diff options
28 files changed, 288 insertions, 80 deletions
@@ -104,8 +104,7 @@ Alternatively, use online services (like Google Colab): 1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH"
2. Install [git](https://git-scm.com/download/win).
3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.
-4. Place stable diffusion checkpoint (`model.ckpt`) in the `models/Stable-diffusion` directory (see [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) for where to get it).
-5. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
+4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
### Automatic Installation on Linux
1. Install the dependencies:
@@ -121,7 +120,7 @@ sudo pacman -S wget git python3 ```bash
bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh)
```
-
+3. Run `webui.sh`.
### Installation on Apple Silicon
Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).
diff --git a/javascript/hints.js b/javascript/hints.js index 9aa82f24..f1199009 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -8,8 +8,8 @@ titles = { "DDIM": "Denoising Diffusion Implicit Models - best at inpainting", "DPM adaptive": "Ignores step count - uses a number of steps determined by the CFG and resolution", - "Batch count": "How many batches of images to create", - "Batch size": "How many image to create in a single batch", + "Batch count": "How many batches of images to create (has no impact on generation performance or VRAM usage)", + "Batch size": "How many image to create in a single batch (increases generation performance at cost of higher VRAM usage)", "CFG Scale": "Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results", "Seed": "A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result", "\u{1f3b2}\ufe0f": "Set seed to -1, which will cause a new random number to be used every time", @@ -242,7 +242,7 @@ def prepare_environment(): sys.argv += shlex.split(commandline_args)
- parser = argparse.ArgumentParser()
+ parser = argparse.ArgumentParser(add_help=False)
parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default='config.json')
args, _ = parser.parse_known_args(sys.argv)
diff --git a/modules/api/api.py b/modules/api/api.py index eb7b1da5..5a9ac5f1 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -498,7 +498,7 @@ class Api: if not apply_optimizations: sd_hijack.undo_optimizations() try: - hypernetwork, filename = train_hypernetwork(*args) + hypernetwork, filename = train_hypernetwork(**args) except Exception as e: error = e finally: diff --git a/modules/esrgan_model_arch.py b/modules/esrgan_model_arch.py index bc9ceb2a..1b52b0f5 100644 --- a/modules/esrgan_model_arch.py +++ b/modules/esrgan_model_arch.py @@ -1,5 +1,6 @@ # this file is adapted from https://github.com/victorca25/iNNfer
+from collections import OrderedDict
import math
import functools
import torch
diff --git a/modules/extensions.py b/modules/extensions.py index 5e12b1aa..3eef9eaf 100644 --- a/modules/extensions.py +++ b/modules/extensions.py @@ -2,6 +2,7 @@ import os import sys
import traceback
+import time
import git
from modules import paths, shared
@@ -25,6 +26,7 @@ class Extension: self.status = ''
self.can_update = False
self.is_builtin = is_builtin
+ self.version = ''
repo = None
try:
@@ -40,6 +42,10 @@ class Extension: try:
self.remote = next(repo.remote().urls, None)
self.status = 'unknown'
+ head = repo.head.commit
+ ts = time.asctime(time.gmtime(repo.head.commit.committed_date))
+ self.version = f'{head.hexsha[:8]} ({ts})'
+
except Exception:
self.remote = None
diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index fc9e17aa..89dc23bf 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -74,8 +74,8 @@ def image_from_url_text(filedata): return image
-def add_paste_fields(tabname, init_img, fields):
- paste_fields[tabname] = {"init_img": init_img, "fields": fields}
+def add_paste_fields(tabname, init_img, fields, override_settings_component=None):
+ paste_fields[tabname] = {"init_img": init_img, "fields": fields, "override_settings_component": override_settings_component}
# backwards compatibility for existing extensions
import modules.ui
@@ -110,6 +110,7 @@ def connect_paste_params_buttons(): for binding in registered_param_bindings:
destination_image_component = paste_fields[binding.tabname]["init_img"]
fields = paste_fields[binding.tabname]["fields"]
+ override_settings_component = binding.override_settings_component or paste_fields[binding.tabname]["override_settings_component"]
destination_width_component = next(iter([field for field, name in fields if name == "Size-1"] if fields else []), None)
destination_height_component = next(iter([field for field, name in fields if name == "Size-2"] if fields else []), None)
@@ -130,7 +131,7 @@ def connect_paste_params_buttons(): )
if binding.source_text_component is not None and fields is not None:
- connect_paste(binding.paste_button, fields, binding.source_text_component, binding.override_settings_component, binding.tabname)
+ connect_paste(binding.paste_button, fields, binding.source_text_component, override_settings_component, binding.tabname)
if binding.source_tabname is not None and fields is not None:
paste_field_names = ['Prompt', 'Negative prompt', 'Steps', 'Face restoration'] + (["Seed"] if shared.opts.send_seed else [])
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 825a93b2..f6ef42d5 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -380,8 +380,8 @@ def apply_single_hypernetwork(hypernetwork, context_k, context_v, layer=None): layer.hyper_k = hypernetwork_layers[0]
layer.hyper_v = hypernetwork_layers[1]
- context_k = hypernetwork_layers[0](context_k)
- context_v = hypernetwork_layers[1](context_v)
+ context_k = devices.cond_cast_unet(hypernetwork_layers[0](devices.cond_cast_float(context_k)))
+ context_v = devices.cond_cast_unet(hypernetwork_layers[1](devices.cond_cast_float(context_v)))
return context_k, context_v
@@ -496,7 +496,7 @@ def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, shared.reload_hypernetworks()
-def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_hypernetwork_every, template_filename, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_hypernetwork_every, template_filename, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
# images allows training previews to have infotext. Importing it at the top causes a circular import problem.
from modules import images
@@ -554,7 +554,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi pin_memory = shared.opts.pin_memory
- ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=hypernetwork_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, include_cond=True, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method, varsize=varsize)
+ ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=hypernetwork_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, include_cond=True, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method, varsize=varsize, use_weight=use_weight)
if shared.opts.save_training_settings_to_txt:
saved_params = dict(
@@ -640,13 +640,19 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi with devices.autocast():
x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
+ if use_weight:
+ w = batch.weight.to(devices.device, non_blocking=pin_memory)
if tag_drop_out != 0 or shuffle_tags:
shared.sd_model.cond_stage_model.to(devices.device)
c = shared.sd_model.cond_stage_model(batch.cond_text).to(devices.device, non_blocking=pin_memory)
shared.sd_model.cond_stage_model.to(devices.cpu)
else:
c = stack_conds(batch.cond).to(devices.device, non_blocking=pin_memory)
- loss = shared.sd_model(x, c)[0] / gradient_step
+ if use_weight:
+ loss = shared.sd_model.weighted_forward(x, c, w)[0] / gradient_step
+ del w
+ else:
+ loss = shared.sd_model.forward(x, c)[0] / gradient_step
del x
del c
diff --git a/modules/images.py b/modules/images.py index c2ca8849..38404de3 100644 --- a/modules/images.py +++ b/modules/images.py @@ -18,7 +18,7 @@ import string import json
import hashlib
-from modules import sd_samplers, shared, script_callbacks
+from modules import sd_samplers, shared, script_callbacks, errors
from modules.shared import opts, cmd_opts
LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS)
@@ -553,6 +553,8 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i elif extension.lower() in (".jpg", ".jpeg", ".webp"):
if image_to_save.mode == 'RGBA':
image_to_save = image_to_save.convert("RGB")
+ elif image_to_save.mode == 'I;16':
+ image_to_save = image_to_save.point(lambda p: p * 0.0038910505836576).convert("RGB" if extension.lower() == ".webp" else "L")
image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality)
@@ -575,17 +577,19 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i image.already_saved_as = fullfn
- target_side_length = 4000
- oversize = image.width > target_side_length or image.height > target_side_length
- if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > 4 * 1024 * 1024):
+ oversize = image.width > opts.target_side_length or image.height > opts.target_side_length
+ if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > opts.img_downscale_threshold * 1024 * 1024):
ratio = image.width / image.height
if oversize and ratio > 1:
- image = image.resize((target_side_length, image.height * target_side_length // image.width), LANCZOS)
+ image = image.resize((opts.target_side_length, image.height * opts.target_side_length // image.width), LANCZOS)
elif oversize:
- image = image.resize((image.width * target_side_length // image.height, target_side_length), LANCZOS)
+ image = image.resize((image.width * opts.target_side_length // image.height, opts.target_side_length), LANCZOS)
- _atomically_save_image(image, fullfn_without_extension, ".jpg")
+ try:
+ _atomically_save_image(image, fullfn_without_extension, ".jpg")
+ except Exception as e:
+ errors.display(e, "saving image as downscaled JPG")
if opts.save_txt and info is not None:
txt_fullfn = f"{fullfn_without_extension}.txt"
diff --git a/modules/img2img.py b/modules/img2img.py index bcc158dc..c973b770 100644 --- a/modules/img2img.py +++ b/modules/img2img.py @@ -73,6 +73,8 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args): if not save_normally:
os.makedirs(output_dir, exist_ok=True)
+ if processed_image.mode == 'RGBA':
+ processed_image = processed_image.convert("RGB")
processed_image.save(os.path.join(output_dir, filename))
diff --git a/modules/processing.py b/modules/processing.py index e1b53ac0..2009d3bf 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -543,8 +543,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if os.path.exists(cmd_opts.embeddings_dir) and not p.do_not_reload_embeddings:
model_hijack.embedding_db.load_textual_inversion_embeddings()
- _, extra_network_data = extra_networks.parse_prompts(p.all_prompts[0:1])
-
if p.scripts is not None:
p.scripts.process(p)
@@ -582,13 +580,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if shared.opts.live_previews_enable and opts.show_progress_type == "Approx NN":
sd_vae_approx.model()
- if not p.disable_extra_networks:
- extra_networks.activate(p, extra_network_data)
-
- with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file:
- processed = Processed(p, [], p.seed, "")
- file.write(processed.infotext(p, 0))
-
if state.job_count == -1:
state.job_count = p.n_iter
@@ -609,11 +600,24 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if len(prompts) == 0:
break
- prompts, _ = extra_networks.parse_prompts(prompts)
+ prompts, extra_network_data = extra_networks.parse_prompts(prompts)
+
+ if not p.disable_extra_networks:
+ with devices.autocast():
+ extra_networks.activate(p, extra_network_data)
if p.scripts is not None:
p.scripts.process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds)
+ # params.txt should be saved after scripts.process_batch, since the
+ # infotext could be modified by that callback
+ # Example: a wildcard processed by process_batch sets an extra model
+ # strength, which is saved as "Model Strength: 1.0" in the infotext
+ if n == 0:
+ with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file:
+ processed = Processed(p, [], p.seed, "")
+ file.write(processed.infotext(p, 0))
+
uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, cached_uc)
c = get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, prompts, p.steps, cached_c)
diff --git a/modules/script_callbacks.py b/modules/script_callbacks.py index 4bb45ec7..edd0e2a7 100644 --- a/modules/script_callbacks.py +++ b/modules/script_callbacks.py @@ -46,6 +46,18 @@ class CFGDenoiserParams: """Total number of sampling steps planned"""
+class CFGDenoisedParams:
+ def __init__(self, x, sampling_step, total_sampling_steps):
+ self.x = x
+ """Latent image representation in the process of being denoised"""
+
+ self.sampling_step = sampling_step
+ """Current Sampling step number"""
+
+ self.total_sampling_steps = total_sampling_steps
+ """Total number of sampling steps planned"""
+
+
class UiTrainTabParams:
def __init__(self, txt2img_preview_params):
self.txt2img_preview_params = txt2img_preview_params
@@ -68,6 +80,7 @@ callback_map = dict( callbacks_before_image_saved=[],
callbacks_image_saved=[],
callbacks_cfg_denoiser=[],
+ callbacks_cfg_denoised=[],
callbacks_before_component=[],
callbacks_after_component=[],
callbacks_image_grid=[],
@@ -150,6 +163,14 @@ def cfg_denoiser_callback(params: CFGDenoiserParams): report_exception(c, 'cfg_denoiser_callback')
+def cfg_denoised_callback(params: CFGDenoisedParams):
+ for c in callback_map['callbacks_cfg_denoised']:
+ try:
+ c.callback(params)
+ except Exception:
+ report_exception(c, 'cfg_denoised_callback')
+
+
def before_component_callback(component, **kwargs):
for c in callback_map['callbacks_before_component']:
try:
@@ -283,6 +304,14 @@ def on_cfg_denoiser(callback): add_callback(callback_map['callbacks_cfg_denoiser'], callback)
+def on_cfg_denoised(callback):
+ """register a function to be called in the kdiffussion cfg_denoiser method after building the inner model inputs.
+ The callback is called with one argument:
+ - params: CFGDenoisedParams - parameters to be passed to the inner model and sampling state details.
+ """
+ add_callback(callback_map['callbacks_cfg_denoised'], callback)
+
+
def on_before_component(callback):
"""register a function to be called before a component is created.
The callback is called with arguments:
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 8fdc5990..79476783 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -1,5 +1,6 @@ import torch
from torch.nn.functional import silu
+from types import MethodType
import modules.textual_inversion.textual_inversion
from modules import devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint
@@ -76,6 +77,54 @@ def fix_checkpoint(): pass
+def weighted_loss(sd_model, pred, target, mean=True):
+ #Calculate the weight normally, but ignore the mean
+ loss = sd_model._old_get_loss(pred, target, mean=False)
+
+ #Check if we have weights available
+ weight = getattr(sd_model, '_custom_loss_weight', None)
+ if weight is not None:
+ loss *= weight
+
+ #Return the loss, as mean if specified
+ return loss.mean() if mean else loss
+
+def weighted_forward(sd_model, x, c, w, *args, **kwargs):
+ try:
+ #Temporarily append weights to a place accessible during loss calc
+ sd_model._custom_loss_weight = w
+
+ #Replace 'get_loss' with a weight-aware one. Otherwise we need to reimplement 'forward' completely
+ #Keep 'get_loss', but don't overwrite the previous old_get_loss if it's already set
+ if not hasattr(sd_model, '_old_get_loss'):
+ sd_model._old_get_loss = sd_model.get_loss
+ sd_model.get_loss = MethodType(weighted_loss, sd_model)
+
+ #Run the standard forward function, but with the patched 'get_loss'
+ return sd_model.forward(x, c, *args, **kwargs)
+ finally:
+ try:
+ #Delete temporary weights if appended
+ del sd_model._custom_loss_weight
+ except AttributeError as e:
+ pass
+
+ #If we have an old loss function, reset the loss function to the original one
+ if hasattr(sd_model, '_old_get_loss'):
+ sd_model.get_loss = sd_model._old_get_loss
+ del sd_model._old_get_loss
+
+def apply_weighted_forward(sd_model):
+ #Add new function 'weighted_forward' that can be called to calc weighted loss
+ sd_model.weighted_forward = MethodType(weighted_forward, sd_model)
+
+def undo_weighted_forward(sd_model):
+ try:
+ del sd_model.weighted_forward
+ except AttributeError as e:
+ pass
+
+
class StableDiffusionModelHijack:
fixes = None
comments = []
@@ -104,6 +153,10 @@ class StableDiffusionModelHijack: m.cond_stage_model.model.token_embedding = EmbeddingsWithFixes(m.cond_stage_model.model.token_embedding, self)
m.cond_stage_model = sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
+ apply_weighted_forward(m)
+ if m.cond_stage_key == "edit":
+ sd_hijack_unet.hijack_ddpm_edit()
+
self.optimization_method = apply_optimizations()
self.clip = m.cond_stage_model
@@ -132,6 +185,7 @@ class StableDiffusionModelHijack: m.cond_stage_model = m.cond_stage_model.wrapped
undo_optimizations()
+ undo_weighted_forward(m)
self.apply_circular(False)
self.layers = None
diff --git a/modules/sd_hijack_inpainting.py b/modules/sd_hijack_inpainting.py index 478cd499..55a2ce4d 100644 --- a/modules/sd_hijack_inpainting.py +++ b/modules/sd_hijack_inpainting.py @@ -11,6 +11,7 @@ import ldm.models.diffusion.plms from ldm.models.diffusion.ddpm import LatentDiffusion from ldm.models.diffusion.plms import PLMSSampler from ldm.models.diffusion.ddim import DDIMSampler, noise_like +from ldm.models.diffusion.sampling_util import norm_thresholding @torch.no_grad() diff --git a/modules/sd_hijack_unet.py b/modules/sd_hijack_unet.py index 45cf2b18..843ab66c 100644 --- a/modules/sd_hijack_unet.py +++ b/modules/sd_hijack_unet.py @@ -44,6 +44,7 @@ def apply_model(orig_func, self, x_noisy, t, cond, **kwargs): with devices.autocast():
return orig_func(self, x_noisy.to(devices.dtype_unet), t.to(devices.dtype_unet), cond, **kwargs).float()
+
class GELUHijack(torch.nn.GELU, torch.nn.Module):
def __init__(self, *args, **kwargs):
torch.nn.GELU.__init__(self, *args, **kwargs)
@@ -53,6 +54,16 @@ class GELUHijack(torch.nn.GELU, torch.nn.Module): else:
return torch.nn.GELU.forward(self, x)
+
+ddpm_edit_hijack = None
+def hijack_ddpm_edit():
+ global ddpm_edit_hijack
+ if not ddpm_edit_hijack:
+ CondFunc('modules.models.diffusion.ddpm_edit.LatentDiffusion.decode_first_stage', first_stage_sub, first_stage_cond)
+ CondFunc('modules.models.diffusion.ddpm_edit.LatentDiffusion.encode_first_stage', first_stage_sub, first_stage_cond)
+ ddpm_edit_hijack = CondFunc('modules.models.diffusion.ddpm_edit.LatentDiffusion.apply_model', apply_model, unet_needs_upcast)
+
+
unet_needs_upcast = lambda *args, **kwargs: devices.unet_needs_upcast
CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.apply_model', apply_model, unet_needs_upcast)
CondFunc('ldm.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 d847d358..127e9663 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -105,7 +105,7 @@ def checkpoint_tiles(): def list_models():
checkpoints_list.clear()
checkpoint_alisases.clear()
- model_list = modelloader.load_models(model_path=model_path, command_path=shared.cmd_opts.ckpt_dir, ext_filter=[".ckpt", ".safetensors"], ext_blacklist=[".vae.safetensors"])
+ model_list = modelloader.load_models(model_path=model_path, model_url="https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors", command_path=shared.cmd_opts.ckpt_dir, ext_filter=[".ckpt", ".safetensors"], download_name="v1-5-pruned-emaonly.safetensors", ext_blacklist=[".vae.ckpt", ".vae.safetensors"])
cmd_ckpt = shared.cmd_opts.ckpt
if os.path.exists(cmd_ckpt):
diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index f076fc55..528f513f 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -8,6 +8,7 @@ from modules import prompt_parser, devices, sd_samplers_common from modules.shared import opts, state
import modules.shared as shared
from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback
+from modules.script_callbacks import CFGDenoisedParams, cfg_denoised_callback
samplers_k_diffusion = [
('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {}),
@@ -136,6 +137,9 @@ class CFGDenoiser(torch.nn.Module): x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond={"c_crossattn": [uncond], "c_concat": [image_cond_in[-uncond.shape[0]:]]})
+ denoised_params = CFGDenoisedParams(x_out, state.sampling_step, state.sampling_steps)
+ cfg_denoised_callback(denoised_params)
+
devices.test_for_nans(x_out, "unet")
if opts.live_preview_content == "Prompt":
@@ -269,6 +273,16 @@ class KDiffusionSampler: return sigmas
+ def create_noise_sampler(self, x, sigmas, p):
+ """For DPM++ SDE: manually create noise sampler to enable deterministic results across different batch sizes"""
+ if shared.opts.no_dpmpp_sde_batch_determinism:
+ return None
+
+ from k_diffusion.sampling import BrownianTreeNoiseSampler
+ sigma_min, sigma_max = sigmas[sigmas > 0].min(), sigmas.max()
+ current_iter_seeds = p.all_seeds[p.iteration * p.batch_size:(p.iteration + 1) * p.batch_size]
+ return BrownianTreeNoiseSampler(x, sigma_min, sigma_max, seed=current_iter_seeds)
+
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
steps, t_enc = sd_samplers_common.setup_img2img_steps(p, steps)
@@ -278,18 +292,24 @@ class KDiffusionSampler: xi = x + noise * sigma_sched[0]
extra_params_kwargs = self.initialize(p)
- if 'sigma_min' in inspect.signature(self.func).parameters:
+ parameters = inspect.signature(self.func).parameters
+
+ if 'sigma_min' in parameters:
## last sigma is zero which isn't allowed by DPM Fast & Adaptive so taking value before last
extra_params_kwargs['sigma_min'] = sigma_sched[-2]
- if 'sigma_max' in inspect.signature(self.func).parameters:
+ if 'sigma_max' in parameters:
extra_params_kwargs['sigma_max'] = sigma_sched[0]
- if 'n' in inspect.signature(self.func).parameters:
+ if 'n' in parameters:
extra_params_kwargs['n'] = len(sigma_sched) - 1
- if 'sigma_sched' in inspect.signature(self.func).parameters:
+ if 'sigma_sched' in parameters:
extra_params_kwargs['sigma_sched'] = sigma_sched
- if 'sigmas' in inspect.signature(self.func).parameters:
+ if 'sigmas' in parameters:
extra_params_kwargs['sigmas'] = sigma_sched
+ if self.funcname == 'sample_dpmpp_sde':
+ noise_sampler = self.create_noise_sampler(x, sigmas, p)
+ extra_params_kwargs['noise_sampler'] = noise_sampler
+
self.model_wrap_cfg.init_latent = x
self.last_latent = x
extra_args={
@@ -303,7 +323,7 @@ class KDiffusionSampler: return samples
- def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning = None):
+ def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
steps = steps or p.steps
sigmas = self.get_sigmas(p, steps)
@@ -311,14 +331,20 @@ class KDiffusionSampler: x = x * sigmas[0]
extra_params_kwargs = self.initialize(p)
- if 'sigma_min' in inspect.signature(self.func).parameters:
+ parameters = inspect.signature(self.func).parameters
+
+ if 'sigma_min' in parameters:
extra_params_kwargs['sigma_min'] = self.model_wrap.sigmas[0].item()
extra_params_kwargs['sigma_max'] = self.model_wrap.sigmas[-1].item()
- if 'n' in inspect.signature(self.func).parameters:
+ if 'n' in parameters:
extra_params_kwargs['n'] = steps
else:
extra_params_kwargs['sigmas'] = sigmas
+ if self.funcname == 'sample_dpmpp_sde':
+ noise_sampler = self.create_noise_sampler(x, sigmas, p)
+ extra_params_kwargs['noise_sampler'] = noise_sampler
+
self.last_latent = x
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
'cond': conditioning,
diff --git a/modules/shared.py b/modules/shared.py index 79fbf724..2c2edfbd 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -81,6 +81,7 @@ parser.add_argument("--freeze-settings", action='store_true', help="disable edit parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default=os.path.join(data_path, 'config.json'))
parser.add_argument("--gradio-debug", action='store_true', help="launch gradio with --debug option")
parser.add_argument("--gradio-auth", type=str, help='set gradio authentication like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
+parser.add_argument("--gradio-auth-path", type=str, help='set gradio authentication file path ex. "/path/to/auth/file" same auth format as --gradio-auth', default=None)
parser.add_argument("--gradio-img2img-tool", type=str, help='does not do anything')
parser.add_argument("--gradio-inpaint-tool", type=str, help="does not do anything")
parser.add_argument("--opt-channelslast", action='store_true', help="change memory type for stable diffusion to channels last")
@@ -325,7 +326,9 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "save_images_before_highres_fix": OptionInfo(False, "Save a copy of image before applying highres fix."),
"save_images_before_color_correction": OptionInfo(False, "Save a copy of image before applying color correction to img2img results"),
"jpeg_quality": OptionInfo(80, "Quality for saved jpeg images", gr.Slider, {"minimum": 1, "maximum": 100, "step": 1}),
- "export_for_4chan": OptionInfo(True, "If PNG image is larger than 4MB or any dimension is larger than 4000, downscale and save copy as JPG"),
+ "export_for_4chan": OptionInfo(True, "If the saved image file size is above the limit, or its either width or height are above the limit, save a downscaled copy as JPG"),
+ "img_downscale_threshold": OptionInfo(4.0, "File size limit for the above option, MB", gr.Number),
+ "target_side_length": OptionInfo(4000, "Width/height limit for the above option, in pixels", gr.Number),
"use_original_name_batch": OptionInfo(True, "Use original name for output filename during batch process in extras tab"),
"use_upscaler_name_as_suffix": OptionInfo(False, "Use upscaler name as filename suffix in the extras tab"),
@@ -364,7 +367,7 @@ options_templates.update(options_section(('upscaling', "Upscaling"), { }))
options_templates.update(options_section(('face-restoration', "Face restoration"), {
- "face_restoration_model": OptionInfo(None, "Face restoration model", gr.Radio, lambda: {"choices": [x.name() for x in face_restorers]}),
+ "face_restoration_model": OptionInfo("CodeFormer", "Face restoration model", gr.Radio, lambda: {"choices": [x.name() for x in face_restorers]}),
"code_former_weight": OptionInfo(0.5, "CodeFormer weight parameter; 0 = maximum effect; 1 = minimum effect", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}),
"face_restoration_unload": OptionInfo(False, "Move face restoration model from VRAM into RAM after processing"),
}))
@@ -414,6 +417,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { options_templates.update(options_section(('compatibility', "Compatibility"), {
"use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
"use_old_karras_scheduler_sigmas": OptionInfo(False, "Use old karras scheduler sigmas (0.1 to 10)."),
+ "no_dpmpp_sde_batch_determinism": OptionInfo(False, "Do not make DPM++ SDE deterministic across different batch sizes."),
"use_old_hires_fix_width_height": OptionInfo(False, "For hires fix, use width/height sliders to set final resolution rather than first pass (disables Upscale by, Resize width/height to)."),
}))
diff --git a/modules/shared_items.py b/modules/shared_items.py index 8b5ec96d..e792a134 100644 --- a/modules/shared_items.py +++ b/modules/shared_items.py @@ -20,4 +20,4 @@ def sd_vae_items(): def refresh_vae_list():
import modules.sd_vae
- return modules.sd_vae.refresh_vae_list
+ modules.sd_vae.refresh_vae_list()
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index d31963d4..af9fbcf2 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -19,9 +19,10 @@ re_numbers_at_start = re.compile(r"^[-\d]+\s*") class DatasetEntry:
- def __init__(self, filename=None, filename_text=None, latent_dist=None, latent_sample=None, cond=None, cond_text=None, pixel_values=None):
+ def __init__(self, filename=None, filename_text=None, latent_dist=None, latent_sample=None, cond=None, cond_text=None, pixel_values=None, weight=None):
self.filename = filename
self.filename_text = filename_text
+ self.weight = weight
self.latent_dist = latent_dist
self.latent_sample = latent_sample
self.cond = cond
@@ -30,7 +31,7 @@ class DatasetEntry: class PersonalizedBase(Dataset):
- def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once', varsize=False):
+ def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once', varsize=False, use_weight=False):
re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex) > 0 else None
self.placeholder_token = placeholder_token
@@ -56,10 +57,16 @@ class PersonalizedBase(Dataset): print("Preparing dataset...")
for path in tqdm.tqdm(self.image_paths):
+ alpha_channel = None
if shared.state.interrupted:
raise Exception("interrupted")
try:
- image = Image.open(path).convert('RGB')
+ image = Image.open(path)
+ #Currently does not work for single color transparency
+ #We would need to read image.info['transparency'] for that
+ if use_weight and 'A' in image.getbands():
+ alpha_channel = image.getchannel('A')
+ image = image.convert('RGB')
if not varsize:
image = image.resize((width, height), PIL.Image.BICUBIC)
except Exception:
@@ -87,17 +94,35 @@ class PersonalizedBase(Dataset): with devices.autocast():
latent_dist = model.encode_first_stage(torchdata.unsqueeze(dim=0))
- if latent_sampling_method == "once" or (latent_sampling_method == "deterministic" and not isinstance(latent_dist, DiagonalGaussianDistribution)):
- latent_sample = model.get_first_stage_encoding(latent_dist).squeeze().to(devices.cpu)
- latent_sampling_method = "once"
- entry = DatasetEntry(filename=path, filename_text=filename_text, latent_sample=latent_sample)
- elif latent_sampling_method == "deterministic":
- # Works only for DiagonalGaussianDistribution
- latent_dist.std = 0
- latent_sample = model.get_first_stage_encoding(latent_dist).squeeze().to(devices.cpu)
- entry = DatasetEntry(filename=path, filename_text=filename_text, latent_sample=latent_sample)
- elif latent_sampling_method == "random":
- entry = DatasetEntry(filename=path, filename_text=filename_text, latent_dist=latent_dist)
+ #Perform latent sampling, even for random sampling.
+ #We need the sample dimensions for the weights
+ if latent_sampling_method == "deterministic":
+ if isinstance(latent_dist, DiagonalGaussianDistribution):
+ # Works only for DiagonalGaussianDistribution
+ latent_dist.std = 0
+ else:
+ latent_sampling_method = "once"
+ latent_sample = model.get_first_stage_encoding(latent_dist).squeeze().to(devices.cpu)
+
+ if use_weight and alpha_channel is not None:
+ channels, *latent_size = latent_sample.shape
+ weight_img = alpha_channel.resize(latent_size)
+ npweight = np.array(weight_img).astype(np.float32)
+ #Repeat for every channel in the latent sample
+ weight = torch.tensor([npweight] * channels).reshape([channels] + latent_size)
+ #Normalize the weight to a minimum of 0 and a mean of 1, that way the loss will be comparable to default.
+ weight -= weight.min()
+ weight /= weight.mean()
+ elif use_weight:
+ #If an image does not have a alpha channel, add a ones weight map anyway so we can stack it later
+ weight = torch.ones(latent_sample.shape)
+ else:
+ weight = None
+
+ if latent_sampling_method == "random":
+ entry = DatasetEntry(filename=path, filename_text=filename_text, latent_dist=latent_dist, weight=weight)
+ else:
+ entry = DatasetEntry(filename=path, filename_text=filename_text, latent_sample=latent_sample, weight=weight)
if not (self.tag_drop_out != 0 or self.shuffle_tags):
entry.cond_text = self.create_text(filename_text)
@@ -110,6 +135,7 @@ class PersonalizedBase(Dataset): del torchdata
del latent_dist
del latent_sample
+ del weight
self.length = len(self.dataset)
self.groups = list(groups.values())
@@ -195,6 +221,10 @@ class BatchLoader: self.cond_text = [entry.cond_text for entry in data]
self.cond = [entry.cond for entry in data]
self.latent_sample = torch.stack([entry.latent_sample for entry in data]).squeeze(1)
+ if all(entry.weight is not None for entry in data):
+ self.weight = torch.stack([entry.weight for entry in data]).squeeze(1)
+ else:
+ self.weight = None
#self.emb_index = [entry.emb_index for entry in data]
#print(self.latent_sample.device)
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index a1a406c2..c63c7d1d 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -351,7 +351,7 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat assert log_directory, "Log directory is empty"
-def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
save_embedding_every = save_embedding_every or 0
create_image_every = create_image_every or 0
template_file = textual_inversion_templates.get(template_filename, None)
@@ -410,7 +410,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st pin_memory = shared.opts.pin_memory
- ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method, varsize=varsize)
+ ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method, varsize=varsize, use_weight=use_weight)
if shared.opts.save_training_settings_to_txt:
save_settings_to_file(log_directory, {**dict(model_name=checkpoint.model_name, model_hash=checkpoint.shorthash, num_of_dataset_images=len(ds), num_vectors_per_token=len(embedding.vec)), **locals()})
@@ -480,6 +480,8 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st with devices.autocast():
x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
+ if use_weight:
+ w = batch.weight.to(devices.device, non_blocking=pin_memory)
c = shared.sd_model.cond_stage_model(batch.cond_text)
if is_training_inpainting_model:
@@ -490,7 +492,11 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st else:
cond = c
- loss = shared.sd_model(x, cond)[0] / gradient_step
+ if use_weight:
+ loss = shared.sd_model.weighted_forward(x, cond, w)[0] / gradient_step
+ del w
+ else:
+ loss = shared.sd_model.forward(x, cond)[0] / gradient_step
del x
_loss_step += loss.item()
diff --git a/modules/ui.py b/modules/ui.py index f5df1ffe..0516c643 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -631,9 +631,9 @@ def create_ui(): (hr_resize_y, "Hires resize-2"),
*modules.scripts.scripts_txt2img.infotext_fields
]
- parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_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, override_settings_component=override_settings,
+ paste_button=txt2img_paste, tabname="txt2img", source_text_component=txt2img_prompt, source_image_component=None,
))
txt2img_preview_params = [
@@ -963,10 +963,10 @@ def create_ui(): (mask_blur, "Mask blur"),
*modules.scripts.scripts_img2img.infotext_fields
]
- parameters_copypaste.add_paste_fields("img2img", init_img, img2img_paste_fields)
- parameters_copypaste.add_paste_fields("inpaint", init_img_with_mask, img2img_paste_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, override_settings_component=override_settings,
+ paste_button=img2img_paste, tabname="img2img", source_text_component=img2img_prompt, source_image_component=None,
))
modules.scripts.scripts_current = None
@@ -1191,6 +1191,8 @@ def create_ui(): create_image_every = gr.Number(label='Save an image to log directory every N steps, 0 to disable', value=500, precision=0, elem_id="train_create_image_every")
save_embedding_every = gr.Number(label='Save a copy of embedding to log directory every N steps, 0 to disable', value=500, precision=0, elem_id="train_save_embedding_every")
+ use_weight = gr.Checkbox(label="Use PNG alpha channel as loss weight", value=False, elem_id="use_weight")
+
save_image_with_stored_embedding = gr.Checkbox(label='Save images with embedding in PNG chunks', value=True, elem_id="train_save_image_with_stored_embedding")
preview_from_txt2img = gr.Checkbox(label='Read parameters (prompt, etc...) from txt2img tab when making previews', value=False, elem_id="train_preview_from_txt2img")
@@ -1304,6 +1306,7 @@ def create_ui(): shuffle_tags,
tag_drop_out,
latent_sampling_method,
+ use_weight,
create_image_every,
save_embedding_every,
template_file,
@@ -1337,6 +1340,7 @@ def create_ui(): shuffle_tags,
tag_drop_out,
latent_sampling_method,
+ use_weight,
create_image_every,
save_embedding_every,
template_file,
@@ -1782,7 +1786,7 @@ def versions_html(): return f"""
python: <span title="{sys.version}">{python_version}</span>
•
-torch: {torch.__version__}
+torch: {getattr(torch, '__long_version__',torch.__version__)}
•
xformers: {xformers_version}
•
diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py index 37d30e1f..bd4308ef 100644 --- a/modules/ui_extensions.py +++ b/modules/ui_extensions.py @@ -80,6 +80,7 @@ def extension_table(): <tr>
<th><abbr title="Use checkbox to enable the extension; it will be enabled or disabled when you click apply button">Extension</abbr></th>
<th>URL</th>
+ <th><abbr title="Extension version">Version</abbr></th>
<th><abbr title="Use checkbox to mark the extension for update; it will be updated when you click apply button">Update</abbr></th>
</tr>
</thead>
@@ -87,11 +88,7 @@ def extension_table(): """
for ext in extensions.extensions:
- remote = ""
- if ext.is_builtin:
- remote = "built-in"
- elif ext.remote:
- remote = f"""<a href="{html.escape(ext.remote or '')}" target="_blank">{html.escape("built-in" if ext.is_builtin else ext.remote or '')}</a>"""
+ remote = f"""<a href="{html.escape(ext.remote or '')}" target="_blank">{html.escape("built-in" if ext.is_builtin else ext.remote or '')}</a>"""
if ext.can_update:
ext_status = f"""<label><input class="gr-check-radio gr-checkbox" name="update_{html.escape(ext.name)}" checked="checked" type="checkbox">{html.escape(ext.status)}</label>"""
@@ -102,6 +99,7 @@ def extension_table(): <tr>
<td><label><input class="gr-check-radio gr-checkbox" name="enable_{html.escape(ext.name)}" type="checkbox" {'checked="checked"' if ext.enabled else ''}>{html.escape(ext.name)}</label></td>
<td>{remote}</td>
+ <td>{ext.version}</td>
<td{' class="extension_status"' if ext.remote is not None else ''}>{ext_status}</td>
</tr>
"""
diff --git a/modules/ui_extra_networks.py b/modules/ui_extra_networks.py index 90abec0a..71f1d81f 100644 --- a/modules/ui_extra_networks.py +++ b/modules/ui_extra_networks.py @@ -76,6 +76,10 @@ class ExtraNetworksPage: while subdir.startswith("/"):
subdir = subdir[1:]
+ is_empty = len(os.listdir(x)) == 0
+ if not is_empty and not subdir.endswith("/"):
+ subdir = subdir + "/"
+
subdirs[subdir] = 1
if subdirs:
@@ -94,11 +98,13 @@ class ExtraNetworksPage: dirs = "".join([f"<li>{x}</li>" for x in self.allowed_directories_for_previews()])
items_html = shared.html("extra-networks-no-cards.html").format(dirs=dirs)
+ self_name_id = self.name.replace(" ", "_")
+
res = f"""
-<div id='{tabname}_{self.name}_subdirs' class='extra-network-subdirs extra-network-subdirs-{view}'>
+<div id='{tabname}_{self_name_id}_subdirs' class='extra-network-subdirs extra-network-subdirs-{view}'>
{subdirs_html}
</div>
-<div id='{tabname}_{self.name}_cards' class='extra-network-{view}'>
+<div id='{tabname}_{self_name_id}_cards' class='extra-network-{view}'>
{items_html}
</div>
"""
diff --git a/requirements_versions.txt b/requirements_versions.txt index eaa08806..331d0fe8 100644 --- a/requirements_versions.txt +++ b/requirements_versions.txt @@ -27,3 +27,4 @@ GitPython==3.1.27 torchsde==0.2.5
safetensors==0.2.7
httpcore<=0.15
+fastapi==0.90.1
diff --git a/scripts/prompt_matrix.py b/scripts/prompt_matrix.py index 3ee3cbe4..b1c486d4 100644 --- a/scripts/prompt_matrix.py +++ b/scripts/prompt_matrix.py @@ -54,7 +54,7 @@ class Script(scripts.Script): prompt_type = gr.Radio(["positive", "negative"], label="Select prompt", elem_id=self.elem_id("prompt_type"), value="positive")
variations_delimiter = gr.Radio(["comma", "space"], label="Select joining char", elem_id=self.elem_id("variations_delimiter"), value="comma")
with gr.Column():
- margin_size = gr.Slider(label="Grid margins (px)", min=0, max=500, value=0, step=2, elem_id=self.elem_id("margin_size"))
+ margin_size = gr.Slider(label="Grid margins (px)", minimum=0, maximum=500, value=0, step=2, elem_id=self.elem_id("margin_size"))
return [put_at_start, different_seeds, prompt_type, variations_delimiter, margin_size]
@@ -99,8 +99,8 @@ class Script(scripts.Script): p.prompt_for_display = positive_prompt
processed = process_images(p)
- grid = images.image_grid(processed.images, p.batch_size, rows=1 << ((len(prompt_matrix_parts) - 1) // 2))
- grid = images.draw_prompt_matrix(grid, p.width, p.height, prompt_matrix_parts, margin_size)
+ grid = images.image_grid(processed.images, p.batch_size, rows=1 << ((len(prompt_matrix_parts) - 1) // 2))
+ grid = images.draw_prompt_matrix(grid, processed.images[0].width, processed.images[1].height, prompt_matrix_parts, margin_size)
processed.images.insert(0, grid)
processed.index_of_first_image = 1
processed.infotexts.insert(0, processed.infotexts[0])
diff --git a/scripts/xyz_grid.py b/scripts/xyz_grid.py index 5982cfba..4afcbbfd 100644 --- a/scripts/xyz_grid.py +++ b/scripts/xyz_grid.py @@ -25,6 +25,8 @@ from modules.ui_components import ToolButton fill_values_symbol = "\U0001f4d2" # 📒
+AxisInfo = namedtuple('AxisInfo', ['axis', 'values'])
+
def apply_field(field):
def fun(p, x, xs):
@@ -186,6 +188,7 @@ axis_options = [ AxisOption("Steps", int, apply_field("steps")),
AxisOptionTxt2Img("Hires steps", int, apply_field("hr_second_pass_steps")),
AxisOption("CFG Scale", float, apply_field("cfg_scale")),
+ 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]),
@@ -358,7 +361,7 @@ class Script(scripts.Script): include_lone_images = gr.Checkbox(label='Include Sub Images', value=False, elem_id=self.elem_id("include_lone_images"))
include_sub_grids = gr.Checkbox(label='Include Sub Grids', value=False, elem_id=self.elem_id("include_sub_grids"))
with gr.Column():
- margin_size = gr.Slider(label="Grid margins (px)", min=0, max=500, value=0, step=2, elem_id=self.elem_id("margin_size"))
+ margin_size = gr.Slider(label="Grid margins (px)", minimum=0, maximum=500, value=0, step=2, elem_id=self.elem_id("margin_size"))
with gr.Row(variant="compact", elem_id="swap_axes"):
swap_xy_axes_button = gr.Button(value="Swap X/Y axes", elem_id="xy_grid_swap_axes_button")
@@ -520,6 +523,10 @@ class Script(scripts.Script): grid_infotext = [None]
+ state.xyz_plot_x = AxisInfo(x_opt, xs)
+ state.xyz_plot_y = AxisInfo(y_opt, ys)
+ state.xyz_plot_z = AxisInfo(z_opt, zs)
+
# If one of the axes is very slow to change between (like SD model
# checkpoint), then make sure it is in the outer iteration of the nested
# `for` loop.
@@ -20,6 +20,7 @@ import torch # Truncate version number of nightly/local build of PyTorch to not cause exceptions with CodeFormer or Safetensors
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, devices, sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks
@@ -97,7 +98,6 @@ def initialize(): modules.sd_models.setup_model()
codeformer.setup_model(cmd_opts.codeformer_models_path)
gfpgan.setup_model(cmd_opts.gfpgan_models_path)
- shared.face_restorers.append(modules.face_restoration.FaceRestoration())
modelloader.list_builtin_upscalers()
modules.scripts.load_scripts()
@@ -207,6 +207,14 @@ def webui(): if cmd_opts.gradio_queue:
shared.demo.queue(64)
+ gradio_auth_creds = []
+ if cmd_opts.gradio_auth:
+ gradio_auth_creds += cmd_opts.gradio_auth.strip('"').replace('\n', '').split(',')
+ if cmd_opts.gradio_auth_path:
+ with open(cmd_opts.gradio_auth_path, 'r', encoding="utf8") as file:
+ for line in file.readlines():
+ gradio_auth_creds += [x.strip() for x in line.split(',')]
+
app, local_url, share_url = shared.demo.launch(
share=cmd_opts.share,
server_name=server_name,
@@ -214,7 +222,7 @@ def webui(): ssl_keyfile=cmd_opts.tls_keyfile,
ssl_certfile=cmd_opts.tls_certfile,
debug=cmd_opts.gradio_debug,
- auth=[tuple(cred.split(':')) for cred in cmd_opts.gradio_auth.strip('"').split(',')] if cmd_opts.gradio_auth else None,
+ auth=[tuple(cred.split(':')) for cred in gradio_auth_creds] if gradio_auth_creds else None,
inbrowser=cmd_opts.autolaunch,
prevent_thread_lock=True
)
|