shared.cmd_opts.disable_extra_extensions:
+ print("*** \"--disable-extra-extensions\" arg was used, will only load built-in extensions ***")
elif shared.opts.disable_all_extensions == "extra":
print("*** \"Disable all extensions\" option was set, will only load built-in extensions ***")
diff --git a/modules/extra_networks.py b/modules/extra_networks.py index 41799b0a..6ae07e91 100644 --- a/modules/extra_networks.py +++ b/modules/extra_networks.py @@ -4,16 +4,22 @@ from collections import defaultdict from modules import errors
extra_network_registry = {}
+extra_network_aliases = {}
def initialize():
extra_network_registry.clear()
+ extra_network_aliases.clear()
def register_extra_network(extra_network):
extra_network_registry[extra_network.name] = extra_network
+def register_extra_network_alias(extra_network, alias):
+ extra_network_aliases[alias] = extra_network
+
+
def register_default_extra_networks():
from modules.extra_networks_hypernet import ExtraNetworkHypernet
register_extra_network(ExtraNetworkHypernet())
@@ -82,20 +88,26 @@ def activate(p, extra_network_data): """call activate for extra networks in extra_network_data in specified order, then call
activate for all remaining registered networks with an empty argument list"""
+ activated = []
+
for extra_network_name, extra_network_args in extra_network_data.items():
extra_network = extra_network_registry.get(extra_network_name, None)
+
+ if extra_network is None:
+ extra_network = extra_network_aliases.get(extra_network_name, None)
+
if extra_network is None:
print(f"Skipping unknown extra network: {extra_network_name}")
continue
try:
extra_network.activate(p, extra_network_args)
+ activated.append(extra_network)
except Exception as e:
errors.display(e, f"activating extra network {extra_network_name} with arguments {extra_network_args}")
for extra_network_name, extra_network in extra_network_registry.items():
- args = extra_network_data.get(extra_network_name, None)
- if args is not None:
+ if extra_network in activated:
continue
try:
diff --git a/modules/extras.py b/modules/extras.py index e9c0263e..2a310ae3 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -7,7 +7,7 @@ import json import torch
import tqdm
-from modules import shared, images, sd_models, sd_vae, sd_models_config
+from modules import shared, images, sd_models, sd_vae, sd_models_config, errors
from modules.ui_common import plaintext_to_html
import gradio as gr
import safetensors.torch
@@ -72,7 +72,20 @@ def to_half(tensor, enable): return tensor
-def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights, save_metadata):
+def read_metadata(primary_model_name, secondary_model_name, tertiary_model_name):
+ metadata = {}
+
+ for checkpoint_name in [primary_model_name, secondary_model_name, tertiary_model_name]:
+ checkpoint_info = sd_models.checkpoints_list.get(checkpoint_name, None)
+ if checkpoint_info is None:
+ continue
+
+ metadata.update(checkpoint_info.metadata)
+
+ return json.dumps(metadata, indent=4, ensure_ascii=False)
+
+
+def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights, save_metadata, add_merge_recipe, copy_metadata_fields, metadata_json):
shared.state.begin(job="model-merge")
def fail(message):
@@ -241,11 +254,25 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ shared.state.textinfo = "Saving"
print(f"Saving to {output_modelname}...")
- metadata = None
+ metadata = {}
+
+ if save_metadata and copy_metadata_fields:
+ if primary_model_info:
+ metadata.update(primary_model_info.metadata)
+ if secondary_model_info:
+ metadata.update(secondary_model_info.metadata)
+ if tertiary_model_info:
+ metadata.update(tertiary_model_info.metadata)
if save_metadata:
- metadata = {"format": "pt"}
+ try:
+ metadata.update(json.loads(metadata_json))
+ except Exception as e:
+ errors.display(e, "readin metadata from json")
+
+ metadata["format"] = "pt"
+ if save_metadata and add_merge_recipe:
merge_recipe = {
"type": "webui", # indicate this model was merged with webui's built-in merger
"primary_model_hash": primary_model_info.sha256,
@@ -261,7 +288,6 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ "is_inpainting": result_is_inpainting_model,
"is_instruct_pix2pix": result_is_instruct_pix2pix_model
}
- metadata["sd_merge_recipe"] = json.dumps(merge_recipe)
sd_merge_models = {}
@@ -281,11 +307,12 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ if tertiary_model_info:
add_model_metadata(tertiary_model_info)
+ metadata["sd_merge_recipe"] = json.dumps(merge_recipe)
metadata["sd_merge_models"] = json.dumps(sd_merge_models)
_, extension = os.path.splitext(output_modelname)
if extension.lower() == ".safetensors":
- safetensors.torch.save_file(theta_0, output_modelname, metadata=metadata)
+ safetensors.torch.save_file(theta_0, output_modelname, metadata=metadata if len(metadata)>0 else None)
else:
torch.save(theta_0, output_modelname)
diff --git a/modules/gradio_extensons.py b/modules/gradio_extensons.py new file mode 100644 index 00000000..5af7fd8e --- /dev/null +++ b/modules/gradio_extensons.py @@ -0,0 +1,60 @@ +import gradio as gr
+
+from modules import scripts
+
+def add_classes_to_gradio_component(comp):
+ """
+ this adds gradio-* to the component for css styling (ie gradio-button to gr.Button), as well as some others
+ """
+
+ comp.elem_classes = [f"gradio-{comp.get_block_name()}", *(comp.elem_classes or [])]
+
+ if getattr(comp, 'multiselect', False):
+ comp.elem_classes.append('multiselect')
+
+
+def IOComponent_init(self, *args, **kwargs):
+ self.webui_tooltip = kwargs.pop('tooltip', None)
+
+ if scripts.scripts_current is not None:
+ scripts.scripts_current.before_component(self, **kwargs)
+
+ scripts.script_callbacks.before_component_callback(self, **kwargs)
+
+ res = original_IOComponent_init(self, *args, **kwargs)
+
+ add_classes_to_gradio_component(self)
+
+ scripts.script_callbacks.after_component_callback(self, **kwargs)
+
+ if scripts.scripts_current is not None:
+ scripts.scripts_current.after_component(self, **kwargs)
+
+ return res
+
+
+def Block_get_config(self):
+ config = original_Block_get_config(self)
+
+ webui_tooltip = getattr(self, 'webui_tooltip', None)
+ if webui_tooltip:
+ config["webui_tooltip"] = webui_tooltip
+
+ return config
+
+
+def BlockContext_init(self, *args, **kwargs):
+ res = original_BlockContext_init(self, *args, **kwargs)
+
+ add_classes_to_gradio_component(self)
+
+ return res
+
+
+original_IOComponent_init = gr.components.IOComponent.__init__
+original_Block_get_config = gr.blocks.Block.get_config
+original_BlockContext_init = gr.blocks.BlockContext.__init__
+
+gr.components.IOComponent.__init__ = IOComponent_init
+gr.blocks.Block.get_config = Block_get_config
+gr.blocks.BlockContext.__init__ = BlockContext_init
diff --git a/modules/images.py b/modules/images.py index fb5d2e75..38aa933d 100644 --- a/modules/images.py +++ b/modules/images.py @@ -363,7 +363,7 @@ class FilenameGenerator: 'styles': lambda self: self.p and sanitize_filename_part(", ".join([style for style in self.p.styles if not style == "None"]) or "None", replace_spaces=False),
'sampler': lambda self: self.p and sanitize_filename_part(self.p.sampler_name, replace_spaces=False),
'model_hash': lambda self: getattr(self.p, "sd_model_hash", shared.sd_model.sd_model_hash),
- 'model_name': lambda self: sanitize_filename_part(shared.sd_model.sd_checkpoint_info.model_name, replace_spaces=False),
+ 'model_name': lambda self: sanitize_filename_part(shared.sd_model.sd_checkpoint_info.name_for_extra, replace_spaces=False),
'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
'datetime': lambda self, *args: self.datetime(*args), # accepts formats: [datetime], [datetime<Format>], [datetime<Format><Time Zone>]
'job_timestamp': lambda self: getattr(self.p, "job_timestamp", shared.state.job_timestamp),
diff --git a/modules/img2img.py b/modules/img2img.py index a811e7a4..68e415ef 100644 --- a/modules/img2img.py +++ b/modules/img2img.py @@ -10,7 +10,6 @@ from modules import sd_samplers, images as imgutil from modules.generation_parameters_copypaste import create_override_settings_dict, parse_generation_parameters
from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
from modules.shared import opts, state
-from modules.images import save_image
import modules.shared as shared
import modules.processing as processing
from modules.ui import plaintext_to_html
@@ -18,9 +17,10 @@ import modules.scripts def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0, use_png_info=False, png_info_props=None, png_info_dir=None):
+ output_dir = output_dir.strip()
processing.fix_seed(p)
- images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp")))
+ images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
is_inpaint_batch = False
if inpaint_mask_dir:
@@ -32,11 +32,6 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal print(f"Will process {len(images)} images, creating {p.n_iter * p.batch_size} new images for each.")
- save_normally = output_dir == ''
-
- p.do_not_save_grid = True
- p.do_not_save_samples = not save_normally
-
state.job_count = len(images) * p.n_iter
# extract "default" params to use in case getting png info fails
@@ -111,21 +106,14 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal proc = modules.scripts.scripts_img2img.run(p, *args)
if proc is None:
- proc = process_images(p)
-
- for n, processed_image in enumerate(proc.images):
- filename = image_path.stem
- infotext = proc.infotext(p, n)
- relpath = os.path.dirname(os.path.relpath(image, input_dir))
-
- if n > 0:
- filename += f"-{n}"
-
- if not save_normally:
- os.makedirs(os.path.join(output_dir, relpath), exist_ok=True)
- if processed_image.mode == 'RGBA':
- processed_image = processed_image.convert("RGB")
- save_image(processed_image, os.path.join(output_dir, relpath), None, extension=opts.samples_format, info=infotext, forced_filename=filename, save_to_dirs=False)
+ if output_dir:
+ p.outpath_samples = output_dir
+ p.override_settings['save_to_dirs'] = False
+ if p.n_iter > 1 or p.batch_size > 1:
+ p.override_settings['samples_filename_pattern'] = f'{image_path.stem}-[generation_number]'
+ else:
+ p.override_settings['samples_filename_pattern'] = f'{image_path.stem}'
+ process_images(p)
def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, request: gr.Request, *args):
diff --git a/modules/launch_utils.py b/modules/launch_utils.py index 434facbc..f77b577a 100644 --- a/modules/launch_utils.py +++ b/modules/launch_utils.py @@ -1,4 +1,5 @@ # this scripts installs necessary requirements and launches main program in webui.py
+import re
import subprocess
import os
import sys
@@ -9,6 +10,7 @@ from functools import lru_cache from modules import cmd_args, errors
from modules.paths_internal import script_path, extensions_dir
+from modules.timer import startup_timer
args, _ = cmd_args.parser.parse_known_args()
@@ -192,7 +194,7 @@ def run_extension_installer(extension_dir): try:
env = os.environ.copy()
- env['PYTHONPATH'] = os.path.abspath(".")
+ env['PYTHONPATH'] = f"{os.path.abspath('.')}{os.pathsep}{env.get('PYTHONPATH', '')}"
print(run(f'"{python}" "{path_installer}"', errdesc=f"Error running install.py for extension {extension_dir}", custom_env=env))
except Exception as e:
@@ -222,8 +224,51 @@ def run_extensions_installers(settings_file): if not os.path.isdir(extensions_dir):
return
- for dirname_extension in list_extensions(settings_file):
- run_extension_installer(os.path.join(extensions_dir, dirname_extension))
+ with startup_timer.subcategory("run extensions installers"):
+ for dirname_extension in list_extensions(settings_file):
+ path = os.path.join(extensions_dir, dirname_extension)
+
+ if os.path.isdir(path):
+ run_extension_installer(path)
+ startup_timer.record(dirname_extension)
+
+
+re_requirement = re.compile(r"\s*([-_a-zA-Z0-9]+)\s*(?:==\s*([-+_.a-zA-Z0-9]+))?\s*")
+
+
+def requirements_met(requirements_file):
+ """
+ Does a simple parse of a requirements.txt file to determine if all rerqirements in it
+ are already installed. Returns True if so, False if not installed or parsing fails.
+ """
+
+ import importlib.metadata
+ import packaging.version
+
+ with open(requirements_file, "r", encoding="utf8") as file:
+ for line in file:
+ if line.strip() == "":
+ continue
+
+ m = re.match(re_requirement, line)
+ if m is None:
+ return False
+
+ package = m.group(1).strip()
+ version_required = (m.group(2) or "").strip()
+
+ if version_required == "":
+ continue
+
+ try:
+ version_installed = importlib.metadata.version(package)
+ except Exception:
+ return False
+
+ if packaging.version.parse(version_required) != packaging.version.parse(version_installed):
+ return False
+
+ return True
def prepare_environment():
@@ -251,15 +296,18 @@ def prepare_environment(): try:
# the existance of this file is a signal to webui.sh/bat that webui needs to be restarted when it stops execution
os.remove(os.path.join(script_path, "tmp", "restart"))
- os.environ.setdefault('SD_WEBUI_RESTARTING ', '1')
+ os.environ.setdefault('SD_WEBUI_RESTARTING', '1')
except OSError:
pass
if not args.skip_python_version_check:
check_python_version()
+ startup_timer.record("checks")
+
commit = commit_hash()
tag = git_tag()
+ startup_timer.record("git version info")
print(f"Python {sys.version}")
print(f"Version: {tag}")
@@ -267,21 +315,27 @@ def prepare_environment(): if args.reinstall_torch or not is_installed("torch") or not is_installed("torchvision"):
run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True)
+ startup_timer.record("install torch")
if not args.skip_torch_cuda_test and not check_run_python("import torch; assert torch.cuda.is_available()"):
raise RuntimeError(
'Torch is not able to use GPU; '
'add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'
)
+ startup_timer.record("torch GPU test")
+
if not is_installed("gfpgan"):
run_pip(f"install {gfpgan_package}", "gfpgan")
+ startup_timer.record("install gfpgan")
if not is_installed("clip"):
run_pip(f"install {clip_package}", "clip")
+ startup_timer.record("install clip")
if not is_installed("open_clip"):
run_pip(f"install {openclip_package}", "open_clip")
+ startup_timer.record("install open_clip")
if (not is_installed("xformers") or args.reinstall_xformers) and args.xformers:
if platform.system() == "Windows":
@@ -295,8 +349,11 @@ def prepare_environment(): elif platform.system() == "Linux":
run_pip(f"install -U -I --no-deps {xformers_package}", "xformers")
+ startup_timer.record("install xformers")
+
if not is_installed("ngrok") and args.ngrok:
run_pip("install ngrok", "ngrok")
+ startup_timer.record("install ngrok")
os.makedirs(os.path.join(script_path, dir_repos), exist_ok=True)
@@ -306,20 +363,28 @@ def prepare_environment(): git_clone(codeformer_repo, repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
git_clone(blip_repo, repo_dir('BLIP'), "BLIP", blip_commit_hash)
+ startup_timer.record("clone repositores")
+
if not is_installed("lpips"):
run_pip(f"install -r \"{os.path.join(repo_dir('CodeFormer'), 'requirements.txt')}\"", "requirements for CodeFormer")
+ startup_timer.record("install CodeFormer requirements")
if not os.path.isfile(requirements_file):
requirements_file = os.path.join(script_path, requirements_file)
- run_pip(f"install -r \"{requirements_file}\"", "requirements")
+
+ if not requirements_met(requirements_file):
+ run_pip(f"install -r \"{requirements_file}\"", "requirements")
+ startup_timer.record("install requirements")
run_extensions_installers(settings_file=args.ui_settings_file)
if args.update_check:
version_check(commit)
+ startup_timer.record("check version")
if args.update_all_extensions:
git_pull_recursive(extensions_dir)
+ startup_timer.record("update extensions")
if "--exit" in sys.argv:
print("Exiting because of --exit argument")
diff --git a/modules/lowvram.py b/modules/lowvram.py index 6bbc11eb..3f830664 100644 --- a/modules/lowvram.py +++ b/modules/lowvram.py @@ -90,8 +90,12 @@ def setup_for_low_vram(sd_model, use_medvram): sd_model.conditioner.register_forward_pre_hook(send_me_to_gpu)
elif is_sd2:
sd_model.cond_stage_model.model.register_forward_pre_hook(send_me_to_gpu)
+ sd_model.cond_stage_model.model.token_embedding.register_forward_pre_hook(send_me_to_gpu)
+ parents[sd_model.cond_stage_model.model] = sd_model.cond_stage_model
+ parents[sd_model.cond_stage_model.model.token_embedding] = sd_model.cond_stage_model
else:
sd_model.cond_stage_model.transformer.register_forward_pre_hook(send_me_to_gpu)
+ parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
sd_model.first_stage_model.register_forward_pre_hook(send_me_to_gpu)
sd_model.first_stage_model.encode = first_stage_model_encode_wrap
@@ -101,9 +105,6 @@ def setup_for_low_vram(sd_model, use_medvram): if sd_model.embedder:
sd_model.embedder.register_forward_pre_hook(send_me_to_gpu)
- if hasattr(sd_model, 'cond_stage_model'):
- parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
-
if use_medvram:
sd_model.model.register_forward_pre_hook(send_me_to_gpu)
else:
diff --git a/modules/processing.py b/modules/processing.py index 6567b3cf..8f34c8b4 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -14,7 +14,7 @@ from skimage import exposure from typing import Any, Dict, List
import modules.sd_hijack
-from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common, sd_unet
+from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common, sd_unet, errors
from modules.sd_hijack import model_hijack
from modules.shared import opts, cmd_opts, state
import modules.shared as shared
@@ -492,7 +492,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see noise_shape = shape if seed_resize_from_h <= 0 or seed_resize_from_w <= 0 else (shape[0], seed_resize_from_h//8, seed_resize_from_w//8)
subnoise = None
- if subseeds is not None:
+ if subseeds is not None and subseed_strength != 0:
subseed = 0 if i >= len(subseeds) else subseeds[i]
subnoise = devices.randn(subseed, noise_shape)
@@ -524,7 +524,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see cnt = p.sampler.number_of_needed_noises(p)
if eta_noise_seed_delta > 0:
- torch.manual_seed(seed + eta_noise_seed_delta)
+ devices.manual_seed(seed + eta_noise_seed_delta)
for j in range(cnt):
sampler_noises[j].append(devices.randn_without_seed(tuple(noise_shape)))
@@ -538,6 +538,40 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see return x
+def decode_latent_batch(model, batch, target_device=None, check_for_nans=False):
+ samples = []
+
+ for i in range(batch.shape[0]):
+ sample = decode_first_stage(model, batch[i:i + 1])[0]
+
+ if check_for_nans:
+ try:
+ devices.test_for_nans(sample, "vae")
+ except devices.NansException as e:
+ if devices.dtype_vae == torch.float32 or not shared.opts.auto_vae_precision:
+ raise e
+
+ errors.print_error_explanation(
+ "A tensor with all NaNs was produced in VAE.\n"
+ "Web UI will now convert VAE into 32-bit float and retry.\n"
+ "To disable this behavior, disable the 'Automaticlly revert VAE to 32-bit floats' setting.\n"
+ "To always start with 32-bit VAE, use --no-half-vae commandline flag."
+ )
+
+ devices.dtype_vae = torch.float32
+ model.first_stage_model.to(devices.dtype_vae)
+ batch = batch.to(devices.dtype_vae)
+
+ sample = decode_first_stage(model, batch[i:i + 1])[0]
+
+ if target_device is not None:
+ sample = sample.to(target_device)
+
+ samples.append(sample)
+
+ return samples
+
+
def decode_first_stage(model, x):
x = model.decode_first_stage(x.to(devices.dtype_vae))
@@ -566,8 +600,12 @@ def program_version(): return res
-def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iteration=0, position_in_batch=0, use_main_prompt=False):
- index = position_in_batch + iteration * p.batch_size
+def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iteration=0, position_in_batch=0, use_main_prompt=False, index=None, all_negative_prompts=None):
+ if index is None:
+ index = position_in_batch + iteration * p.batch_size
+
+ if all_negative_prompts is None:
+ all_negative_prompts = p.all_negative_prompts
clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers)
enable_hr = getattr(p, 'enable_hr', False)
@@ -583,12 +621,12 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Sampler": p.sampler_name,
"CFG scale": p.cfg_scale,
"Image CFG scale": getattr(p, 'image_cfg_scale', None),
- "Seed": all_seeds[index],
+ "Seed": p.all_seeds[0] if use_main_prompt else all_seeds[index],
"Face restoration": (opts.face_restoration_model if p.restore_faces else None),
"Size": f"{p.width}x{p.height}",
"Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
- "Model": (None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', '')),
- "Variation seed": (None if p.subseed_strength == 0 else all_subseeds[index]),
+ "Model": (None if not opts.add_model_name_to_info else shared.sd_model.sd_checkpoint_info.name_for_extra),
+ "Variation seed": (None if p.subseed_strength == 0 else (p.all_subseeds[0] if use_main_prompt else all_subseeds[index])),
"Variation seed strength": (None if p.subseed_strength == 0 else p.subseed_strength),
"Seed resize from": (None if p.seed_resize_from_w <= 0 or p.seed_resize_from_h <= 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
"Denoising strength": getattr(p, 'denoising_strength', None),
@@ -598,7 +636,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Token merging ratio": None if token_merging_ratio == 0 else token_merging_ratio,
"Token merging ratio hr": None if not enable_hr or token_merging_ratio_hr == 0 else token_merging_ratio_hr,
"Init image hash": getattr(p, 'init_img_hash', None),
- "RNG": opts.randn_source if opts.randn_source != "GPU" else None,
+ "RNG": opts.randn_source if opts.randn_source != "GPU" and opts.randn_source != "NV" else None,
"NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond,
**p.extra_generation_params,
"Version": program_version() if opts.add_version_to_infotext else None,
@@ -608,7 +646,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter generation_params_text = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in generation_params.items() if v is not None])
prompt_text = p.prompt if use_main_prompt else all_prompts[index]
- negative_prompt_text = f"\nNegative prompt: {p.all_negative_prompts[index]}" if p.all_negative_prompts[index] else ""
+ negative_prompt_text = f"\nNegative prompt: {all_negative_prompts[index]}" if all_negative_prompts[index] else ""
return f"{prompt_text}{negative_prompt_text}\n{generation_params_text}".strip()
@@ -682,9 +720,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: else:
p.all_subseeds = [int(subseed) + x for x in range(len(p.all_prompts))]
- def infotext(iteration=0, position_in_batch=0, use_main_prompt=False):
- return create_infotext(p, p.all_prompts, p.all_seeds, p.all_subseeds, comments, iteration, position_in_batch, use_main_prompt)
-
if os.path.exists(cmd_opts.embeddings_dir) and not p.do_not_reload_embeddings:
model_hijack.embedding_db.load_textual_inversion_embeddings()
@@ -758,10 +793,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast():
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
- x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
- for x in x_samples_ddim:
- devices.test_for_nans(x, "vae")
-
+ x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
x_samples_ddim = torch.stack(x_samples_ddim).float()
x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
@@ -775,6 +807,16 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.scripts is not None:
p.scripts.postprocess_batch(p, x_samples_ddim, batch_number=n)
+ p.prompts = p.all_prompts[n * p.batch_size:(n + 1) * p.batch_size]
+ p.negative_prompts = p.all_negative_prompts[n * p.batch_size:(n + 1) * p.batch_size]
+
+ batch_params = scripts.PostprocessBatchListArgs(list(x_samples_ddim))
+ p.scripts.postprocess_batch_list(p, batch_params, batch_number=n)
+ x_samples_ddim = batch_params.images
+
+ def infotext(index=0, use_main_prompt=False):
+ return create_infotext(p, p.prompts, p.seeds, p.subseeds, use_main_prompt=use_main_prompt, index=index, all_negative_prompts=p.negative_prompts)
+
for i, x_sample in enumerate(x_samples_ddim):
p.batch_index = i
@@ -783,7 +825,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.restore_faces:
if opts.save and not p.do_not_save_samples and opts.save_images_before_face_restoration:
- images.save_image(Image.fromarray(x_sample), p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-face-restoration")
+ images.save_image(Image.fromarray(x_sample), p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-before-face-restoration")
devices.torch_gc()
@@ -800,15 +842,15 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if p.color_corrections is not None and i < len(p.color_corrections):
if opts.save and not p.do_not_save_samples and opts.save_images_before_color_correction:
image_without_cc = apply_overlay(image, p.paste_to, i, p.overlay_images)
- images.save_image(image_without_cc, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-before-color-correction")
+ images.save_image(image_without_cc, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-before-color-correction")
image = apply_color_correction(p.color_corrections[i], image)
image = apply_overlay(image, p.paste_to, i, p.overlay_images)
if opts.samples_save and not p.do_not_save_samples:
- images.save_image(image, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p)
+ images.save_image(image, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p)
- text = infotext(n, i)
+ text = infotext(i)
infotexts.append(text)
if opts.enable_pnginfo:
image.info["parameters"] = text
@@ -819,10 +861,10 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: image_mask_composite = Image.composite(image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, p.mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA')
if opts.save_mask:
- images.save_image(image_mask, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask")
+ images.save_image(image_mask, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask")
if opts.save_mask_composite:
- images.save_image(image_mask_composite, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(n, i), p=p, suffix="-mask-composite")
+ images.save_image(image_mask_composite, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask-composite")
if opts.return_mask:
output_images.append(image_mask)
@@ -863,7 +905,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: p,
images_list=output_images,
seed=p.all_seeds[0],
- info=infotext(),
+ info=infotexts[0],
comments="".join(f"{comment}\n" for comment in comments),
subseed=p.all_subseeds[0],
index_of_first_image=index_of_first_image,
@@ -1029,7 +1071,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): image = sd_samplers.sample_to_image(image, index, approximation=0)
info = create_infotext(self, self.all_prompts, self.all_seeds, self.all_subseeds, [], iteration=self.iteration, position_in_batch=index)
- images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, info=info, suffix="-before-highres-fix")
+ images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, info=info, p=self, suffix="-before-highres-fix")
if latent_scale_mode is not None:
for i in range(samples.shape[0]):
@@ -1306,6 +1348,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): image = image.to(shared.device, dtype=devices.dtype_vae)
self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image))
+ devices.torch_gc()
if self.resize_mode == 3:
self.init_latent = torch.nn.functional.interpolate(self.init_latent, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py index b29d079d..8169a459 100644 --- a/modules/prompt_parser.py +++ b/modules/prompt_parser.py @@ -19,7 +19,7 @@ prompt: (emphasized | scheduled | alternate | plain | WHITESPACE)* !emphasized: "(" prompt ")"
| "(" prompt ":" prompt ")"
| "[" prompt "]"
-scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER "]"
+scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER [WHITESPACE] "]"
alternate: "[" prompt ("|" prompt)+ "]"
WHITESPACE: /\s+/
plain: /([^\\\[\]():|]|\\.)+/
@@ -60,11 +60,11 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): class CollectSteps(lark.Visitor):
def scheduled(self, tree):
- tree.children[-1] = float(tree.children[-1])
- if tree.children[-1] < 1:
- tree.children[-1] *= steps
- tree.children[-1] = min(steps, int(tree.children[-1]))
- res.append(tree.children[-1])
+ tree.children[-2] = float(tree.children[-2])
+ if tree.children[-2] < 1:
+ tree.children[-2] *= steps
+ tree.children[-2] = min(steps, int(tree.children[-2]))
+ res.append(tree.children[-2])
def alternate(self, tree):
res.extend(range(1, steps+1))
@@ -75,7 +75,7 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): def at_step(step, tree):
class AtStep(lark.Transformer):
def scheduled(self, args):
- before, after, _, when = args
+ before, after, _, when, _ = args
yield before or () if step <= when else after
def alternate(self, args):
yield next(args[(step - 1)%len(args)])
@@ -178,7 +178,7 @@ def get_learned_conditioning(model, prompts: SdConditioning | list[str], steps): re_AND = re.compile(r"\bAND\b")
-re_weight = re.compile(r"^(.*?)(?:\s*:\s*([-+]?(?:\d+\.?|\d*\.\d+)))?\s*$")
+re_weight = re.compile(r"^((?:\s|.)*?)(?:\s*:\s*([-+]?(?:\d+\.?|\d*\.\d+)))?\s*$")
def get_multicond_prompt_list(prompts: SdConditioning | list[str]):
@@ -333,7 +333,7 @@ re_attention = re.compile(r""" \\|
\(|
\[|
-:([+-]?[.\d]+)\)|
+:\s*([+-]?[.\d]+)\s*\)|
\)|
]|
[^\\()\[\]:]+|
diff --git a/modules/rng_philox.py b/modules/rng_philox.py new file mode 100644 index 00000000..5532cf9d --- /dev/null +++ b/modules/rng_philox.py @@ -0,0 +1,102 @@ +"""RNG imitiating torch cuda randn on CPU. You are welcome.
+
+Usage:
+
+```
+g = Generator(seed=0)
+print(g.randn(shape=(3, 4)))
+```
+
+Expected output:
+```
+[[-0.92466259 -0.42534415 -2.6438457 0.14518388]
+ [-0.12086647 -0.57972564 -0.62285122 -0.32838709]
+ [-1.07454231 -0.36314407 -1.67105067 2.26550497]]
+```
+"""
+
+import numpy as np
+
+philox_m = [0xD2511F53, 0xCD9E8D57]
+philox_w = [0x9E3779B9, 0xBB67AE85]
+
+two_pow32_inv = np.array([2.3283064e-10], dtype=np.float32)
+two_pow32_inv_2pi = np.array([2.3283064e-10 * 6.2831855], dtype=np.float32)
+
+
+def uint32(x):
+ """Converts (N,) np.uint64 array into (2, N) np.unit32 array."""
+ return x.view(np.uint32).reshape(-1, 2).transpose(1, 0)
+
+
+def philox4_round(counter, key):
+ """A single round of the Philox 4x32 random number generator."""
+
+ v1 = uint32(counter[0].astype(np.uint64) * philox_m[0])
+ v2 = uint32(counter[2].astype(np.uint64) * philox_m[1])
+
+ counter[0] = v2[1] ^ counter[1] ^ key[0]
+ counter[1] = v2[0]
+ counter[2] = v1[1] ^ counter[3] ^ key[1]
+ counter[3] = v1[0]
+
+
+def philox4_32(counter, key, rounds=10):
+ """Generates 32-bit random numbers using the Philox 4x32 random number generator.
+
+ Parameters:
+ counter (numpy.ndarray): A 4xN array of 32-bit integers representing the counter values (offset into generation).
+ key (numpy.ndarray): A 2xN array of 32-bit integers representing the key values (seed).
+ rounds (int): The number of rounds to perform.
+
+ Returns:
+ numpy.ndarray: A 4xN array of 32-bit integers containing the generated random numbers.
+ """
+
+ for _ in range(rounds - 1):
+ philox4_round(counter, key)
+
+ key[0] = key[0] + philox_w[0]
+ key[1] = key[1] + philox_w[1]
+
+ philox4_round(counter, key)
+ return counter
+
+
+def box_muller(x, y):
+ """Returns just the first out of two numbers generated by Box–Muller transform algorithm."""
+ u = x * two_pow32_inv + two_pow32_inv / 2
+ v = y * two_pow32_inv_2pi + two_pow32_inv_2pi / 2
+
+ s = np.sqrt(-2.0 * np.log(u))
+
+ r1 = s * np.sin(v)
+ return r1.astype(np.float32)
+
+
+class Generator:
+ """RNG that produces same outputs as torch.randn(..., device='cuda') on CPU"""
+
+ def __init__(self, seed):
+ self.seed = seed
+ self.offset = 0
+
+ def randn(self, shape):
+ """Generate a sequence of n standard normal random variables using the Philox 4x32 random number generator and the Box-Muller transform."""
+
+ n = 1
+ for x in shape:
+ n *= x
+
+ counter = np.zeros((4, n), dtype=np.uint32)
+ counter[0] = self.offset
+ counter[2] = np.arange(n, dtype=np.uint32) # up to 2^32 numbers can be generated - if you want more you'd need to spill into counter[3]
+ self.offset += 1
+
+ key = np.empty(n, dtype=np.uint64)
+ key.fill(self.seed)
+ key = uint32(key)
+
+ g = philox4_32(counter, key)
+
+ return box_muller(g[0], g[1]).reshape(shape) # discard g[2] and g[3]
diff --git a/modules/script_loading.py b/modules/script_loading.py index 306a1f35..0d55f193 100644 --- a/modules/script_loading.py +++ b/modules/script_loading.py @@ -12,11 +12,12 @@ def load_module(path): return module
-def preload_extensions(extensions_dir, parser):
+def preload_extensions(extensions_dir, parser, extension_list=None):
if not os.path.isdir(extensions_dir):
return
- for dirname in sorted(os.listdir(extensions_dir)):
+ extensions = extension_list if extension_list is not None else os.listdir(extensions_dir)
+ for dirname in sorted(extensions):
preload_script = os.path.join(extensions_dir, dirname, "preload.py")
if not os.path.isfile(preload_script):
continue
diff --git a/modules/scripts.py b/modules/scripts.py index 7d9dd59f..f7d060aa 100644 --- a/modules/scripts.py +++ b/modules/scripts.py @@ -16,6 +16,11 @@ class PostprocessImageArgs: self.image = image
+class PostprocessBatchListArgs:
+ def __init__(self, images):
+ self.images = images
+
+
class Script:
name = None
"""script's internal name derived from title"""
@@ -119,7 +124,7 @@ class Script: def after_extra_networks_activate(self, p, *args, **kwargs):
"""
- Calledafter extra networks activation, before conds calculation
+ Called after extra networks activation, before conds calculation
allow modification of the network after extra networks activation been applied
won't be call if p.disable_extra_networks
@@ -156,6 +161,25 @@ class Script: pass
+ def postprocess_batch_list(self, p, pp: PostprocessBatchListArgs, *args, **kwargs):
+ """
+ Same as postprocess_batch(), but receives batch images as a list of 3D tensors instead of a 4D tensor.
+ This is useful when you want to update the entire batch instead of individual images.
+
+ You can modify the postprocessing object (pp) to update the images in the batch, remove images, add images, etc.
+ If the number of images is different from the batch size when returning,
+ then the script has the responsibility to also update the following attributes in the processing object (p):
+ - p.prompts
+ - p.negative_prompts
+ - p.seeds
+ - p.subseeds
+
+ **kwargs will have same items as process_batch, and also:
+ - batch_number - index of current batch, from 0 to number of batches-1
+ """
+
+ pass
+
def postprocess_image(self, p, pp: PostprocessImageArgs, *args):
"""
Called for every image after it has been generated.
@@ -536,6 +560,14 @@ class ScriptRunner: except Exception:
errors.report(f"Error running postprocess_batch: {script.filename}", exc_info=True)
+ def postprocess_batch_list(self, p, pp: PostprocessBatchListArgs, **kwargs):
+ for script in self.alwayson_scripts:
+ try:
+ script_args = p.script_args[script.args_from:script.args_to]
+ script.postprocess_batch_list(p, pp, *script_args, **kwargs)
+ except Exception:
+ errors.report(f"Error running postprocess_batch_list: {script.filename}", exc_info=True)
+
def postprocess_image(self, p, pp: PostprocessImageArgs):
for script in self.alwayson_scripts:
try:
@@ -599,49 +631,3 @@ def reload_script_body_only(): reload_scripts = load_scripts # compatibility alias
-
-
-def add_classes_to_gradio_component(comp):
- """
- this adds gradio-* to the component for css styling (ie gradio-button to gr.Button), as well as some others
- """
-
- comp.elem_classes = [f"gradio-{comp.get_block_name()}", *(comp.elem_classes or [])]
-
- if getattr(comp, 'multiselect', False):
- comp.elem_classes.append('multiselect')
-
-
-
-def IOComponent_init(self, *args, **kwargs):
- if scripts_current is not None:
- scripts_current.before_component(self, **kwargs)
-
- script_callbacks.before_component_callback(self, **kwargs)
-
- res = original_IOComponent_init(self, *args, **kwargs)
-
- add_classes_to_gradio_component(self)
-
- script_callbacks.after_component_callback(self, **kwargs)
-
- if scripts_current is not None:
- scripts_current.after_component(self, **kwargs)
-
- return res
-
-
-original_IOComponent_init = gr.components.IOComponent.__init__
-gr.components.IOComponent.__init__ = IOComponent_init
-
-
-def BlockContext_init(self, *args, **kwargs):
- res = original_BlockContext_init(self, *args, **kwargs)
-
- add_classes_to_gradio_component(self)
-
- return res
-
-
-original_BlockContext_init = gr.blocks.BlockContext.__init__
-gr.blocks.BlockContext.__init__ = BlockContext_init
diff --git a/modules/sd_disable_initialization.py b/modules/sd_disable_initialization.py index 9fc89dc6..695c5736 100644 --- a/modules/sd_disable_initialization.py +++ b/modules/sd_disable_initialization.py @@ -3,8 +3,31 @@ import open_clip import torch
import transformers.utils.hub
+from modules import shared
-class DisableInitialization:
+
+class ReplaceHelper:
+ def __init__(self):
+ self.replaced = []
+
+ def replace(self, obj, field, func):
+ original = getattr(obj, field, None)
+ if original is None:
+ return None
+
+ self.replaced.append((obj, field, original))
+ setattr(obj, field, func)
+
+ return original
+
+ def restore(self):
+ for obj, field, original in self.replaced:
+ setattr(obj, field, original)
+
+ self.replaced.clear()
+
+
+class DisableInitialization(ReplaceHelper):
"""
When an object of this class enters a `with` block, it starts:
- preventing torch's layer initialization functions from working
@@ -21,7 +44,7 @@ class DisableInitialization: """
def __init__(self, disable_clip=True):
- self.replaced = []
+ super().__init__()
self.disable_clip = disable_clip
def replace(self, obj, field, func):
@@ -86,8 +109,81 @@ class DisableInitialization: self.transformers_utils_hub_get_from_cache = self.replace(transformers.utils.hub, 'get_from_cache', transformers_utils_hub_get_from_cache)
def __exit__(self, exc_type, exc_val, exc_tb):
- for obj, field, original in self.replaced:
- setattr(obj, field, original)
+ self.restore()
- self.replaced.clear()
+class InitializeOnMeta(ReplaceHelper):
+ """
+ Context manager that causes all parameters for linear/conv2d/mha layers to be allocated on meta device,
+ which results in those parameters having no values and taking no memory. model.to() will be broken and
+ will need to be repaired by using LoadStateDictOnMeta below when loading params from state dict.
+
+ Usage:
+ ```
+ with sd_disable_initialization.InitializeOnMeta():
+ sd_model = instantiate_from_config(sd_config.model)
+ ```
+ """
+
+ def __enter__(self):
+ if shared.cmd_opts.disable_model_loading_ram_optimization:
+ return
+
+ def set_device(x):
+ x["device"] = "meta"
+ return x
+
+ linear_init = self.replace(torch.nn.Linear, '__init__', lambda *args, **kwargs: linear_init(*args, **set_device(kwargs)))
+ conv2d_init = self.replace(torch.nn.Conv2d, '__init__', lambda *args, **kwargs: conv2d_init(*args, **set_device(kwargs)))
+ mha_init = self.replace(torch.nn.MultiheadAttention, '__init__', lambda *args, **kwargs: mha_init(*args, **set_device(kwargs)))
+ self.replace(torch.nn.Module, 'to', lambda *args, **kwargs: None)
+
+ def __exit__(self, exc_type, exc_val, exc_tb):
+ self.restore()
+
+
+class LoadStateDictOnMeta(ReplaceHelper):
+ """
+ Context manager that allows to read parameters from state_dict into a model that has some of its parameters in the meta device.
+ As those parameters are read from state_dict, they will be deleted from it, so by the end state_dict will be mostly empty, to save memory.
+ Meant to be used together with InitializeOnMeta above.
+
+ Usage:
+ ```
+ with sd_disable_initialization.LoadStateDictOnMeta(state_dict):
+ model.load_state_dict(state_dict, strict=False)
+ ```
+ """
+
+ def __init__(self, state_dict, device):
+ super().__init__()
+ self.state_dict = state_dict
+ self.device = device
+
+ def __enter__(self):
+ if shared.cmd_opts.disable_model_loading_ram_optimization:
+ return
+
+ sd = self.state_dict
+ device = self.device
+
+ def load_from_state_dict(original, self, state_dict, prefix, *args, **kwargs):
+ params = [(name, param) for name, param in self._parameters.items() if param is not None and param.is_meta]
+
+ for name, param in params:
+ if param.is_meta:
+ self._parameters[name] = torch.nn.parameter.Parameter(torch.zeros_like(param, device=device), requires_grad=param.requires_grad)
+
+ original(self, state_dict, prefix, *args, **kwargs)
+
+ for name, _ in params:
+ key = prefix + name
+ if key in sd:
+ del sd[key]
+
+ linear_load_from_state_dict = self.replace(torch.nn.Linear, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(linear_load_from_state_dict, *args, **kwargs))
+ conv2d_load_from_state_dict = self.replace(torch.nn.Conv2d, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(conv2d_load_from_state_dict, *args, **kwargs))
+ mha_load_from_state_dict = self.replace(torch.nn.MultiheadAttention, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(mha_load_from_state_dict, *args, **kwargs))
+
+ def __exit__(self, exc_type, exc_val, exc_tb):
+ self.restore()
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index f5615967..cfa5f0eb 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -197,7 +197,7 @@ class StableDiffusionModelHijack: conditioner.embedders[i] = sd_hijack_clip.FrozenCLIPEmbedderForSDXLWithCustomWords(embedder, self)
text_cond_models.append(conditioner.embedders[i])
if typename == 'FrozenOpenCLIPEmbedder2':
- embedder.model.token_embedding = EmbeddingsWithFixes(embedder.model.token_embedding, self)
+ embedder.model.token_embedding = EmbeddingsWithFixes(embedder.model.token_embedding, self, textual_inversion_key='clip_g')
conditioner.embedders[i] = sd_hijack_open_clip.FrozenOpenCLIPEmbedder2WithCustomWords(embedder, self)
text_cond_models.append(conditioner.embedders[i])
@@ -243,7 +243,7 @@ class StableDiffusionModelHijack: ldm.modules.diffusionmodules.openaimodel.UNetModel.forward = sd_unet.UNetModel_forward
def undo_hijack(self, m):
- if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
+ if type(m.cond_stage_model) == sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords:
m.cond_stage_model = m.cond_stage_model.wrapped
elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
@@ -292,10 +292,11 @@ class StableDiffusionModelHijack: class EmbeddingsWithFixes(torch.nn.Module):
- def __init__(self, wrapped, embeddings):
+ def __init__(self, wrapped, embeddings, textual_inversion_key='clip_l'):
super().__init__()
self.wrapped = wrapped
self.embeddings = embeddings
+ self.textual_inversion_key = textual_inversion_key
def forward(self, input_ids):
batch_fixes = self.embeddings.fixes
@@ -309,7 +310,8 @@ class EmbeddingsWithFixes(torch.nn.Module): vecs = []
for fixes, tensor in zip(batch_fixes, inputs_embeds):
for offset, embedding in fixes:
- emb = devices.cond_cast_unet(embedding.vec)
+ vec = embedding.vec[self.textual_inversion_key] if isinstance(embedding.vec, dict) else embedding.vec
+ emb = devices.cond_cast_unet(vec)
emb_len = min(tensor.shape[0] - offset - 1, emb.shape[0])
tensor = torch.cat([tensor[0:offset + 1], emb[0:emb_len], tensor[offset + 1 + emb_len:]])
diff --git a/modules/sd_hijack_clip.py b/modules/sd_hijack_clip.py index 5443e609..8f29057a 100644 --- a/modules/sd_hijack_clip.py +++ b/modules/sd_hijack_clip.py @@ -161,7 +161,7 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module): position += 1
continue
- emb_len = int(embedding.vec.shape[0])
+ emb_len = int(embedding.vectors)
if len(chunk.tokens) + emb_len > self.chunk_length:
next_chunk()
@@ -245,6 +245,8 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module): hashes.append(f"{name}: {shorthash}")
if hashes:
+ if self.hijack.extra_generation_params.get("TI hashes"):
+ hashes.append(self.hijack.extra_generation_params.get("TI hashes"))
self.hijack.extra_generation_params["TI hashes"] = ", ".join(hashes)
if getattr(self.wrapped, 'return_pooled', False):
@@ -270,12 +272,17 @@ class FrozenCLIPEmbedderWithCustomWordsBase(torch.nn.Module): z = self.encode_with_transformers(tokens)
+ pooled = getattr(z, 'pooled', None)
+
# restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise
batch_multipliers = torch.asarray(batch_multipliers).to(devices.device)
original_mean = z.mean()
- z *= batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape)
+ z = z * batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape)
new_mean = z.mean()
- z *= (original_mean / new_mean)
+ z = z * (original_mean / new_mean)
+
+ if pooled is not None:
+ z.pooled = pooled
return z
diff --git a/modules/sd_hijack_open_clip.py b/modules/sd_hijack_open_clip.py index bb0b96c7..25c5e983 100644 --- a/modules/sd_hijack_open_clip.py +++ b/modules/sd_hijack_open_clip.py @@ -32,7 +32,7 @@ class FrozenOpenCLIPEmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWit def encode_embedding_init_text(self, init_text, nvpt):
ids = tokenizer.encode(init_text)
ids = torch.asarray([ids], device=devices.device, dtype=torch.int)
- embedded = self.wrapped.model.token_embedding.wrapped(ids.to(self.wrapped.model.token_embedding.wrapped.weight.device)).squeeze(0)
+ embedded = self.wrapped.model.token_embedding.wrapped(ids).squeeze(0)
return embedded
diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index b5f85ba5..0e810eec 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -256,9 +256,9 @@ def split_cross_attention_forward(self, x, context=None, mask=None, **kwargs): raise RuntimeError(f'Not enough memory, use lower resolution (max approx. {max_res}x{max_res}). '
f'Need: {mem_required / 64 / gb:0.1f}GB free, Have:{mem_free_total / gb:0.1f}GB free')
- slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1]
+ slice_size = q.shape[1] // steps
for i in range(0, q.shape[1], slice_size):
- end = i + slice_size
+ end = min(i + slice_size, q.shape[1])
s1 = einsum('b i d, b j d -> b i j', q[:, i:end], k)
s2 = s1.softmax(dim=-1, dtype=q.dtype)
diff --git a/modules/sd_hijack_unet.py b/modules/sd_hijack_unet.py index ca1daf45..2101f1a0 100644 --- a/modules/sd_hijack_unet.py +++ b/modules/sd_hijack_unet.py @@ -39,7 +39,10 @@ def apply_model(orig_func, self, x_noisy, t, cond, **kwargs): if isinstance(cond, dict):
for y in cond.keys():
- cond[y] = [x.to(devices.dtype_unet) if isinstance(x, torch.Tensor) else x for x in cond[y]]
+ if isinstance(cond[y], list):
+ cond[y] = [x.to(devices.dtype_unet) if isinstance(x, torch.Tensor) else x for x in cond[y]]
+ else:
+ cond[y] = cond[y].to(devices.dtype_unet) if isinstance(cond[y], torch.Tensor) else cond[y]
with devices.autocast():
return orig_func(self, x_noisy.to(devices.dtype_unet), t.to(devices.dtype_unet), cond, **kwargs).float()
@@ -77,3 +80,6 @@ first_stage_sub = lambda orig_func, self, x, **kwargs: orig_func(self, x.to(devi CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.decode_first_stage', first_stage_sub, first_stage_cond)
CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.encode_first_stage', first_stage_sub, first_stage_cond)
CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.get_first_stage_encoding', lambda orig_func, *args, **kwargs: orig_func(*args, **kwargs).float(), first_stage_cond)
+
+CondFunc('sgm.modules.diffusionmodules.wrappers.OpenAIWrapper.forward', apply_model, unet_needs_upcast)
+CondFunc('sgm.modules.diffusionmodules.openaimodel.timestep_embedding', lambda orig_func, timesteps, *args, **kwargs: orig_func(timesteps, *args, **kwargs).to(torch.float32 if timesteps.dtype == torch.int64 else devices.dtype_unet), unet_needs_upcast)
diff --git a/modules/sd_models.py b/modules/sd_models.py index 729f03d7..1d93d893 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -14,7 +14,7 @@ import ldm.modules.midas as midas from ldm.util import instantiate_from_config
-from modules import paths, shared, modelloader, devices, script_callbacks, sd_vae, sd_disable_initialization, errors, hashes, sd_models_config, sd_unet, sd_models_xl
+from modules import paths, shared, modelloader, devices, script_callbacks, sd_vae, sd_disable_initialization, errors, hashes, sd_models_config, sd_unet, sd_models_xl, cache
from modules.sd_hijack_inpainting import do_inpainting_hijack
from modules.timer import Timer
import tomesd
@@ -33,6 +33,8 @@ class CheckpointInfo: self.filename = filename
abspath = os.path.abspath(filename)
+ self.is_safetensors = os.path.splitext(filename)[1].lower() == ".safetensors"
+
if shared.cmd_opts.ckpt_dir is not None and abspath.startswith(shared.cmd_opts.ckpt_dir):
name = abspath.replace(shared.cmd_opts.ckpt_dir, '')
elif abspath.startswith(model_path):
@@ -43,6 +45,19 @@ class CheckpointInfo: if name.startswith("\\") or name.startswith("/"):
name = name[1:]
+ def read_metadata():
+ metadata = read_metadata_from_safetensors(filename)
+ self.modelspec_thumbnail = metadata.pop('modelspec.thumbnail', None)
+
+ return metadata
+
+ self.metadata = {}
+ if self.is_safetensors:
+ try:
+ self.metadata = cache.cached_data_for_file('safetensors-metadata', "checkpoint/" + name, filename, read_metadata)
+ except Exception as e:
+ errors.display(e, f"reading metadata for {filename}")
+
self.name = name
self.name_for_extra = os.path.splitext(os.path.basename(filename))[0]
self.model_name = os.path.splitext(name.replace("/", "_").replace("\\", "_"))[0]
@@ -53,16 +68,7 @@ class CheckpointInfo: self.title = name if self.shorthash is None else f'{name} [{self.shorthash}]'
- self.ids = [self.hash, self.model_name, self.title, name, f'{name} [{self.hash}]'] + ([self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]'] if self.shorthash else [])
-
- self.metadata = {}
-
- _, ext = os.path.splitext(self.filename)
- if ext.lower() == ".safetensors":
- try:
- self.metadata = read_metadata_from_safetensors(filename)
- except Exception as e:
- errors.display(e, f"reading checkpoint metadata: {filename}")
+ self.ids = [self.hash, self.model_name, self.title, name, self.name_for_extra, f'{name} [{self.hash}]'] + ([self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]'] if self.shorthash else [])
def register(self):
checkpoints_list[self.title] = self
@@ -79,7 +85,7 @@ class CheckpointInfo: if self.shorthash not in self.ids:
self.ids += [self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]']
- checkpoints_list.pop(self.title)
+ checkpoints_list.pop(self.title, None)
self.title = f'{self.name} [{self.shorthash}]'
self.register()
@@ -290,6 +296,9 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
model.is_sdxl = hasattr(model, 'conditioner')
+ model.is_sd2 = not model.is_sdxl and hasattr(model.cond_stage_model, 'model')
+ model.is_sd1 = not model.is_sdxl and not model.is_sd2
+
if model.is_sdxl:
sd_models_xl.extend_sdxl(model)
@@ -323,7 +332,7 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer timer.record("apply half()")
- devices.dtype_unet = model.model.diffusion_model.dtype
+ devices.dtype_unet = torch.float16 if model.is_sdxl and not shared.cmd_opts.no_half else model.model.diffusion_model.dtype
devices.unet_needs_upcast = shared.cmd_opts.upcast_sampling and devices.dtype == torch.float16 and devices.dtype_unet == torch.float16
model.first_stage_model.to(devices.dtype_vae)
@@ -457,7 +466,6 @@ def get_empty_cond(sd_model): return sd_model.cond_stage_model([""])
-
def load_model(checkpoint_info=None, already_loaded_state_dict=None):
from modules import lowvram, sd_hijack
checkpoint_info = checkpoint_info or select_checkpoint()
@@ -491,20 +499,25 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None): sd_model = None
try:
- with sd_disable_initialization.DisableInitialization(disable_clip=clip_is_included_into_sd):
- sd_model = instantiate_from_config(sd_config.model)
- except Exception:
- pass
+ with sd_disable_initialization.DisableInitialization(disable_clip=clip_is_included_into_sd or shared.cmd_opts.do_not_download_clip):
+ with sd_disable_initialization.InitializeOnMeta():
+ sd_model = instantiate_from_config(sd_config.model)
+
+ except Exception as e:
+ errors.display(e, "creating model quickly", full_traceback=True)
if sd_model is None:
print('Failed to create model quickly; will retry using slow method.', file=sys.stderr)
- sd_model = instantiate_from_config(sd_config.model)
+
+ with sd_disable_initialization.InitializeOnMeta():
+ sd_model = instantiate_from_config(sd_config.model)
sd_model.used_config = checkpoint_config
timer.record("create model")
- load_model_weights(sd_model, checkpoint_info, state_dict, timer)
+ with sd_disable_initialization.LoadStateDictOnMeta(state_dict, devices.cpu):
+ load_model_weights(sd_model, checkpoint_info, state_dict, timer)
if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
lowvram.setup_for_low_vram(sd_model, shared.cmd_opts.medvram)
diff --git a/modules/sd_models_xl.py b/modules/sd_models_xl.py index 01320c7a..bc219508 100644 --- a/modules/sd_models_xl.py +++ b/modules/sd_models_xl.py @@ -12,8 +12,8 @@ def get_learned_conditioning(self: sgm.models.diffusion.DiffusionEngine, batch: for embedder in self.conditioner.embedders:
embedder.ucg_rate = 0.0
- width = getattr(self, 'target_width', 1024)
- height = getattr(self, 'target_height', 1024)
+ width = getattr(batch, 'width', 1024)
+ height = getattr(batch, 'height', 1024)
is_negative_prompt = getattr(batch, 'is_negative_prompt', False)
aesthetic_score = shared.opts.sdxl_refiner_low_aesthetic_score if is_negative_prompt else shared.opts.sdxl_refiner_high_aesthetic_score
@@ -56,6 +56,14 @@ def encode_embedding_init_text(self: sgm.modules.GeneralConditioner, init_text, return torch.cat(res, dim=1)
+def tokenize(self: sgm.modules.GeneralConditioner, texts):
+ for embedder in [embedder for embedder in self.embedders if hasattr(embedder, 'tokenize')]:
+ return embedder.tokenize(texts)
+
+ raise AssertionError('no tokenizer available')
+
+
+
def process_texts(self, texts):
for embedder in [embedder for embedder in self.embedders if hasattr(embedder, 'process_texts')]:
return embedder.process_texts(texts)
@@ -68,6 +76,7 @@ def get_target_prompt_token_count(self, token_count): # those additions to GeneralConditioner make it possible to use it as model.cond_stage_model from SD1.5 in exist
sgm.modules.GeneralConditioner.encode_embedding_init_text = encode_embedding_init_text
+sgm.modules.GeneralConditioner.tokenize = tokenize
sgm.modules.GeneralConditioner.process_texts = process_texts
sgm.modules.GeneralConditioner.get_target_prompt_token_count = get_target_prompt_token_count
diff --git a/modules/sd_samplers_common.py b/modules/sd_samplers_common.py index 763829f1..5deda761 100644 --- a/modules/sd_samplers_common.py +++ b/modules/sd_samplers_common.py @@ -2,10 +2,8 @@ from collections import namedtuple import numpy as np
import torch
from PIL import Image
-from modules import devices, processing, images, sd_vae_approx, sd_samplers, sd_vae_taesd
-
+from modules import devices, processing, images, sd_vae_approx, sd_samplers, sd_vae_taesd, shared
from modules.shared import opts, state
-import modules.shared as shared
SamplerData = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options'])
@@ -85,11 +83,13 @@ class InterruptedException(BaseException): pass
-if opts.randn_source == "CPU":
+def replace_torchsde_browinan():
import torchsde._brownian.brownian_interval
def torchsde_randn(size, dtype, device, seed):
- generator = torch.Generator(devices.cpu).manual_seed(int(seed))
- return torch.randn(size, dtype=dtype, device=devices.cpu, generator=generator).to(device)
+ return devices.randn_local(seed, size).to(device=device, dtype=dtype)
torchsde._brownian.brownian_interval._randn = torchsde_randn
+
+
+replace_torchsde_browinan()
diff --git a/modules/sd_samplers_extra.py b/modules/sd_samplers_extra.py new file mode 100644 index 00000000..1b981ca8 --- /dev/null +++ b/modules/sd_samplers_extra.py @@ -0,0 +1,74 @@ +import torch
+import tqdm
+import k_diffusion.sampling
+
+
+@torch.no_grad()
+def restart_sampler(model, x, sigmas, extra_args=None, callback=None, disable=None, s_noise=1., restart_list=None):
+ """Implements restart sampling in Restart Sampling for Improving Generative Processes (2023)
+ Restart_list format: {min_sigma: [ restart_steps, restart_times, max_sigma]}
+ If restart_list is None: will choose restart_list automatically, otherwise will use the given restart_list
+ """
+ extra_args = {} if extra_args is None else extra_args
+ s_in = x.new_ones([x.shape[0]])
+ step_id = 0
+ from k_diffusion.sampling import to_d, get_sigmas_karras
+
+ def heun_step(x, old_sigma, new_sigma, second_order=True):
+ nonlocal step_id
+ denoised = model(x, old_sigma * s_in, **extra_args)
+ d = to_d(x, old_sigma, denoised)
+ if callback is not None:
+ callback({'x': x, 'i': step_id, 'sigma': new_sigma, 'sigma_hat': old_sigma, 'denoised': denoised})
+ dt = new_sigma - old_sigma
+ if new_sigma == 0 or not second_order:
+ # Euler method
+ x = x + d * dt
+ else:
+ # Heun's method
+ x_2 = x + d * dt
+ denoised_2 = model(x_2, new_sigma * s_in, **extra_args)
+ d_2 = to_d(x_2, new_sigma, denoised_2)
+ d_prime = (d + d_2) / 2
+ x = x + d_prime * dt
+ step_id += 1
+ return x
+
+ steps = sigmas.shape[0] - 1
+ if restart_list is None:
+ if steps >= 20:
+ restart_steps = 9
+ restart_times = 1
+ if steps >= 36:
+ restart_steps = steps // 4
+ restart_times = 2
+ sigmas = get_sigmas_karras(steps - restart_steps * restart_times, sigmas[-2].item(), sigmas[0].item(), device=sigmas.device)
+ restart_list = {0.1: [restart_steps + 1, restart_times, 2]}
+ else:
+ restart_list = {}
+
+ restart_list = {int(torch.argmin(abs(sigmas - key), dim=0)): value for key, value in restart_list.items()}
+
+ step_list = []
+ for i in range(len(sigmas) - 1):
+ step_list.append((sigmas[i], sigmas[i + 1]))
+ if i + 1 in restart_list:
+ restart_steps, restart_times, restart_max = restart_list[i + 1]
+ min_idx = i + 1
+ max_idx = int(torch.argmin(abs(sigmas - restart_max), dim=0))
+ if max_idx < min_idx:
+ sigma_restart = get_sigmas_karras(restart_steps, sigmas[min_idx].item(), sigmas[max_idx].item(), device=sigmas.device)[:-1]
+ while restart_times > 0:
+ restart_times -= 1
+ step_list.extend([(old_sigma, new_sigma) for (old_sigma, new_sigma) in zip(sigma_restart[:-1], sigma_restart[1:])])
+
+ last_sigma = None
+ for old_sigma, new_sigma in tqdm.tqdm(step_list, disable=disable):
+ if last_sigma is None:
+ last_sigma = old_sigma
+ elif last_sigma < old_sigma:
+ x = x + k_diffusion.sampling.torch.randn_like(x) * s_noise * (old_sigma ** 2 - last_sigma ** 2) ** 0.5
+ x = heun_step(x, old_sigma, new_sigma)
+ last_sigma = new_sigma
+
+ return x
diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index 5552a8dc..d72c1b5f 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -2,7 +2,7 @@ from collections import deque import torch
import inspect
import k_diffusion.sampling
-from modules import prompt_parser, devices, sd_samplers_common
+from modules import prompt_parser, devices, sd_samplers_common, sd_samplers_extra
from modules.shared import opts, state
import modules.shared as shared
@@ -30,12 +30,14 @@ samplers_k_diffusion = [ ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}),
('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras', "second_order": True, "brownian_noise": True}),
('DPM++ 2M SDE Karras', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_ka'], {'scheduler': 'karras', "brownian_noise": True}),
+ ('Restart', sd_samplers_extra.restart_sampler, ['restart'], {'scheduler': 'karras'}),
]
+
samplers_data_k_diffusion = [
sd_samplers_common.SamplerData(label, lambda model, funcname=funcname: KDiffusionSampler(funcname, model), aliases, options)
for label, funcname, aliases, options in samplers_k_diffusion
- if hasattr(k_diffusion.sampling, funcname)
+ if callable(funcname) or hasattr(k_diffusion.sampling, funcname)
]
sampler_extra_params = {
@@ -258,10 +260,7 @@ class TorchHijack: if noise.shape == x.shape:
return noise
- if opts.randn_source == "CPU" or x.device.type == 'mps':
- return torch.randn_like(x, device=devices.cpu).to(x.device)
- else:
- return torch.randn_like(x)
+ return devices.randn_like(x)
class KDiffusionSampler:
@@ -270,7 +269,7 @@ class KDiffusionSampler: self.model_wrap = denoiser(sd_model, quantize=shared.opts.enable_quantization)
self.funcname = funcname
- self.func = getattr(k_diffusion.sampling, self.funcname)
+ self.func = funcname if callable(funcname) else getattr(k_diffusion.sampling, self.funcname)
self.extra_params = sampler_extra_params.get(funcname, [])
self.model_wrap_cfg = CFGDenoiser(self.model_wrap)
self.sampler_noises = None
diff --git a/modules/shared.py b/modules/shared.py index 6162938a..cec030f7 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -11,6 +11,7 @@ import gradio as gr import torch
import tqdm
+import launch
import modules.interrogate
import modules.memmon
import modules.styles
@@ -26,7 +27,7 @@ demo = None parser = cmd_args.parser
-script_loading.preload_extensions(extensions_dir, parser)
+script_loading.preload_extensions(extensions_dir, parser, extension_list=launch.list_extensions(launch.args.ui_settings_file))
script_loading.preload_extensions(extensions_builtin_dir, parser)
if os.environ.get('IGNORE_CMD_ARGS_ERRORS', None) is None:
@@ -384,7 +385,8 @@ options_templates.update(options_section(('face-restoration', "Face restoration" }))
options_templates.update(options_section(('system', "System"), {
- "show_warnings": OptionInfo(False, "Show warnings in console."),
+ "show_warnings": OptionInfo(False, "Show warnings in console.").needs_restart(),
+ "show_gradio_deprecation_warnings": OptionInfo(True, "Show gradio deprecation warnings in console.").needs_restart(),
"memmon_poll_rate": OptionInfo(8, "VRAM usage polls per second during generation.", gr.Slider, {"minimum": 0, "maximum": 40, "step": 1}).info("0 = disable"),
"samples_log_stdout": OptionInfo(False, "Always print all generation info to standard output"),
"multiple_tqdm": OptionInfo(True, "Add a second progress bar to the console that shows progress for an entire job."),
@@ -426,7 +428,8 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "comma_padding_backtrack": OptionInfo(20, "Prompt word wrap length limit", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1}).info("in tokens - for texts shorter than specified, if they don't fit into 75 token limit, move them to the next 75 token chunk"),
"CLIP_stop_at_last_layers": OptionInfo(1, "Clip skip", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}).link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#clip-skip").info("ignore last layers of CLIP network; 1 ignores none, 2 ignores one layer"),
"upcast_attn": OptionInfo(False, "Upcast cross attention layer to float32"),
- "randn_source": OptionInfo("GPU", "Random number generator source.", gr.Radio, {"choices": ["GPU", "CPU"]}).info("changes seeds drastically; use CPU to produce the same picture across different videocard vendors"),
+ "auto_vae_precision": OptionInfo(True, "Automaticlly revert VAE to 32-bit floats").info("triggers when a tensor with NaNs is produced in VAE; disabling the option in this case will result in a black square image"),
+ "randn_source": OptionInfo("GPU", "Random number generator source.", gr.Radio, {"choices": ["GPU", "CPU", "NV"]}).info("changes seeds drastically; use CPU to produce the same picture across different videocard vendors; use NV to produce same picture as on NVidia videocards"),
}))
options_templates.update(options_section(('sdxl', "Stable Diffusion XL"), {
diff --git a/modules/styles.py b/modules/styles.py index ec0e1bc5..0740fe1b 100644 --- a/modules/styles.py +++ b/modules/styles.py @@ -106,10 +106,7 @@ class StyleDatabase: if os.path.exists(path):
shutil.copy(path, f"{path}.bak")
- fd = os.open(path, os.O_RDWR | os.O_CREAT)
- with os.fdopen(fd, "w", encoding="utf-8-sig", newline='') as file:
- # _fields is actually part of the public API: typing.NamedTuple is a replacement for collections.NamedTuple,
- # and collections.NamedTuple has explicit documentation for accessing _fields. Same goes for _asdict()
+ with open(path, "w", encoding="utf-8-sig", newline='') as file:
writer = csv.DictWriter(file, fieldnames=PromptStyle._fields)
writer.writeheader()
writer.writerows(style._asdict() for k, style in self.styles.items())
diff --git a/modules/sysinfo.py b/modules/sysinfo.py index 5f15ac4f..cf24c6dd 100644 --- a/modules/sysinfo.py +++ b/modules/sysinfo.py @@ -109,11 +109,15 @@ def format_traceback(tb): return [[f"{x.filename}, line {x.lineno}, {x.name}", x.line] for x in traceback.extract_tb(tb)]
+def format_exception(e, tb):
+ return {"exception": str(e), "traceback": format_traceback(tb)}
+
+
def get_exceptions():
try:
from modules import errors
- return [{"exception": str(e), "traceback": format_traceback(tb)} for e, tb in reversed(errors.exception_records)]
+ return list(reversed(errors.exception_records))
except Exception as e:
return str(e)
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 6166c76f..4713bc2d 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -181,29 +181,38 @@ class EmbeddingDatabase: else:
return
+
# textual inversion embeddings
if 'string_to_param' in data:
param_dict = data['string_to_param']
param_dict = getattr(param_dict, '_parameters', param_dict) # fix for torch 1.12.1 loading saved file from torch 1.11
assert len(param_dict) == 1, 'embedding file has multiple terms in it'
emb = next(iter(param_dict.items()))[1]
- # diffuser concepts
- elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor:
+ vec = emb.detach().to(devices.device, dtype=torch.float32)
+ shape = vec.shape[-1]
+ vectors = vec.shape[0]
+ elif type(data) == dict and 'clip_g' in data and 'clip_l' in data: # SDXL embedding
+ vec = {k: v.detach().to(devices.device, dtype=torch.float32) for k, v in data.items()}
+ shape = data['clip_g'].shape[-1] + data['clip_l'].shape[-1]
+ vectors = data['clip_g'].shape[0]
+ elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor: # diffuser concepts
assert len(data.keys()) == 1, 'embedding file has multiple terms in it'
emb = next(iter(data.values()))
if len(emb.shape) == 1:
emb = emb.unsqueeze(0)
+ vec = emb.detach().to(devices.device, dtype=torch.float32)
+ shape = vec.shape[-1]
+ vectors = vec.shape[0]
else:
raise Exception(f"Couldn't identify {filename} as neither textual inversion embedding nor diffuser concept.")
- vec = emb.detach().to(devices.device, dtype=torch.float32)
embedding = Embedding(vec, name)
embedding.step = data.get('step', None)
embedding.sd_checkpoint = data.get('sd_checkpoint', None)
embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None)
- embedding.vectors = vec.shape[0]
- embedding.shape = vec.shape[-1]
+ embedding.vectors = vectors
+ embedding.shape = shape
embedding.filename = path
embedding.set_hash(hashes.sha256(embedding.filename, "textual_inversion/" + name) or '')
diff --git a/modules/timer.py b/modules/timer.py index da99e49f..1d38595c 100644 --- a/modules/timer.py +++ b/modules/timer.py @@ -1,4 +1,5 @@ import time
+import argparse
class TimerSubcategory:
@@ -11,20 +12,27 @@ class TimerSubcategory: def __enter__(self):
self.start = time.time()
self.timer.base_category = self.original_base_category + self.category + "/"
+ self.timer.subcategory_level += 1
+
+ if self.timer.print_log:
+ print(f"{' ' * self.timer.subcategory_level}{self.category}:")
def __exit__(self, exc_type, exc_val, exc_tb):
elapsed_for_subcategroy = time.time() - self.start
self.timer.base_category = self.original_base_category
self.timer.add_time_to_record(self.original_base_category + self.category, elapsed_for_subcategroy)
- self.timer.record(self.category)
+ self.timer.subcategory_level -= 1
+ self.timer.record(self.category, disable_log=True)
class Timer:
- def __init__(self):
+ def __init__(self, print_log=False):
self.start = time.time()
self.records = {}
self.total = 0
self.base_category = ''
+ self.print_log = print_log
+ self.subcategory_level = 0
def elapsed(self):
end = time.time()
@@ -38,13 +46,16 @@ class Timer: self.records[category] += amount
- def record(self, category, extra_time=0):
+ def record(self, category, extra_time=0, disable_log=False):
e = self.elapsed()
self.add_time_to_record(self.base_category + category, e + extra_time)
self.total += e + extra_time
+ if self.print_log and not disable_log:
+ print(f"{' ' * self.subcategory_level}{category}: done in {e + extra_time:.3f}s")
+
def subcategory(self, name):
self.elapsed()
@@ -71,6 +82,10 @@ class Timer: self.__init__()
-startup_timer = Timer()
+parser = argparse.ArgumentParser(add_help=False)
+parser.add_argument("--log-startup", action='store_true', help="print a detailed log of what's happening at startup")
+args = parser.parse_known_args()[0]
+
+startup_timer = Timer(print_log=args.log_startup)
startup_record = None
diff --git a/modules/ui.py b/modules/ui.py index 07ecee7b..822a7660 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -12,34 +12,30 @@ import numpy as np from PIL import Image, PngImagePlugin # noqa: F401
from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, wrap_gradio_call
-from modules import sd_hijack, sd_models, script_callbacks, ui_extensions, deepbooru, sd_vae, extra_networks, ui_common, ui_postprocessing, progress, ui_loadsave, errors, shared_items, ui_settings, timer, sysinfo
+from modules import gradio_extensons # noqa: F401
+from modules import sd_hijack, sd_models, script_callbacks, ui_extensions, deepbooru, extra_networks, ui_common, ui_postprocessing, progress, ui_loadsave, errors, shared_items, ui_settings, timer, sysinfo, ui_checkpoint_merger, ui_prompt_styles, scripts
from modules.ui_components import FormRow, FormGroup, ToolButton, FormHTML
from modules.paths import script_path
from modules.ui_common import create_refresh_button
from modules.ui_gradio_extensions import reload_javascript
-
from modules.shared import opts, cmd_opts
-import modules.codeformer_model
import modules.generation_parameters_copypaste as parameters_copypaste
-import modules.gfpgan_model
-import modules.hypernetworks.ui
-import modules.scripts
+import modules.hypernetworks.ui as hypernetworks_ui
+import modules.textual_inversion.ui as textual_inversion_ui
+import modules.textual_inversion.textual_inversion as textual_inversion
import modules.shared as shared
-import modules.styles
-import modules.textual_inversion.ui
+import modules.images
from modules import prompt_parser
from modules.sd_hijack import model_hijack
from modules.sd_samplers import samplers, samplers_for_img2img
-from modules.textual_inversion import textual_inversion
-import modules.hypernetworks.ui
from modules.generation_parameters_copypaste import image_from_url_text
-import modules.extras
create_setting_component = ui_settings.create_setting_component
warnings.filterwarnings("default" if opts.show_warnings else "ignore", category=UserWarning)
+warnings.filterwarnings("default" if opts.show_gradio_deprecation_warnings else "ignore", category=gr.deprecation.GradioDeprecationWarning)
# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the browser will not show any UI
mimetypes.init()
@@ -92,19 +88,6 @@ def send_gradio_gallery_to_image(x): return image_from_url_text(x[0])
-def add_style(name: str, prompt: str, negative_prompt: str):
- if name is None:
- return [gr_show() for x in range(4)]
-
- style = modules.styles.PromptStyle(name, prompt, negative_prompt)
- shared.prompt_styles.styles[style.name] = style
- # Save all loaded prompt styles: this allows us to update the storage format in the future more easily, because we
- # reserialize all styles every time we save them
- shared.prompt_styles.save_styles(shared.styles_filename)
-
- return [gr.Dropdown.update(visible=True, choices=list(shared.prompt_styles.styles)) for _ in range(2)]
-
-
def calc_resolution_hires(enable, width, height, hr_scale, hr_resize_x, hr_resize_y):
from modules import processing, devices
@@ -129,13 +112,6 @@ def resize_from_to_html(width, height, scale_by): return f"resize: from <span class='resolution'>{width}x{height}</span> to <span class='resolution'>{target_width}x{target_height}</span>"
-def apply_styles(prompt, prompt_neg, styles):
- prompt = shared.prompt_styles.apply_styles_to_prompt(prompt, styles)
- prompt_neg = shared.prompt_styles.apply_negative_styles_to_prompt(prompt_neg, styles)
-
- return [gr.Textbox.update(value=prompt), gr.Textbox.update(value=prompt_neg), gr.Dropdown.update(value=[])]
-
-
def process_interrogate(interrogation_function, mode, ii_input_dir, ii_output_dir, *ii_singles):
if mode in {0, 1, 3, 4}:
return [interrogation_function(ii_singles[mode]), None]
@@ -172,7 +148,6 @@ def interrogate_deepbooru(image): def create_seed_inputs(target_interface):
with FormRow(elem_id=f"{target_interface}_seed_row", variant="compact"):
seed = (gr.Textbox if cmd_opts.use_textbox_seed else gr.Number)(label='Seed', value=-1, elem_id=f"{target_interface}_seed")
- seed.style(container=False)
random_seed = ToolButton(random_symbol, elem_id=f"{target_interface}_random_seed", label='Random seed')
reuse_seed = ToolButton(reuse_symbol, elem_id=f"{target_interface}_reuse_seed", label='Reuse seed')
@@ -184,7 +159,6 @@ def create_seed_inputs(target_interface): with FormRow(visible=False, elem_id=f"{target_interface}_subseed_row") as seed_extra_row_1:
seed_extras.append(seed_extra_row_1)
subseed = gr.Number(label='Variation seed', value=-1, elem_id=f"{target_interface}_subseed")
- subseed.style(container=False)
random_subseed = ToolButton(random_symbol, elem_id=f"{target_interface}_random_subseed")
reuse_subseed = ToolButton(reuse_symbol, elem_id=f"{target_interface}_reuse_subseed")
subseed_strength = gr.Slider(label='Variation strength', value=0.0, minimum=0, maximum=1, step=0.01, elem_id=f"{target_interface}_subseed_strength")
@@ -267,71 +241,78 @@ def update_token_counter(text, steps): return f"<span class='gr-box gr-text-input'>{token_count}/{max_length}</span>"
-def create_toprow(is_img2img):
- id_part = "img2img" if is_img2img else "txt2img"
+class Toprow:
+ """Creates a top row UI with prompts, generate button, styles, extra little buttons for things, and enables some functionality related to their operation"""
- with gr.Row(elem_id=f"{id_part}_toprow", variant="compact"):
- with gr.Column(elem_id=f"{id_part}_prompt_container", scale=6):
- with gr.Row():
- with gr.Column(scale=80):
- with gr.Row():
- prompt = gr.Textbox(label="Prompt", elem_id=f"{id_part}_prompt", show_label=False, lines=3, placeholder="Prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
+ def __init__(self, is_img2img):
+ id_part = "img2img" if is_img2img else "txt2img"
+ self.id_part = id_part
- with gr.Row():
- with gr.Column(scale=80):
- with gr.Row():
- negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{id_part}_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
-
- button_interrogate = None
- button_deepbooru = None
- if is_img2img:
- with gr.Column(scale=1, elem_classes="interrogate-col"):
- button_interrogate = gr.Button('Interrogate\nCLIP', elem_id="interrogate")
- button_deepbooru = gr.Button('Interrogate\nDeepBooru', elem_id="deepbooru")
-
- with gr.Column(scale=1, elem_id=f"{id_part}_actions_column"):
- with gr.Row(elem_id=f"{id_part}_generate_box", elem_classes="generate-box"):
- interrupt = gr.Button('Interrupt', elem_id=f"{id_part}_interrupt", elem_classes="generate-box-interrupt")
- skip = gr.Button('Skip', elem_id=f"{id_part}_skip", elem_classes="generate-box-skip")
- submit = gr.Button('Generate', elem_id=f"{id_part}_generate", variant='primary')
-
- skip.click(
- fn=lambda: shared.state.skip(),
- inputs=[],
- outputs=[],
- )
+ with gr.Row(elem_id=f"{id_part}_toprow", variant="compact"):
+ with gr.Column(elem_id=f"{id_part}_prompt_container", scale=6):
+ with gr.Row():
+ with gr.Column(scale=80):
+ with gr.Row():
+ self.prompt = gr.Textbox(label="Prompt", elem_id=f"{id_part}_prompt", show_label=False, lines=3, placeholder="Prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
+ self.prompt_img = gr.File(label="", elem_id=f"{id_part}_prompt_image", file_count="single", type="binary", visible=False)
- interrupt.click(
- fn=lambda: shared.state.interrupt(),
- inputs=[],
- outputs=[],
- )
+ with gr.Row():
+ with gr.Column(scale=80):
+ with gr.Row():
+ self.negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{id_part}_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
- with gr.Row(elem_id=f"{id_part}_tools"):
- paste = ToolButton(value=paste_symbol, elem_id="paste")
- clear_prompt_button = ToolButton(value=clear_prompt_symbol, elem_id=f"{id_part}_clear_prompt")
- extra_networks_button = ToolButton(value=extra_networks_symbol, elem_id=f"{id_part}_extra_networks")
- prompt_style_apply = ToolButton(value=apply_style_symbol, elem_id=f"{id_part}_style_apply")
- save_style = ToolButton(value=save_style_symbol, elem_id=f"{id_part}_style_create")
- restore_progress_button = ToolButton(value=restore_progress_symbol, elem_id=f"{id_part}_restore_progress", visible=False)
-
- token_counter = gr.HTML(value="<span>0/75</span>", elem_id=f"{id_part}_token_counter", elem_classes=["token-counter"])
- token_button = gr.Button(visible=False, elem_id=f"{id_part}_token_button")
- negative_token_counter = gr.HTML(value="<span>0/75</span>", elem_id=f"{id_part}_negative_token_counter", elem_classes=["token-counter"])
- negative_token_button = gr.Button(visible=False, elem_id=f"{id_part}_negative_token_button")
-
- clear_prompt_button.click(
- fn=lambda *x: x,
- _js="confirm_clear_prompt",
- inputs=[prompt, negative_prompt],
- outputs=[prompt, negative_prompt],
- )
- with gr.Row(elem_id=f"{id_part}_styles_row"):
- prompt_styles = gr.Dropdown(label="Styles", elem_id=f"{id_part}_styles", choices=[k for k, v in shared.prompt_styles.styles.items()], value=[], multiselect=True)
- create_refresh_button(prompt_styles, shared.prompt_styles.reload, lambda: {"choices": [k for k, v in shared.prompt_styles.styles.items()]}, f"refresh_{id_part}_styles")
+ self.button_interrogate = None
+ self.button_deepbooru = None
+ if is_img2img:
+ with gr.Column(scale=1, elem_classes="interrogate-col"):
+ self.button_interrogate = gr.Button('Interrogate\nCLIP', elem_id="interrogate")
+ self.button_deepbooru = gr.Button('Interrogate\nDeepBooru', elem_id="deepbooru")
- return prompt, prompt_styles, negative_prompt, submit, button_interrogate, button_deepbooru, prompt_style_apply, save_style, paste, extra_networks_button, token_counter, token_button, negative_token_counter, negative_token_button, restore_progress_button
+ with gr.Column(scale=1, elem_id=f"{id_part}_actions_column"):
+ with gr.Row(elem_id=f"{id_part}_generate_box", elem_classes="generate-box"):
+ self.interrupt = gr.Button('Interrupt', elem_id=f"{id_part}_interrupt", elem_classes="generate-box-interrupt")
+ self.skip = gr.Button('Skip', elem_id=f"{id_part}_skip", elem_classes="generate-box-skip")
+ self.submit = gr.Button('Generate', elem_id=f"{id_part}_generate", variant='primary')
+
+ self.skip.click(
+ fn=lambda: shared.state.skip(),
+ inputs=[],
+ outputs=[],
+ )
+
+ self.interrupt.click(
+ fn=lambda: shared.state.interrupt(),
+ inputs=[],
+ outputs=[],
+ )
+
+ with gr.Row(elem_id=f"{id_part}_tools"):
+ self.paste = ToolButton(value=paste_symbol, elem_id="paste")
+ self.clear_prompt_button = ToolButton(value=clear_prompt_symbol, elem_id=f"{id_part}_clear_prompt")
+ self.extra_networks_button = ToolButton(value=extra_networks_symbol, elem_id=f"{id_part}_extra_networks")
+ self.restore_progress_button = ToolButton(value=restore_progress_symbol, elem_id=f"{id_part}_restore_progress", visible=False)
+
+ self.token_counter = gr.HTML(value="<span>0/75</span>", elem_id=f"{id_part}_token_counter", elem_classes=["token-counter"])
+ self.token_button = gr.Button(visible=False, elem_id=f"{id_part}_token_button")
+ self.negative_token_counter = gr.HTML(value="<span>0/75</span>", elem_id=f"{id_part}_negative_token_counter", elem_classes=["token-counter"])
+ self.negative_token_button = gr.Button(visible=False, elem_id=f"{id_part}_negative_token_button")
+
+ self.clear_prompt_button.click(
+ fn=lambda *x: x,
+ _js="confirm_clear_prompt",
+ inputs=[self.prompt, self.negative_prompt],
+ outputs=[self.prompt, self.negative_prompt],
+ )
+
+ self.ui_styles = ui_prompt_styles.UiPromptStyles(id_part, self.prompt, self.negative_prompt)
+
+ self.prompt_img.change(
+ fn=modules.images.image_data,
+ inputs=[self.prompt_img],
+ outputs=[self.prompt, self.prompt_img],
+ show_progress=False,
+ )
def setup_progressbar(*args, **kwargs):
@@ -415,22 +396,21 @@ def create_ui(): parameters_copypaste.reset()
- modules.scripts.scripts_current = modules.scripts.scripts_txt2img
- modules.scripts.scripts_txt2img.initialize_scripts(is_img2img=False)
+ scripts.scripts_current = scripts.scripts_txt2img
+ scripts.scripts_txt2img.initialize_scripts(is_img2img=False)
with gr.Blocks(analytics_enabled=False) as txt2img_interface:
- txt2img_prompt, txt2img_prompt_styles, txt2img_negative_prompt, submit, _, _, txt2img_prompt_style_apply, txt2img_save_style, txt2img_paste, extra_networks_button, token_counter, token_button, negative_token_counter, negative_token_button, restore_progress_button = create_toprow(is_img2img=False)
+ toprow = Toprow(is_img2img=False)
dummy_component = gr.Label(visible=False)
- txt_prompt_img = gr.File(label="", elem_id="txt2img_prompt_image", file_count="single", type="binary", visible=False)
with FormRow(variant='compact', elem_id="txt2img_extra_networks", visible=False) as extra_networks:
from modules import ui_extra_networks
- extra_networks_ui = ui_extra_networks.create_ui(extra_networks, extra_networks_button, 'txt2img')
+ extra_networks_ui = ui_extra_networks.create_ui(extra_networks, toprow.extra_networks_button, 'txt2img')
- with gr.Row().style(equal_height=False):
+ with gr.Row(equal_height=False):
with gr.Column(variant='compact', elem_id="txt2img_settings"):
- modules.scripts.scripts_txt2img.prepare_ui()
+ scripts.scripts_txt2img.prepare_ui()
for category in ordered_ui_categories():
if category == "sampler":
@@ -498,10 +478,10 @@ def create_ui(): elif category == "scripts":
with FormGroup(elem_id="txt2img_script_container"):
- custom_inputs = modules.scripts.scripts_txt2img.setup_ui()
+ custom_inputs = scripts.scripts_txt2img.setup_ui()
else:
- modules.scripts.scripts_txt2img.setup_ui_for_section(category)
+ scripts.scripts_txt2img.setup_ui_for_section(category)
hr_resolution_preview_inputs = [enable_hr, width, height, hr_scale, hr_resize_x, hr_resize_y]
@@ -532,9 +512,9 @@ def create_ui(): _js="submit",
inputs=[
dummy_component,
- txt2img_prompt,
- txt2img_negative_prompt,
- txt2img_prompt_styles,
+ toprow.prompt,
+ toprow.negative_prompt,
+ toprow.ui_styles.dropdown,
steps,
sampler_index,
restore_faces,
@@ -569,12 +549,12 @@ def create_ui(): show_progress=False,
)
- txt2img_prompt.submit(**txt2img_args)
- submit.click(**txt2img_args)
+ toprow.prompt.submit(**txt2img_args)
+ toprow.submit.click(**txt2img_args)
res_switch_btn.click(fn=None, _js="function(){switchWidthHeight('txt2img')}", inputs=None, outputs=None, show_progress=False)
- restore_progress_button.click(
+ toprow.restore_progress_button.click(
fn=progress.restore_progress,
_js="restoreProgressTxt2img",
inputs=[dummy_component],
@@ -587,18 +567,6 @@ def create_ui(): show_progress=False,
)
- txt_prompt_img.change(
- fn=modules.images.image_data,
- inputs=[
- txt_prompt_img
- ],
- outputs=[
- txt2img_prompt,
- txt_prompt_img
- ],
- show_progress=False,
- )
-
enable_hr.change(
fn=lambda x: gr_show(x),
inputs=[enable_hr],
@@ -607,8 +575,8 @@ def create_ui(): )
txt2img_paste_fields = [
- (txt2img_prompt, "Prompt"),
- (txt2img_negative_prompt, "Negative prompt"),
+ (toprow.prompt, "Prompt"),
+ (toprow.negative_prompt, "Negative prompt"),
(steps, "Steps"),
(sampler_index, "Sampler"),
(restore_faces, "Face restoration"),
@@ -621,7 +589,7 @@ def create_ui(): (subseed_strength, "Variation seed strength"),
(seed_resize_from_w, "Seed resize from-1"),
(seed_resize_from_h, "Seed resize from-2"),
- (txt2img_prompt_styles, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update()),
+ (toprow.ui_styles.dropdown, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update()),
(denoising_strength, "Denoising strength"),
(enable_hr, lambda d: "Denoising strength" in d),
(hr_options, lambda d: gr.Row.update(visible="Denoising strength" in d)),
@@ -635,16 +603,16 @@ def create_ui(): (hr_prompt, "Hires prompt"),
(hr_negative_prompt, "Hires negative prompt"),
(hr_prompts_container, lambda d: gr.update(visible=True) if d.get("Hires prompt", "") != "" or d.get("Hires negative prompt", "") != "" else gr.update()),
- *modules.scripts.scripts_txt2img.infotext_fields
+ *scripts.scripts_txt2img.infotext_fields
]
parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields, override_settings)
parameters_copypaste.register_paste_params_button(parameters_copypaste.ParamBinding(
- paste_button=txt2img_paste, tabname="txt2img", source_text_component=txt2img_prompt, source_image_component=None,
+ paste_button=toprow.paste, tabname="txt2img", source_text_component=toprow.prompt, source_image_component=None,
))
txt2img_preview_params = [
- txt2img_prompt,
- txt2img_negative_prompt,
+ toprow.prompt,
+ toprow.negative_prompt,
steps,
sampler_index,
cfg_scale,
@@ -653,24 +621,22 @@ def create_ui(): height,
]
- token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[txt2img_prompt, steps], outputs=[token_counter])
- negative_token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[txt2img_negative_prompt, steps], outputs=[negative_token_counter])
+ toprow.token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[toprow.prompt, steps], outputs=[toprow.token_counter])
+ toprow.negative_token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[toprow.negative_prompt, steps], outputs=[toprow.negative_token_counter])
ui_extra_networks.setup_ui(extra_networks_ui, txt2img_gallery)
- modules.scripts.scripts_current = modules.scripts.scripts_img2img
- modules.scripts.scripts_img2img.initialize_scripts(is_img2img=True)
+ scripts.scripts_current = scripts.scripts_img2img
+ scripts.scripts_img2img.initialize_scripts(is_img2img=True)
with gr.Blocks(analytics_enabled=False) as img2img_interface:
- img2img_prompt, img2img_prompt_styles, img2img_negative_prompt, submit, img2img_interrogate, img2img_deepbooru, img2img_prompt_style_apply, img2img_save_style, img2img_paste, extra_networks_button, token_counter, token_button, negative_token_counter, negative_token_button, restore_progress_button = create_toprow(is_img2img=True)
-
- img2img_prompt_img = gr.File(label="", elem_id="img2img_prompt_image", file_count="single", type="binary", visible=False)
+ toprow = Toprow(is_img2img=True)
with FormRow(variant='compact', elem_id="img2img_extra_networks", visible=False) as extra_networks:
from modules import ui_extra_networks
- extra_networks_ui_img2img = ui_extra_networks.create_ui(extra_networks, extra_networks_button, 'img2img')
+ extra_networks_ui_img2img = ui_extra_networks.create_ui(extra_networks, toprow.extra_networks_button, 'img2img')
- with FormRow().style(equal_height=False):
+ with FormRow(equal_height=False):
with gr.Column(variant='compact', elem_id="img2img_settings"):
copy_image_buttons = []
copy_image_destinations = {}
@@ -692,19 +658,19 @@ def create_ui(): img2img_selected_tab = gr.State(0)
with gr.TabItem('img2img', id='img2img', elem_id="img2img_img2img_tab") as tab_img2img:
- init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool="editor", image_mode="RGBA").style(height=opts.img2img_editor_height)
+ init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool="editor", image_mode="RGBA", height=opts.img2img_editor_height)
add_copy_image_controls('img2img', init_img)
with gr.TabItem('Sketch', id='img2img_sketch', elem_id="img2img_img2img_sketch_tab") as tab_sketch:
- sketch = gr.Image(label="Image for img2img", elem_id="img2img_sketch", show_label=False, source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGBA").style(height=opts.img2img_editor_height)
+ sketch = gr.Image(label="Image for img2img", elem_id="img2img_sketch", show_label=False, source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGBA", height=opts.img2img_editor_height)
add_copy_image_controls('sketch', sketch)
with gr.TabItem('Inpaint', id='inpaint', elem_id="img2img_inpaint_tab") as tab_inpaint:
- init_img_with_mask = gr.Image(label="Image for inpainting with mask", show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool="sketch", image_mode="RGBA").style(height=opts.img2img_editor_height)
+ init_img_with_mask = gr.Image(label="Image for inpainting with mask", show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool="sketch", image_mode="RGBA", height=opts.img2img_editor_height)
add_copy_image_controls('inpaint', init_img_with_mask)
with gr.TabItem('Inpaint sketch', id='inpaint_sketch', elem_id="img2img_inpaint_sketch_tab") as tab_inpaint_color:
- inpaint_color_sketch = gr.Image(label="Color sketch inpainting", show_label=False, elem_id="inpaint_sketch", source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGBA").style(height=opts.img2img_editor_height)
+ inpaint_color_sketch = gr.Image(label="Color sketch inpainting", show_label=False, elem_id="inpaint_sketch", source="upload", interactive=True, type="pil", tool="color-sketch", image_mode="RGBA", height=opts.img2img_editor_height)
inpaint_color_sketch_orig = gr.State(None)
add_copy_image_controls('inpaint_sketch', inpaint_color_sketch)
@@ -764,7 +730,7 @@ def create_ui(): with FormRow():
resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize (latent upscale)"], type="index", value="Just resize")
- modules.scripts.scripts_img2img.prepare_ui()
+ scripts.scripts_img2img.prepare_ui()
for category in ordered_ui_categories():
if category == "sampler":
@@ -845,7 +811,7 @@ def create_ui(): elif category == "scripts":
with FormGroup(elem_id="img2img_script_container"):
- custom_inputs = modules.scripts.scripts_img2img.setup_ui()
+ custom_inputs = scripts.scripts_img2img.setup_ui()
elif category == "inpaint":
with FormGroup(elem_id="inpaint_controls", visible=False) as inpaint_controls:
@@ -876,34 +842,22 @@ def create_ui(): outputs=[inpaint_controls, mask_alpha],
)
else:
- modules.scripts.scripts_img2img.setup_ui_for_section(category)
+ scripts.scripts_img2img.setup_ui_for_section(category)
img2img_gallery, generation_info, html_info, html_log = create_output_panel("img2img", opts.outdir_img2img_samples)
connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False)
connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True)
- img2img_prompt_img.change(
- fn=modules.images.image_data,
- inputs=[
- img2img_prompt_img
- ],
- outputs=[
- img2img_prompt,
- img2img_prompt_img
- ],
- show_progress=False,
- )
-
img2img_args = dict(
fn=wrap_gradio_gpu_call(modules.img2img.img2img, extra_outputs=[None, '', '']),
_js="submit_img2img",
inputs=[
dummy_component,
dummy_component,
- img2img_prompt,
- img2img_negative_prompt,
- img2img_prompt_styles,
+ toprow.prompt,
+ toprow.negative_prompt,
+ toprow.ui_styles.dropdown,
init_img,
sketch,
init_img_with_mask,
@@ -962,11 +916,11 @@ def create_ui(): inpaint_color_sketch,
init_img_inpaint,
],
- outputs=[img2img_prompt, dummy_component],
+ outputs=[toprow.prompt, dummy_component],
)
- img2img_prompt.submit(**img2img_args)
- submit.click(**img2img_args)
+ toprow.prompt.submit(**img2img_args)
+ toprow.submit.click(**img2img_args)
res_switch_btn.click(fn=None, _js="function(){switchWidthHeight('img2img')}", inputs=None, outputs=None, show_progress=False)
@@ -978,7 +932,7 @@ def create_ui(): show_progress=False,
)
- restore_progress_button.click(
+ toprow.restore_progress_button.click(
fn=progress.restore_progress,
_js="restoreProgressImg2img",
inputs=[dummy_component],
@@ -991,46 +945,24 @@ def create_ui(): show_progress=False,
)
- img2img_interrogate.click(
+ toprow.button_interrogate.click(
fn=lambda *args: process_interrogate(interrogate, *args),
**interrogate_args,
)
- img2img_deepbooru.click(
+ toprow.button_deepbooru.click(
fn=lambda *args: process_interrogate(interrogate_deepbooru, *args),
**interrogate_args,
)
- prompts = [(txt2img_prompt, txt2img_negative_prompt), (img2img_prompt, img2img_negative_prompt)]
- style_dropdowns = [txt2img_prompt_styles, img2img_prompt_styles]
- style_js_funcs = ["update_txt2img_tokens", "update_img2img_tokens"]
-
- for button, (prompt, negative_prompt) in zip([txt2img_save_style, img2img_save_style], prompts):
- button.click(
- fn=add_style,
- _js="ask_for_style_name",
- # Have to pass empty dummy component here, because the JavaScript and Python function have to accept
- # the same number of parameters, but we only know the style-name after the JavaScript prompt
- inputs=[dummy_component, prompt, negative_prompt],
- outputs=[txt2img_prompt_styles, img2img_prompt_styles],
- )
-
- for button, (prompt, negative_prompt), styles, js_func in zip([txt2img_prompt_style_apply, img2img_prompt_style_apply], prompts, style_dropdowns, style_js_funcs):
- button.click(
- fn=apply_styles,
- _js=js_func,
- inputs=[prompt, negative_prompt, styles],
- outputs=[prompt, negative_prompt, styles],
- )
-
- token_button.click(fn=update_token_counter, inputs=[img2img_prompt, steps], outputs=[token_counter])
- negative_token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[img2img_negative_prompt, steps], outputs=[negative_token_counter])
+ toprow.token_button.click(fn=update_token_counter, inputs=[toprow.prompt, steps], outputs=[toprow.token_counter])
+ toprow.negative_token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[toprow.negative_prompt, steps], outputs=[toprow.negative_token_counter])
ui_extra_networks.setup_ui(extra_networks_ui_img2img, img2img_gallery)
img2img_paste_fields = [
- (img2img_prompt, "Prompt"),
- (img2img_negative_prompt, "Negative prompt"),
+ (toprow.prompt, "Prompt"),
+ (toprow.negative_prompt, "Negative prompt"),
(steps, "Steps"),
(sampler_index, "Sampler"),
(restore_faces, "Face restoration"),
@@ -1044,24 +976,24 @@ def create_ui(): (subseed_strength, "Variation seed strength"),
(seed_resize_from_w, "Seed resize from-1"),
(seed_resize_from_h, "Seed resize from-2"),
- (img2img_prompt_styles, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update()),
+ (toprow.ui_styles.dropdown, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update()),
(denoising_strength, "Denoising strength"),
(mask_blur, "Mask blur"),
- *modules.scripts.scripts_img2img.infotext_fields
+ *scripts.scripts_img2img.infotext_fields
]
parameters_copypaste.add_paste_fields("img2img", init_img, img2img_paste_fields, override_settings)
parameters_copypaste.add_paste_fields("inpaint", init_img_with_mask, img2img_paste_fields, override_settings)
parameters_copypaste.register_paste_params_button(parameters_copypaste.ParamBinding(
- paste_button=img2img_paste, tabname="img2img", source_text_component=img2img_prompt, source_image_component=None,
+ paste_button=toprow.paste, tabname="img2img", source_text_component=toprow.prompt, source_image_component=None,
))
- modules.scripts.scripts_current = None
+ scripts.scripts_current = None
with gr.Blocks(analytics_enabled=False) as extras_interface:
ui_postprocessing.create_ui()
with gr.Blocks(analytics_enabled=False) as pnginfo_interface:
- with gr.Row().style(equal_height=False):
+ with gr.Row(equal_height=False):
with gr.Column(variant='panel'):
image = gr.Image(elem_id="pnginfo_image", label="Source", source="upload", interactive=True, type="pil")
@@ -1083,64 +1015,13 @@ def create_ui(): outputs=[html, generation_info, html2],
)
- def update_interp_description(value):
- interp_description_css = "<p style='margin-bottom: 2.5em'>{}</p>"
- interp_descriptions = {
- "No interpolation": interp_description_css.format("No interpolation will be used. Requires one model; A. Allows for format conversion and VAE baking."),
- "Weighted sum": interp_description_css.format("A weighted sum will be used for interpolation. Requires two models; A and B. The result is calculated as A * (1 - M) + B * M"),
- "Add difference": interp_description_css.format("The difference between the last two models will be added to the first. Requires three models; A, B and C. The result is calculated as A + (B - C) * M")
- }
- return interp_descriptions[value]
-
- with gr.Blocks(analytics_enabled=False) as modelmerger_interface:
- with gr.Row().style(equal_height=False):
- with gr.Column(variant='compact'):
- interp_description = gr.HTML(value=update_interp_description("Weighted sum"), elem_id="modelmerger_interp_description")
-
- with FormRow(elem_id="modelmerger_models"):
- primary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_primary_model_name", label="Primary model (A)")
- create_refresh_button(primary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_A")
-
- secondary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_secondary_model_name", label="Secondary model (B)")
- create_refresh_button(secondary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_B")
-
- tertiary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_tertiary_model_name", label="Tertiary model (C)")
- create_refresh_button(tertiary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_C")
-
- custom_name = gr.Textbox(label="Custom Name (Optional)", elem_id="modelmerger_custom_name")
- interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Multiplier (M) - set to 0 to get model A', value=0.3, elem_id="modelmerger_interp_amount")
- interp_method = gr.Radio(choices=["No interpolation", "Weighted sum", "Add difference"], value="Weighted sum", label="Interpolation Method", elem_id="modelmerger_interp_method")
- interp_method.change(fn=update_interp_description, inputs=[interp_method], outputs=[interp_description])
-
- with FormRow():
- checkpoint_format = gr.Radio(choices=["ckpt", "safetensors"], value="safetensors", label="Checkpoint format", elem_id="modelmerger_checkpoint_format")
- save_as_half = gr.Checkbox(value=False, label="Save as float16", elem_id="modelmerger_save_as_half")
- save_metadata = gr.Checkbox(value=True, label="Save metadata (.safetensors only)", elem_id="modelmerger_save_metadata")
-
- with FormRow():
- with gr.Column():
- config_source = gr.Radio(choices=["A, B or C", "B", "C", "Don't"], value="A, B or C", label="Copy config from", type="index", elem_id="modelmerger_config_method")
-
- with gr.Column():
- with FormRow():
- bake_in_vae = gr.Dropdown(choices=["None"] + list(sd_vae.vae_dict), value="None", label="Bake in VAE", elem_id="modelmerger_bake_in_vae")
- create_refresh_button(bake_in_vae, sd_vae.refresh_vae_list, lambda: {"choices": ["None"] + list(sd_vae.vae_dict)}, "modelmerger_refresh_bake_in_vae")
-
- with FormRow():
- discard_weights = gr.Textbox(value="", label="Discard weights with matching name", elem_id="modelmerger_discard_weights")
-
- with gr.Row():
- modelmerger_merge = gr.Button(elem_id="modelmerger_merge", value="Merge", variant='primary')
-
- with gr.Column(variant='compact', elem_id="modelmerger_results_container"):
- with gr.Group(elem_id="modelmerger_results_panel"):
- modelmerger_result = gr.HTML(elem_id="modelmerger_result", show_label=False)
+ modelmerger_ui = ui_checkpoint_merger.UiCheckpointMerger()
with gr.Blocks(analytics_enabled=False) as train_interface:
- with gr.Row().style(equal_height=False):
+ with gr.Row(equal_height=False):
gr.HTML(value="<p style='margin-bottom: 0.7em'>See <b><a href=\"https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Textual-Inversion\">wiki</a></b> for detailed explanation.</p>")
- with gr.Row(variant="compact").style(equal_height=False):
+ with gr.Row(variant="compact", equal_height=False):
with gr.Tabs(elem_id="train_tabs"):
with gr.Tab(label="Create embedding", id="create_embedding"):
@@ -1160,7 +1041,7 @@ def create_ui(): new_hypernetwork_name = gr.Textbox(label="Name", elem_id="train_new_hypernetwork_name")
new_hypernetwork_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "1024", "320", "640", "1280"], elem_id="train_new_hypernetwork_sizes")
new_hypernetwork_layer_structure = gr.Textbox("1, 2, 1", label="Enter hypernetwork layer structure", placeholder="1st and last digit must be 1. ex:'1, 2, 1'", elem_id="train_new_hypernetwork_layer_structure")
- new_hypernetwork_activation_func = gr.Dropdown(value="linear", label="Select activation function of hypernetwork. Recommended : Swish / Linear(none)", choices=modules.hypernetworks.ui.keys, elem_id="train_new_hypernetwork_activation_func")
+ new_hypernetwork_activation_func = gr.Dropdown(value="linear", label="Select activation function of hypernetwork. Recommended : Swish / Linear(none)", choices=hypernetworks_ui.keys, elem_id="train_new_hypernetwork_activation_func")
new_hypernetwork_initialization_option = gr.Dropdown(value = "Normal", label="Select Layer weights initialization. Recommended: Kaiming for relu-like, Xavier for sigmoid-like, Normal otherwise", choices=["Normal", "KaimingUniform", "KaimingNormal", "XavierUniform", "XavierNormal"], elem_id="train_new_hypernetwork_initialization_option")
new_hypernetwork_add_layer_norm = gr.Checkbox(label="Add layer normalization", elem_id="train_new_hypernetwork_add_layer_norm")
new_hypernetwork_use_dropout = gr.Checkbox(label="Use dropout", elem_id="train_new_hypernetwork_use_dropout")
@@ -1300,12 +1181,12 @@ def create_ui(): with gr.Column(elem_id='ti_gallery_container'):
ti_output = gr.Text(elem_id="ti_output", value="", show_label=False)
- gr.Gallery(label='Output', show_label=False, elem_id='ti_gallery').style(columns=4)
+ gr.Gallery(label='Output', show_label=False, elem_id='ti_gallery', columns=4)
gr.HTML(elem_id="ti_progress", value="")
ti_outcome = gr.HTML(elem_id="ti_error", value="")
create_embedding.click(
- fn=modules.textual_inversion.ui.create_embedding,
+ fn=textual_inversion_ui.create_embedding,
inputs=[
new_embedding_name,
initialization_text,
@@ -1320,7 +1201,7 @@ def create_ui(): )
create_hypernetwork.click(
- fn=modules.hypernetworks.ui.create_hypernetwork,
+ fn=hypernetworks_ui.create_hypernetwork,
inputs=[
new_hypernetwork_name,
new_hypernetwork_sizes,
@@ -1340,7 +1221,7 @@ def create_ui(): )
run_preprocess.click(
- fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.preprocess, extra_outputs=[gr.update()]),
+ fn=wrap_gradio_gpu_call(textual_inversion_ui.preprocess, extra_outputs=[gr.update()]),
_js="start_training_textual_inversion",
inputs=[
dummy_component,
@@ -1376,7 +1257,7 @@ def create_ui(): )
train_embedding.click(
- fn=wrap_gradio_gpu_call(modules.textual_inversion.ui.train_embedding, extra_outputs=[gr.update()]),
+ fn=wrap_gradio_gpu_call(textual_inversion_ui.train_embedding, extra_outputs=[gr.update()]),
_js="start_training_textual_inversion",
inputs=[
dummy_component,
@@ -1410,7 +1291,7 @@ def create_ui(): )
train_hypernetwork.click(
- fn=wrap_gradio_gpu_call(modules.hypernetworks.ui.train_hypernetwork, extra_outputs=[gr.update()]),
+ fn=wrap_gradio_gpu_call(hypernetworks_ui.train_hypernetwork, extra_outputs=[gr.update()]),
_js="start_training_textual_inversion",
inputs=[
dummy_component,
@@ -1464,7 +1345,7 @@ def create_ui(): (img2img_interface, "img2img", "img2img"),
(extras_interface, "Extras", "extras"),
(pnginfo_interface, "PNG Info", "pnginfo"),
- (modelmerger_interface, "Checkpoint Merger", "modelmerger"),
+ (modelmerger_ui.blocks, "Checkpoint Merger", "modelmerger"),
(train_interface, "Train", "train"),
]
@@ -1516,49 +1397,11 @@ def create_ui(): settings.text_settings.change(fn=update_image_cfg_scale_visibility, inputs=[], outputs=[image_cfg_scale])
demo.load(fn=update_image_cfg_scale_visibility, inputs=[], outputs=[image_cfg_scale])
- def modelmerger(*args):
- try:
- results = modules.extras.run_modelmerger(*args)
- except Exception as e:
- errors.report("Error loading/saving model file", exc_info=True)
- modules.sd_models.list_models() # to remove the potentially missing models from the list
- return [*[gr.Dropdown.update(choices=modules.sd_models.checkpoint_tiles()) for _ in range(4)], f"Error merging checkpoints: {e}"]
- return results
-
- modelmerger_merge.click(fn=lambda: '', inputs=[], outputs=[modelmerger_result])
- modelmerger_merge.click(
- fn=wrap_gradio_gpu_call(modelmerger, extra_outputs=lambda: [gr.update() for _ in range(4)]),
- _js='modelmerger',
- inputs=[
- dummy_component,
- primary_model_name,
- secondary_model_name,
- tertiary_model_name,
- interp_method,
- interp_amount,
- save_as_half,
- custom_name,
- checkpoint_format,
- config_source,
- bake_in_vae,
- discard_weights,
- save_metadata,
- ],
- outputs=[
- primary_model_name,
- secondary_model_name,
- tertiary_model_name,
- settings.component_dict['sd_model_checkpoint'],
- modelmerger_result,
- ]
- )
+ modelmerger_ui.setup_ui(dummy_component=dummy_component, sd_model_checkpoint_component=settings.component_dict['sd_model_checkpoint'])
loadsave.dump_defaults()
demo.ui_loadsave = loadsave
- # Required as a workaround for change() event not triggering when loading values from ui-config.json
- interp_description.value = update_interp_description(interp_method.value)
-
return demo
diff --git a/modules/ui_checkpoint_merger.py b/modules/ui_checkpoint_merger.py new file mode 100644 index 00000000..f9c5dd6b --- /dev/null +++ b/modules/ui_checkpoint_merger.py @@ -0,0 +1,124 @@ +
+import gradio as gr
+
+from modules import sd_models, sd_vae, errors, extras, call_queue
+from modules.ui_components import FormRow
+from modules.ui_common import create_refresh_button
+
+
+def update_interp_description(value):
+ interp_description_css = "<p style='margin-bottom: 2.5em'>{}</p>"
+ interp_descriptions = {
+ "No interpolation": interp_description_css.format("No interpolation will be used. Requires one model; A. Allows for format conversion and VAE baking."),
+ "Weighted sum": interp_description_css.format("A weighted sum will be used for interpolation. Requires two models; A and B. The result is calculated as A * (1 - M) + B * M"),
+ "Add difference": interp_description_css.format("The difference between the last two models will be added to the first. Requires three models; A, B and C. The result is calculated as A + (B - C) * M")
+ }
+ return interp_descriptions[value]
+
+
+def modelmerger(*args):
+ try:
+ results = extras.run_modelmerger(*args)
+ except Exception as e:
+ errors.report("Error loading/saving model file", exc_info=True)
+ sd_models.list_models() # to remove the potentially missing models from the list
+ return [*[gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)], f"Error merging checkpoints: {e}"]
+ return results
+
+
+class UiCheckpointMerger:
+ def __init__(self):
+ with gr.Blocks(analytics_enabled=False) as modelmerger_interface:
+ with gr.Row(equal_height=False):
+ with gr.Column(variant='compact'):
+ self.interp_description = gr.HTML(value=update_interp_description("Weighted sum"), elem_id="modelmerger_interp_description")
+
+ with FormRow(elem_id="modelmerger_models"):
+ self.primary_model_name = gr.Dropdown(sd_models.checkpoint_tiles(), elem_id="modelmerger_primary_model_name", label="Primary model (A)")
+ create_refresh_button(self.primary_model_name, sd_models.list_models, lambda: {"choices": sd_models.checkpoint_tiles()}, "refresh_checkpoint_A")
+
+ self.secondary_model_name = gr.Dropdown(sd_models.checkpoint_tiles(), elem_id="modelmerger_secondary_model_name", label="Secondary model (B)")
+ create_refresh_button(self.secondary_model_name, sd_models.list_models, lambda: {"choices": sd_models.checkpoint_tiles()}, "refresh_checkpoint_B")
+
+ self.tertiary_model_name = gr.Dropdown(sd_models.checkpoint_tiles(), elem_id="modelmerger_tertiary_model_name", label="Tertiary model (C)")
+ create_refresh_button(self.tertiary_model_name, sd_models.list_models, lambda: {"choices": sd_models.checkpoint_tiles()}, "refresh_checkpoint_C")
+
+ self.custom_name = gr.Textbox(label="Custom Name (Optional)", elem_id="modelmerger_custom_name")
+ self.interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Multiplier (M) - set to 0 to get model A', value=0.3, elem_id="modelmerger_interp_amount")
+ self.interp_method = gr.Radio(choices=["No interpolation", "Weighted sum", "Add difference"], value="Weighted sum", label="Interpolation Method", elem_id="modelmerger_interp_method")
+ self.interp_method.change(fn=update_interp_description, inputs=[self.interp_method], outputs=[self.interp_description])
+
+ with FormRow():
+ self.checkpoint_format = gr.Radio(choices=["ckpt", "safetensors"], value="safetensors", label="Checkpoint format", elem_id="modelmerger_checkpoint_format")
+ self.save_as_half = gr.Checkbox(value=False, label="Save as float16", elem_id="modelmerger_save_as_half")
+
+ with FormRow():
+ with gr.Column():
+ self.config_source = gr.Radio(choices=["A, B or C", "B", "C", "Don't"], value="A, B or C", label="Copy config from", type="index", elem_id="modelmerger_config_method")
+
+ with gr.Column():
+ with FormRow():
+ self.bake_in_vae = gr.Dropdown(choices=["None"] + list(sd_vae.vae_dict), value="None", label="Bake in VAE", elem_id="modelmerger_bake_in_vae")
+ create_refresh_button(self.bake_in_vae, sd_vae.refresh_vae_list, lambda: {"choices": ["None"] + list(sd_vae.vae_dict)}, "modelmerger_refresh_bake_in_vae")
+
+ with FormRow():
+ self.discard_weights = gr.Textbox(value="", label="Discard weights with matching name", elem_id="modelmerger_discard_weights")
+
+ with gr.Accordion("Metadata", open=False) as metadata_editor:
+ with FormRow():
+ self.save_metadata = gr.Checkbox(value=True, label="Save metadata", elem_id="modelmerger_save_metadata")
+ self.add_merge_recipe = gr.Checkbox(value=True, label="Add merge recipe metadata", elem_id="modelmerger_add_recipe")
+ self.copy_metadata_fields = gr.Checkbox(value=True, label="Copy metadata from merged models", elem_id="modelmerger_copy_metadata")
+
+ self.metadata_json = gr.TextArea('{}', label="Metadata in JSON format")
+ self.read_metadata = gr.Button("Read metadata from selected checkpoints")
+
+ with FormRow():
+ self.modelmerger_merge = gr.Button(elem_id="modelmerger_merge", value="Merge", variant='primary')
+
+ with gr.Column(variant='compact', elem_id="modelmerger_results_container"):
+ with gr.Group(elem_id="modelmerger_results_panel"):
+ self.modelmerger_result = gr.HTML(elem_id="modelmerger_result", show_label=False)
+
+ self.metadata_editor = metadata_editor
+ self.blocks = modelmerger_interface
+
+ def setup_ui(self, dummy_component, sd_model_checkpoint_component):
+ self.checkpoint_format.change(lambda fmt: gr.update(visible=fmt == 'safetensors'), inputs=[self.checkpoint_format], outputs=[self.metadata_editor], show_progress=False)
+
+ self.read_metadata.click(extras.read_metadata, inputs=[self.primary_model_name, self.secondary_model_name, self.tertiary_model_name], outputs=[self.metadata_json])
+
+ self.modelmerger_merge.click(fn=lambda: '', inputs=[], outputs=[self.modelmerger_result])
+ self.modelmerger_merge.click(
+ fn=call_queue.wrap_gradio_gpu_call(modelmerger, extra_outputs=lambda: [gr.update() for _ in range(4)]),
+ _js='modelmerger',
+ inputs=[
+ dummy_component,
+ self.primary_model_name,
+ self.secondary_model_name,
+ self.tertiary_model_name,
+ self.interp_method,
+ self.interp_amount,
+ self.save_as_half,
+ self.custom_name,
+ self.checkpoint_format,
+ self.config_source,
+ self.bake_in_vae,
+ self.discard_weights,
+ self.save_metadata,
+ self.add_merge_recipe,
+ self.copy_metadata_fields,
+ self.metadata_json,
+ ],
+ outputs=[
+ self.primary_model_name,
+ self.secondary_model_name,
+ self.tertiary_model_name,
+ sd_model_checkpoint_component,
+ self.modelmerger_result,
+ ]
+ )
+
+ # Required as a workaround for change() event not triggering when loading values from ui-config.json
+ self.interp_description.value = update_interp_description(self.interp_method.value)
+
diff --git a/modules/ui_common.py b/modules/ui_common.py index 11eb2a4b..eefe0c0e 100644 --- a/modules/ui_common.py +++ b/modules/ui_common.py @@ -134,7 +134,7 @@ Requested path was: {f} with gr.Column(variant='panel', elem_id=f"{tabname}_results"):
with gr.Group(elem_id=f"{tabname}_gallery_container"):
- result_gallery = gr.Gallery(label='Output', show_label=False, elem_id=f"{tabname}_gallery").style(columns=4)
+ result_gallery = gr.Gallery(label='Output', show_label=False, elem_id=f"{tabname}_gallery", columns=4)
generation_info = None
with gr.Column():
@@ -223,20 +223,44 @@ Requested path was: {f} def create_refresh_button(refresh_component, refresh_method, refreshed_args, elem_id):
+ refresh_components = refresh_component if isinstance(refresh_component, list) else [refresh_component]
+
+ label = None
+ for comp in refresh_components:
+ label = getattr(comp, 'label', None)
+ if label is not None:
+ break
+
def refresh():
refresh_method()
args = refreshed_args() if callable(refreshed_args) else refreshed_args
for k, v in args.items():
- setattr(refresh_component, k, v)
+ for comp in refresh_components:
+ setattr(comp, k, v)
- return gr.update(**(args or {}))
+ return [gr.update(**(args or {})) for _ in refresh_components]
- refresh_button = ToolButton(value=refresh_symbol, elem_id=elem_id)
+ refresh_button = ToolButton(value=refresh_symbol, elem_id=elem_id, tooltip=f"{label}: refresh" if label else "Refresh")
refresh_button.click(
fn=refresh,
inputs=[],
- outputs=[refresh_component]
+ outputs=[*refresh_components]
)
return refresh_button
+
+def setup_dialog(button_show, dialog, *, button_close=None):
+ """Sets up the UI so that the dialog (gr.Box) is invisible, and is only shown when buttons_show is clicked, in a fullscreen modal window."""
+
+ dialog.visible = False
+
+ button_show.click(
+ fn=lambda: gr.update(visible=True),
+ inputs=[],
+ outputs=[dialog],
+ ).then(fn=None, _js="function(){ popup(gradioApp().getElementById('" + dialog.elem_id + "')); }")
+
+ if button_close:
+ button_close.click(fn=None, _js="closePopup")
+
diff --git a/modules/ui_components.py b/modules/ui_components.py index 64451df7..8f8a7088 100644 --- a/modules/ui_components.py +++ b/modules/ui_components.py @@ -35,7 +35,7 @@ class FormColumn(FormComponent, gr.Column): class FormGroup(FormComponent, gr.Group):
- """Same as gr.Row but fits inside gradio forms"""
+ """Same as gr.Group but fits inside gradio forms"""
def get_block_name(self):
return "group"
diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py index f3e4fba7..15a8b0bf 100644 --- a/modules/ui_extensions.py +++ b/modules/ui_extensions.py @@ -164,7 +164,7 @@ def extension_table(): ext_status = ext.status
style = ""
- if shared.opts.disable_all_extensions == "extra" and not ext.is_builtin or shared.opts.disable_all_extensions == "all":
+ if shared.cmd_opts.disable_extra_extensions and not ext.is_builtin or shared.opts.disable_all_extensions == "extra" and not ext.is_builtin or shared.cmd_opts.disable_all_extensions or shared.opts.disable_all_extensions == "all":
style = STYLE_PRIMARY
version_link = ext.version
@@ -533,16 +533,20 @@ def create_ui(): apply = gr.Button(value=apply_label, variant="primary")
check = gr.Button(value="Check for updates")
extensions_disable_all = gr.Radio(label="Disable all extensions", choices=["none", "extra", "all"], value=shared.opts.disable_all_extensions, elem_id="extensions_disable_all")
- extensions_disabled_list = gr.Text(elem_id="extensions_disabled_list", visible=False).style(container=False)
- extensions_update_list = gr.Text(elem_id="extensions_update_list", visible=False).style(container=False)
+ extensions_disabled_list = gr.Text(elem_id="extensions_disabled_list", visible=False, container=False)
+ extensions_update_list = gr.Text(elem_id="extensions_update_list", visible=False, container=False)
html = ""
- if shared.opts.disable_all_extensions != "none":
- html = """
-<span style="color: var(--primary-400);">
- "Disable all extensions" was set, change it to "none" to load all extensions again
-</span>
- """
+
+ if shared.cmd_opts.disable_all_extensions or shared.cmd_opts.disable_extra_extensions or shared.opts.disable_all_extensions != "none":
+ if shared.cmd_opts.disable_all_extensions:
+ msg = '"--disable-all-extensions" was used, remove it to load all extensions again'
+ elif shared.opts.disable_all_extensions != "none":
+ msg = '"Disable all extensions" was set, change it to "none" to load all extensions again'
+ elif shared.cmd_opts.disable_extra_extensions:
+ msg = '"--disable-extra-extensions" was used, remove it to load all extensions again'
+ html = f'<span style="color: var(--primary-400);">{msg}</span>'
+
info = gr.HTML(html)
extensions_table = gr.HTML('Loading...')
ui.load(fn=extension_table, inputs=[], outputs=[extensions_table])
@@ -565,7 +569,7 @@ def create_ui(): with gr.Row():
refresh_available_extensions_button = gr.Button(value="Load from:", variant="primary")
extensions_index_url = os.environ.get('WEBUI_EXTENSIONS_INDEX', "https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui-extensions/master/index.json")
- available_extensions_index = gr.Text(value=extensions_index_url, label="Extension index URL").style(container=False)
+ available_extensions_index = gr.Text(value=extensions_index_url, label="Extension index URL", container=False)
extension_to_install = gr.Text(elem_id="extension_to_install", visible=False)
install_extension_button = gr.Button(elem_id="install_extension_button", visible=False)
@@ -574,7 +578,7 @@ def create_ui(): sort_column = gr.Radio(value="newest first", label="Order", choices=["newest first", "oldest first", "a-z", "z-a", "internal order",'update time', 'create time', "stars"], type="index")
with gr.Row():
- search_extensions_text = gr.Text(label="Search").style(container=False)
+ search_extensions_text = gr.Text(label="Search", container=False)
install_result = gr.HTML()
available_extensions_table = gr.HTML()
diff --git a/modules/ui_extra_networks.py b/modules/ui_extra_networks.py index 6c73998f..f2752f10 100644 --- a/modules/ui_extra_networks.py +++ b/modules/ui_extra_networks.py @@ -62,7 +62,8 @@ def get_single_card(page: str = "", tabname: str = "", name: str = ""): page = next(iter([x for x in extra_pages if x.name == page]), None)
try:
- item = page.create_item(name)
+ item = page.create_item(name, enable_filter=False)
+ page.items[name] = item
except Exception as e:
errors.display(e, "creating item for extra network")
item = page.items.get(name)
@@ -252,7 +253,7 @@ class ExtraNetworksPage: "prompt": item.get("prompt", None),
"tabname": quote_js(tabname),
"local_preview": quote_js(item["local_preview"]),
- "name": item["name"],
+ "name": html.escape(item["name"]),
"description": (item.get("description") or "" if shared.opts.extra_networks_card_show_desc else ""),
"card_clicked": onclick,
"save_card_preview": '"' + html.escape(f"""return saveCardPreview(event, {quote_js(tabname)}, {quote_js(item["local_preview"])})""") + '"',
diff --git a/modules/ui_extra_networks_checkpoints.py b/modules/ui_extra_networks_checkpoints.py index 76780cfd..891d8f2c 100644 --- a/modules/ui_extra_networks_checkpoints.py +++ b/modules/ui_extra_networks_checkpoints.py @@ -12,7 +12,7 @@ class ExtraNetworksPageCheckpoints(ui_extra_networks.ExtraNetworksPage): def refresh(self):
shared.refresh_checkpoints()
- def create_item(self, name, index=None):
+ def create_item(self, name, index=None, enable_filter=True):
checkpoint: sd_models.CheckpointInfo = sd_models.checkpoint_aliases.get(name)
path, ext = os.path.splitext(checkpoint.filename)
return {
@@ -23,6 +23,7 @@ class ExtraNetworksPageCheckpoints(ui_extra_networks.ExtraNetworksPage): "search_term": self.search_terms_from_path(checkpoint.filename) + " " + (checkpoint.sha256 or ""),
"onclick": '"' + html.escape(f"""return selectCheckpoint({quote_js(name)})""") + '"',
"local_preview": f"{path}.{shared.opts.samples_format}",
+ "metadata": checkpoint.metadata,
"sort_keys": {'default': index, **self.get_sort_keys(checkpoint.filename)},
}
diff --git a/modules/ui_extra_networks_hypernets.py b/modules/ui_extra_networks_hypernets.py index e53ccb42..514a4562 100644 --- a/modules/ui_extra_networks_hypernets.py +++ b/modules/ui_extra_networks_hypernets.py @@ -11,7 +11,7 @@ class ExtraNetworksPageHypernetworks(ui_extra_networks.ExtraNetworksPage): def refresh(self):
shared.reload_hypernetworks()
- def create_item(self, name, index=None):
+ def create_item(self, name, index=None, enable_filter=True):
full_path = shared.hypernetworks[name]
path, ext = os.path.splitext(full_path)
diff --git a/modules/ui_extra_networks_textual_inversion.py b/modules/ui_extra_networks_textual_inversion.py index d1794e50..73134698 100644 --- a/modules/ui_extra_networks_textual_inversion.py +++ b/modules/ui_extra_networks_textual_inversion.py @@ -12,7 +12,7 @@ class ExtraNetworksPageTextualInversion(ui_extra_networks.ExtraNetworksPage): def refresh(self):
sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True)
- def create_item(self, name, index=None):
+ def create_item(self, name, index=None, enable_filter=True):
embedding = sd_hijack.model_hijack.embedding_db.word_embeddings.get(name)
path, ext = os.path.splitext(embedding.filename)
diff --git a/modules/ui_extra_networks_user_metadata.py b/modules/ui_extra_networks_user_metadata.py index 01ff4e4b..1cb9eb6f 100644 --- a/modules/ui_extra_networks_user_metadata.py +++ b/modules/ui_extra_networks_user_metadata.py @@ -42,6 +42,9 @@ class UserMetadataEditor: return user_metadata
+ def create_extra_default_items_in_left_column(self):
+ pass
+
def create_default_editor_elems(self):
with gr.Row():
with gr.Column(scale=2):
@@ -49,6 +52,8 @@ class UserMetadataEditor: self.edit_description = gr.Textbox(label="Description", lines=4)
self.html_filedata = gr.HTML()
+ self.create_extra_default_items_in_left_column()
+
with gr.Column(scale=1, min_width=0):
self.html_preview = gr.HTML()
@@ -91,6 +96,7 @@ class UserMetadataEditor: stats = os.stat(filename)
params = [
+ ('Filename: ', os.path.basename(filename)),
('File size: ', sysinfo.pretty_bytes(stats.st_size)),
('Modified: ', datetime.datetime.fromtimestamp(stats.st_mtime).strftime('%Y-%m-%d %H:%M')),
]
@@ -111,7 +117,7 @@ class UserMetadataEditor: table = '<table class="file-metadata">' + "".join(f"<tr><th>{name}</th><td>{value}</td></tr>" for name, value in params) + '</table>'
- return html.escape(name), user_metadata.get('description', ''), table, self.get_card_html(name), user_metadata.get('notes', ''),
+ return html.escape(name), user_metadata.get('description', ''), table, self.get_card_html(name), user_metadata.get('notes', '')
def write_user_metadata(self, name, metadata):
item = self.page.items.get(name, {})
diff --git a/modules/ui_postprocessing.py b/modules/ui_postprocessing.py index c7dc1154..802e1ce7 100644 --- a/modules/ui_postprocessing.py +++ b/modules/ui_postprocessing.py @@ -6,7 +6,7 @@ import modules.generation_parameters_copypaste as parameters_copypaste def create_ui():
tab_index = gr.State(value=0)
- with gr.Row().style(equal_height=False, variant='compact'):
+ with gr.Row(equal_height=False, variant='compact'):
with gr.Column(variant='compact'):
with gr.Tabs(elem_id="mode_extras"):
with gr.TabItem('Single Image', id="single_image", elem_id="extras_single_tab") as tab_single:
diff --git a/modules/ui_prompt_styles.py b/modules/ui_prompt_styles.py new file mode 100644 index 00000000..85eb3a64 --- /dev/null +++ b/modules/ui_prompt_styles.py @@ -0,0 +1,110 @@ +import gradio as gr
+
+from modules import shared, ui_common, ui_components, styles
+
+styles_edit_symbol = '\U0001f58c\uFE0F' # 🖌️
+styles_materialize_symbol = '\U0001f4cb' # 📋
+
+
+def select_style(name):
+ style = shared.prompt_styles.styles.get(name)
+ existing = style is not None
+ empty = not name
+
+ prompt = style.prompt if style else gr.update()
+ negative_prompt = style.negative_prompt if style else gr.update()
+
+ return prompt, negative_prompt, gr.update(visible=existing), gr.update(visible=not empty)
+
+
+def save_style(name, prompt, negative_prompt):
+ if not name:
+ return gr.update(visible=False)
+
+ style = styles.PromptStyle(name, prompt, negative_prompt)
+ shared.prompt_styles.styles[style.name] = style
+ shared.prompt_styles.save_styles(shared.styles_filename)
+
+ return gr.update(visible=True)
+
+
+def delete_style(name):
+ if name == "":
+ return
+
+ shared.prompt_styles.styles.pop(name, None)
+ shared.prompt_styles.save_styles(shared.styles_filename)
+
+ return '', '', ''
+
+
+def materialize_styles(prompt, negative_prompt, styles):
+ prompt = shared.prompt_styles.apply_styles_to_prompt(prompt, styles)
+ negative_prompt = shared.prompt_styles.apply_negative_styles_to_prompt(negative_prompt, styles)
+
+ return [gr.Textbox.update(value=prompt), gr.Textbox.update(value=negative_prompt), gr.Dropdown.update(value=[])]
+
+
+def refresh_styles():
+ return gr.update(choices=list(shared.prompt_styles.styles)), gr.update(choices=list(shared.prompt_styles.styles))
+
+
+class UiPromptStyles:
+ def __init__(self, tabname, main_ui_prompt, main_ui_negative_prompt):
+ self.tabname = tabname
+
+ with gr.Row(elem_id=f"{tabname}_styles_row"):
+ self.dropdown = gr.Dropdown(label="Styles", show_label=False, elem_id=f"{tabname}_styles", choices=list(shared.prompt_styles.styles), value=[], multiselect=True, tooltip="Styles")
+ edit_button = ui_components.ToolButton(value=styles_edit_symbol, elem_id=f"{tabname}_styles_edit_button", tooltip="Edit styles")
+
+ with gr.Box(elem_id=f"{tabname}_styles_dialog", elem_classes="popup-dialog") as styles_dialog:
+ with gr.Row():
+ self.selection = gr.Dropdown(label="Styles", elem_id=f"{tabname}_styles_edit_select", choices=list(shared.prompt_styles.styles), value=[], allow_custom_value=True, info="Styles allow you to add custom text to prompt. Use the {prompt} token in style text, and it will be replaced with user's prompt when applying style. Otherwise, style's text will be added to the end of the prompt.")
+ ui_common.create_refresh_button([self.dropdown, self.selection], shared.prompt_styles.reload, lambda: {"choices": list(shared.prompt_styles.styles)}, f"refresh_{tabname}_styles")
+ self.materialize = ui_components.ToolButton(value=styles_materialize_symbol, elem_id=f"{tabname}_style_apply", tooltip="Apply all selected styles from the style selction dropdown in main UI to the prompt.")
+
+ with gr.Row():
+ self.prompt = gr.Textbox(label="Prompt", show_label=True, elem_id=f"{tabname}_edit_style_prompt", lines=3)
+
+ with gr.Row():
+ self.neg_prompt = gr.Textbox(label="Negative prompt", show_label=True, elem_id=f"{tabname}_edit_style_neg_prompt", lines=3)
+
+ with gr.Row():
+ self.save = gr.Button('Save', variant='primary', elem_id=f'{tabname}_edit_style_save', visible=False)
+ self.delete = gr.Button('Delete', variant='primary', elem_id=f'{tabname}_edit_style_delete', visible=False)
+ self.close = gr.Button('Close', variant='secondary', elem_id=f'{tabname}_edit_style_close')
+
+ self.selection.change(
+ fn=select_style,
+ inputs=[self.selection],
+ outputs=[self.prompt, self.neg_prompt, self.delete, self.save],
+ show_progress=False,
+ )
+
+ self.save.click(
+ fn=save_style,
+ inputs=[self.selection, self.prompt, self.neg_prompt],
+ outputs=[self.delete],
+ show_progress=False,
+ ).then(refresh_styles, outputs=[self.dropdown, self.selection], show_progress=False)
+
+ self.delete.click(
+ fn=delete_style,
+ _js='function(name){ if(name == "") return ""; return confirm("Delete style " + name + "?") ? name : ""; }',
+ inputs=[self.selection],
+ outputs=[self.selection, self.prompt, self.neg_prompt],
+ show_progress=False,
+ ).then(refresh_styles, outputs=[self.dropdown, self.selection], show_progress=False)
+
+ self.materialize.click(
+ fn=materialize_styles,
+ inputs=[main_ui_prompt, main_ui_negative_prompt, self.dropdown],
+ outputs=[main_ui_prompt, main_ui_negative_prompt, self.dropdown],
+ show_progress=False,
+ ).then(fn=None, _js="function(){update_"+tabname+"_tokens(); closePopup();}", show_progress=False)
+
+ ui_common.setup_dialog(button_show=edit_button, dialog=styles_dialog, button_close=self.close)
+
+
+
+
diff --git a/requirements.txt b/requirements.txt index 0a2fd236..9a47d6d0 100644 --- a/requirements.txt +++ b/requirements.txt @@ -7,7 +7,7 @@ blendmodes clean-fid
einops
gfpgan
-gradio==3.36.1
+gradio==3.39.0
inflection
jsonmerge
kornia
diff --git a/requirements_versions.txt b/requirements_versions.txt index 09c2d292..dec45df3 100644 --- a/requirements_versions.txt +++ b/requirements_versions.txt @@ -7,8 +7,8 @@ clean-fid==0.1.35 einops==0.4.1
fastapi==0.94.0
gfpgan==1.3.8
-gradio==3.36.1
-httpcore<=0.15
+gradio==3.39.0
+httpcore==0.15
inflection==0.5.1
jsonmerge==1.8.0
kornia==0.6.7
@@ -17,7 +17,7 @@ numpy==1.23.5 omegaconf==2.2.3
open-clip-torch==2.20.0
piexif==1.1.3
-psutil~=5.9.5
+psutil==5.9.5
pytorch_lightning==1.9.4
realesrgan==0.3.0
resize-right==0.0.2
@@ -29,4 +29,3 @@ torch torchdiffeq==0.2.3
torchsde==0.2.5
transformers==4.30.2
-diffusers==0.18.2
diff --git a/scripts/xyz_grid.py b/scripts/xyz_grid.py index 7821cc65..d37b428f 100644 --- a/scripts/xyz_grid.py +++ b/scripts/xyz_grid.py @@ -3,6 +3,7 @@ from copy import copy from itertools import permutations, chain
import random
import csv
+import os.path
from io import StringIO
from PIL import Image
import numpy as np
@@ -10,7 +11,7 @@ import numpy as np import modules.scripts as scripts
import gradio as gr
-from modules import images, sd_samplers, processing, sd_models, sd_vae, sd_samplers_kdiffusion
+from modules import images, sd_samplers, processing, sd_models, sd_vae, sd_samplers_kdiffusion, errors
from modules.processing import process_images, Processed, StableDiffusionProcessingTxt2Img
from modules.shared import opts, state
import modules.shared as shared
@@ -66,14 +67,6 @@ def apply_order(p, x, xs): p.prompt = prompt_tmp + p.prompt
-def apply_sampler(p, x, xs):
- sampler_name = sd_samplers.samplers_map.get(x.lower(), None)
- if sampler_name is None:
- raise RuntimeError(f"Unknown sampler: {x}")
-
- p.sampler_name = sampler_name
-
-
def confirm_samplers(p, xs):
for x in xs:
if x.lower() not in sd_samplers.samplers_map:
@@ -144,11 +137,20 @@ def apply_face_restore(p, opt, x): p.restore_faces = is_active
-def apply_override(field):
+def apply_override(field, boolean: bool = False):
def fun(p, x, xs):
+ if boolean:
+ x = True if x.lower() == "true" else False
p.override_settings[field] = x
return fun
+
+def boolean_choice(reverse: bool = False):
+ def choice():
+ return ["False", "True"] if reverse else ["True", "False"]
+ return choice
+
+
def format_value_add_label(p, opt, x):
if type(x) == float:
x = round(x, 8)
@@ -173,6 +175,8 @@ def do_nothing(p, x, xs): def format_nothing(p, opt, x):
return ""
+def format_remove_path(p, opt, x):
+ return os.path.basename(x)
def str_permutations(x):
"""dummy function for specifying it in AxisOption's type when you want to get a list of permutations"""
@@ -212,9 +216,10 @@ axis_options = [ AxisOptionImg2Img("Image CFG Scale", float, apply_field("image_cfg_scale")),
AxisOption("Prompt S/R", str, apply_prompt, format_value=format_value),
AxisOption("Prompt order", str_permutations, apply_order, format_value=format_value_join_list),
- AxisOptionTxt2Img("Sampler", str, apply_sampler, format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers]),
- AxisOptionImg2Img("Sampler", str, apply_sampler, format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers_for_img2img]),
- AxisOption("Checkpoint name", str, apply_checkpoint, format_value=format_value, confirm=confirm_checkpoints, cost=1.0, choices=lambda: sorted(sd_models.checkpoints_list, key=str.casefold)),
+ AxisOptionTxt2Img("Sampler", str, apply_field("sampler_name"), format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers]),
+ AxisOptionTxt2Img("Hires sampler", str, apply_field("hr_sampler_name"), confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers_for_img2img]),
+ AxisOptionImg2Img("Sampler", str, apply_field("sampler_name"), format_value=format_value, confirm=confirm_samplers, choices=lambda: [x.name for x in sd_samplers.samplers_for_img2img]),
+ AxisOption("Checkpoint name", str, apply_checkpoint, format_value=format_remove_path, confirm=confirm_checkpoints, cost=1.0, choices=lambda: sorted(sd_models.checkpoints_list, key=str.casefold)),
AxisOption("Negative Guidance minimum sigma", float, apply_field("s_min_uncond")),
AxisOption("Sigma Churn", float, apply_field("s_churn")),
AxisOption("Sigma min", float, apply_field("s_tmin")),
@@ -235,6 +240,7 @@ axis_options = [ AxisOption("Face restore", str, apply_face_restore, format_value=format_value),
AxisOption("Token merging ratio", float, apply_override('token_merging_ratio')),
AxisOption("Token merging ratio high-res", float, apply_override('token_merging_ratio_hr')),
+ AxisOption("Always discard next-to-last sigma", str, apply_override('always_discard_next_to_last_sigma', boolean=True), choices=boolean_choice(reverse=True)),
]
@@ -638,7 +644,12 @@ class Script(scripts.Script): y_opt.apply(pc, y, ys)
z_opt.apply(pc, z, zs)
- res = process_images(pc)
+ try:
+ res = process_images(pc)
+ except Exception as e:
+ errors.display(e, "generating image for xyz plot")
+
+ res = Processed(p, [], p.seed, "")
# Sets subgrid infotexts
subgrid_index = 1 + iz
@@ -8,6 +8,7 @@ --checkbox-label-gap: 0.25em 0.1em;
--section-header-text-size: 12pt;
--block-background-fill: transparent;
+
}
.block.padded:not(.gradio-accordion) {
@@ -42,7 +43,8 @@ div.form{ .block.gradio-radio,
.block.gradio-checkboxgroup,
.block.gradio-number,
-.block.gradio-colorpicker
+.block.gradio-colorpicker,
+div.gradio-group
{
border-width: 0 !important;
box-shadow: none !important;
@@ -133,6 +135,11 @@ a{ cursor: pointer;
}
+div.styler{
+ border: none;
+ background: var(--background-fill-primary);
+}
+
/* general styled components */
@@ -164,7 +171,7 @@ a{ .checkboxes-row > div{
flex: 0;
white-space: nowrap;
- min-width: auto;
+ min-width: auto !important;
}
button.custom-button{
@@ -388,6 +395,7 @@ div#extras_scale_to_tab div.form{ #quicksettings > div, #quicksettings > fieldset{
max-width: 24em;
min-width: 24em;
+ width: 24em;
padding: 0;
border: none;
box-shadow: none;
@@ -423,15 +431,16 @@ div#extras_scale_to_tab div.form{ }
table.popup-table{
- background: white;
+ background: var(--body-background-fill);
+ color: var(--body-text-color);
border-collapse: collapse;
margin: 1em;
- border: 4px solid white;
+ border: 4px solid var(--body-background-fill);
}
table.popup-table td{
padding: 0.4em;
- border: 1px solid #ccc;
+ border: 1px solid rgba(128, 128, 128, 0.5);
max-width: 36em;
}
@@ -841,7 +850,7 @@ footer { .extra-network-cards .card .card-button {
text-shadow: 2px 2px 3px black;
- padding: 0.25em;
+ padding: 0.25em 0.1em;
font-size: 200%;
width: 1.5em;
}
@@ -957,6 +966,10 @@ div.block.gradio-box.edit-user-metadata { text-align: left;
}
+.edit-user-metadata .file-metadata th, .edit-user-metadata .file-metadata td{
+ padding: 0.3em 1em;
+}
+
.edit-user-metadata .wrap.translucent{
background: var(--body-background-fill);
}
@@ -967,3 +980,16 @@ div.block.gradio-box.edit-user-metadata { .edit-user-metadata-buttons{
margin-top: 1.5em;
}
+
+
+
+
+div.block.gradio-box.popup-dialog, .popup-dialog {
+ width: 56em;
+ background: var(--body-background-fill);
+ padding: 2em !important;
+}
+
+div.block.gradio-box.popup-dialog > div:last-child, .popup-dialog > div:last-child{
+ margin-top: 1em;
+}
@@ -14,7 +14,6 @@ from typing import Iterable from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from fastapi.middleware.gzip import GZipMiddleware
-from packaging import version
import logging
@@ -31,24 +30,26 @@ if log_level: logging.getLogger("torch.distributed.nn").setLevel(logging.ERROR) # sshh...
logging.getLogger("xformers").addFilter(lambda record: 'A matching Triton is not available' not in record.getMessage())
-from modules import paths, timer, import_hook, errors, devices # noqa: F401
-
+from modules import timer
startup_timer = timer.startup_timer
+startup_timer.record("launcher")
import torch
import pytorch_lightning # noqa: F401 # pytorch_lightning should be imported after torch, but it re-enables warnings on import so import once to disable them
warnings.filterwarnings(action="ignore", category=DeprecationWarning, module="pytorch_lightning")
warnings.filterwarnings(action="ignore", category=UserWarning, module="torchvision")
-
-
startup_timer.record("import torch")
import gradio # noqa: F401
startup_timer.record("import gradio")
+from modules import paths, timer, import_hook, errors, devices # noqa: F401
+startup_timer.record("setup paths")
+
import ldm.modules.encoders.modules # noqa: F401
startup_timer.record("import ldm")
+
from modules import extra_networks
from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, queue_lock # noqa: F401
@@ -57,10 +58,15 @@ if ".dev" in torch.__version__ or "+git" in torch.__version__: torch.__long_version__ = torch.__version__
torch.__version__ = re.search(r'[\d.]+[\d]', torch.__version__).group(0)
-from modules import shared, sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks, config_states
+from modules import shared
+
+if not shared.cmd_opts.skip_version_check:
+ errors.check_versions()
+
import modules.codeformer_model as codeformer
-import modules.face_restoration
import modules.gfpgan_model as gfpgan
+from modules import sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks, config_states
+import modules.face_restoration
import modules.img2img
import modules.lowvram
@@ -129,37 +135,6 @@ def fix_asyncio_event_loop_policy(): asyncio.set_event_loop_policy(AnyThreadEventLoopPolicy())
-def check_versions():
- if shared.cmd_opts.skip_version_check:
- return
-
- expected_torch_version = "2.0.0"
-
- if version.parse(torch.__version__) < version.parse(expected_torch_version):
- errors.print_error_explanation(f"""
-You are running torch {torch.__version__}.
-The program is tested to work with torch {expected_torch_version}.
-To reinstall the desired version, run with commandline flag --reinstall-torch.
-Beware that this will cause a lot of large files to be downloaded, as well as
-there are reports of issues with training tab on the latest version.
-
-Use --skip-version-check commandline argument to disable this check.
- """.strip())
-
- expected_xformers_version = "0.0.20"
- if shared.xformers_available:
- import xformers
-
- if version.parse(xformers.__version__) < version.parse(expected_xformers_version):
- errors.print_error_explanation(f"""
-You are running xformers {xformers.__version__}.
-The program is tested to work with xformers {expected_xformers_version}.
-To reinstall the desired version, run with commandline flag --reinstall-xformers.
-
-Use --skip-version-check commandline argument to disable this check.
- """.strip())
-
-
def restore_config_state_file():
config_state_file = shared.opts.restore_config_state_file
if config_state_file == "":
@@ -247,7 +222,6 @@ def initialize(): fix_asyncio_event_loop_policy()
validate_tls_options()
configure_sigint_handler()
- check_versions()
modelloader.cleanup_models()
configure_opts_onchange()
@@ -319,9 +293,9 @@ def initialize_rest(*, reload_script_modules=False): if modules.sd_hijack.current_optimizer is None:
modules.sd_hijack.apply_optimizations()
- Thread(target=load_model).start()
+ devices.first_time_calculation()
- Thread(target=devices.first_time_calculation).start()
+ Thread(target=load_model).start()
shared.reload_hypernetworks()
startup_timer.record("reload hypernetworks")
@@ -373,7 +347,7 @@ def api_only(): api.launch(
server_name="0.0.0.0" if cmd_opts.listen else "127.0.0.1",
port=cmd_opts.port if cmd_opts.port else 7861,
- root_path = f"/{cmd_opts.subpath}"
+ root_path=f"/{cmd_opts.subpath}" if cmd_opts.subpath else ""
)
@@ -406,7 +380,7 @@ def webui(): ssl_verify=cmd_opts.disable_tls_verify,
debug=cmd_opts.gradio_debug,
auth=gradio_auth_creds,
- inbrowser=cmd_opts.autolaunch and os.getenv('SD_WEBUI_RESTARTING ') != '1',
+ inbrowser=cmd_opts.autolaunch and os.getenv('SD_WEBUI_RESTARTING') != '1',
prevent_thread_lock=True,
allowed_paths=cmd_opts.gradio_allowed_path,
app_kwargs={
@@ -4,8 +4,15 @@ # change the variables in webui-user.sh instead # ################################################# + +use_venv=1 +if [[ $venv_dir == "-" ]]; then + use_venv=0 +fi + SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd ) + # If run from macOS, load defaults from webui-macos-env.sh if [[ "$OSTYPE" == "darwin"* ]]; then if [[ -f "$SCRIPT_DIR"/webui-macos-env.sh ]] @@ -47,7 +54,7 @@ then fi # python3 venv without trailing slash (defaults to ${install_dir}/${clone_dir}/venv) -if [[ -z "${venv_dir}" ]] +if [[ -z "${venv_dir}" ]] && [[ $use_venv -eq 1 ]] then venv_dir="venv" fi @@ -164,7 +171,7 @@ do fi done -if ! "${python_cmd}" -c "import venv" &>/dev/null +if [[ $use_venv -eq 1 ]] && ! "${python_cmd}" -c "import venv" &>/dev/null then printf "\n%s\n" "${delimiter}" printf "\e[1m\e[31mERROR: python3-venv is not installed, aborting...\e[0m" @@ -184,7 +191,7 @@ else cd "${clone_dir}"/ || { printf "\e[1m\e[31mERROR: Can't cd to %s/%s/, aborting...\e[0m" "${install_dir}" "${clone_dir}"; exit 1; } fi -if [[ -z "${VIRTUAL_ENV}" ]]; +if [[ $use_venv -eq 1 ]] && [[ -z "${VIRTUAL_ENV}" ]]; then printf "\n%s\n" "${delimiter}" printf "Create and activate python venv" @@ -207,7 +214,7 @@ then fi else printf "\n%s\n" "${delimiter}" - printf "python venv already activate: ${VIRTUAL_ENV}" + printf "python venv already activate or run without venv: ${VIRTUAL_ENV}" printf "\n%s\n" "${delimiter}" fi |