aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--extensions-builtin/Lora/extra_networks_lora.py10
-rw-r--r--extensions-builtin/Lora/networks.py61
-rw-r--r--extensions-builtin/Lora/scripts/lora_script.py6
-rw-r--r--modules/launch_utils.py2
-rwxr-xr-xmodules/processing.py13
-rw-r--r--modules/sd_samplers_common.py8
-rw-r--r--modules/sd_samplers_kdiffusion.py11
-rw-r--r--modules/shared_options.py4
8 files changed, 75 insertions, 40 deletions
diff --git a/extensions-builtin/Lora/extra_networks_lora.py b/extensions-builtin/Lora/extra_networks_lora.py
index ba2945c6..005ff32c 100644
--- a/extensions-builtin/Lora/extra_networks_lora.py
+++ b/extensions-builtin/Lora/extra_networks_lora.py
@@ -6,9 +6,14 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
def __init__(self):
super().__init__('lora')
+ self.errors = {}
+ """mapping of network names to the number of errors the network had during operation"""
+
def activate(self, p, params_list):
additional = shared.opts.sd_lora
+ self.errors.clear()
+
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]))
@@ -56,4 +61,7 @@ class ExtraNetworkLora(extra_networks.ExtraNetwork):
p.extra_generation_params["Lora hashes"] = ", ".join(network_hashes)
def deactivate(self, p):
- pass
+ if self.errors:
+ p.comment("Networks with errors: " + ", ".join(f"{k} ({v})" for k, v in self.errors.items()))
+
+ self.errors.clear()
diff --git a/extensions-builtin/Lora/networks.py b/extensions-builtin/Lora/networks.py
index ba621139..c252ed9e 100644
--- a/extensions-builtin/Lora/networks.py
+++ b/extensions-builtin/Lora/networks.py
@@ -1,3 +1,4 @@
+import logging
import os
import re
@@ -194,7 +195,7 @@ def load_network(name, network_on_disk):
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}")
+ logging.debug(f"Network {network_on_disk.filename} didn't match keys: {keys_failed_to_match}")
return net
@@ -207,7 +208,6 @@ def purge_networks_from_memory():
devices.torch_gc()
-
def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=None):
already_loaded = {}
@@ -248,7 +248,7 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
if net is None:
failed_to_load_networks.append(name)
- print(f"Couldn't find network with name {name}")
+ logging.info(f"Couldn't find network with name {name}")
continue
net.te_multiplier = te_multipliers[i] if te_multipliers else 1.0
@@ -257,7 +257,7 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
loaded_networks.append(net)
if failed_to_load_networks:
- sd_hijack.model_hijack.comments.append("Failed to find networks: " + ", ".join(failed_to_load_networks))
+ sd_hijack.model_hijack.comments.append("Networks not found: " + ", ".join(failed_to_load_networks))
purge_networks_from_memory()
@@ -314,17 +314,22 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
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, ex_bias = module.calc_updown(self.weight)
+ try:
+ with torch.no_grad():
+ updown, ex_bias = 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))
+ 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
- if ex_bias is not None and getattr(self, 'bias', None) is not None:
- self.bias += ex_bias
- continue
+ self.weight += updown
+ if ex_bias is not None and getattr(self, 'bias', None) is not None:
+ self.bias += ex_bias
+ except RuntimeError as e:
+ logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
+ extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
+
+ continue
module_q = net.modules.get(network_layer_name + "_q_proj", None)
module_k = net.modules.get(network_layer_name + "_k_proj", None)
@@ -332,21 +337,28 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
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
+ try:
+ 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
+
+ except RuntimeError as e:
+ logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
+ extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
+
+ continue
if module is None:
continue
- print(f'failed to calculate network weights for layer {network_layer_name}')
+ logging.debug(f"Network {net.name} layer {network_layer_name}: couldn't find supported operation")
+ extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
self.network_current_names = wanted_names
@@ -519,6 +531,7 @@ def infotext_pasted(infotext, params):
if added:
params["Prompt"] += "\n" + "".join(added)
+extra_network_lora = None
available_networks = {}
available_network_aliases = {}
diff --git a/extensions-builtin/Lora/scripts/lora_script.py b/extensions-builtin/Lora/scripts/lora_script.py
index dc307f8c..4c6e774a 100644
--- a/extensions-builtin/Lora/scripts/lora_script.py
+++ b/extensions-builtin/Lora/scripts/lora_script.py
@@ -23,9 +23,9 @@ def unload():
def before_ui():
ui_extra_networks.register_page(ui_extra_networks_lora.ExtraNetworksPageLora())
- extra_network = extra_networks_lora.ExtraNetworkLora()
- extra_networks.register_extra_network(extra_network)
- extra_networks.register_extra_network_alias(extra_network, "lyco")
+ networks.extra_network_lora = extra_networks_lora.ExtraNetworkLora()
+ extra_networks.register_extra_network(networks.extra_network_lora)
+ extra_networks.register_extra_network_alias(networks.extra_network_lora, "lyco")
if not hasattr(torch.nn, 'Linear_forward_before_network'):
diff --git a/modules/launch_utils.py b/modules/launch_utils.py
index 65eb684f..e30fbac8 100644
--- a/modules/launch_utils.py
+++ b/modules/launch_utils.py
@@ -319,7 +319,7 @@ def prepare_environment():
stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf")
stable_diffusion_xl_commit_hash = os.environ.get('STABLE_DIFFUSION_XL_COMMIT_HASH', "5c10deee76adad0032b412294130090932317a87")
- k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "c9fe758757e022f05ca5a53fa8fac28889e4f1cf")
+ k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "ab527a9a6d347f364e3d185ba6d714e22d80cb3c")
codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
diff --git a/modules/processing.py b/modules/processing.py
index 007a4e05..10749aa2 100755
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -157,6 +157,7 @@ class StableDiffusionProcessing:
cached_uc = [None, None]
cached_c = [None, None]
+ comments: dict = None
sampler: sd_samplers_common.Sampler | None = field(default=None, init=False)
is_using_inpainting_conditioning: bool = field(default=False, init=False)
paste_to: tuple | None = field(default=None, init=False)
@@ -196,6 +197,8 @@ class StableDiffusionProcessing:
if self.sampler_index is not None:
print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
+ self.comments = {}
+
self.sampler_noise_scheduler_override = None
self.s_min_uncond = self.s_min_uncond if self.s_min_uncond is not None else opts.s_min_uncond
self.s_churn = self.s_churn if self.s_churn is not None else opts.s_churn
@@ -226,6 +229,9 @@ class StableDiffusionProcessing:
def sd_model(self, value):
pass
+ def comment(self, text):
+ self.comments[text] = 1
+
def txt2img_image_conditioning(self, x, width=None, height=None):
self.is_using_inpainting_conditioning = self.sd_model.model.conditioning_key in {'hybrid', 'concat'}
@@ -429,7 +435,7 @@ class Processed:
self.subseed = subseed
self.subseed_strength = p.subseed_strength
self.info = info
- self.comments = comments
+ self.comments = "".join(f"{comment}\n" for comment in p.comments)
self.width = p.width
self.height = p.height
self.sampler_name = p.sampler_name
@@ -720,8 +726,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
modules.sd_hijack.model_hijack.apply_circular(p.tiling)
modules.sd_hijack.model_hijack.clear_comments()
- comments = {}
-
p.setup_prompts()
if type(seed) == list:
@@ -801,7 +805,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
p.setup_conds()
for comment in model_hijack.comments:
- comments[comment] = 1
+ p.comment(comment)
p.extra_generation_params.update(model_hijack.extra_generation_params)
@@ -930,7 +934,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
images_list=output_images,
seed=p.all_seeds[0],
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,
infotexts=infotexts,
diff --git a/modules/sd_samplers_common.py b/modules/sd_samplers_common.py
index f9d034ca..07fc4434 100644
--- a/modules/sd_samplers_common.py
+++ b/modules/sd_samplers_common.py
@@ -284,19 +284,19 @@ class Sampler:
s_tmax = getattr(opts, 's_tmax', p.s_tmax) or self.s_tmax # 0 = inf
s_noise = getattr(opts, 's_noise', p.s_noise)
- if s_churn != self.s_churn:
+ if 's_churn' in extra_params_kwargs and s_churn != self.s_churn:
extra_params_kwargs['s_churn'] = s_churn
p.s_churn = s_churn
p.extra_generation_params['Sigma churn'] = s_churn
- if s_tmin != self.s_tmin:
+ if 's_tmin' in extra_params_kwargs and s_tmin != self.s_tmin:
extra_params_kwargs['s_tmin'] = s_tmin
p.s_tmin = s_tmin
p.extra_generation_params['Sigma tmin'] = s_tmin
- if s_tmax != self.s_tmax:
+ if 's_tmax' in extra_params_kwargs and s_tmax != self.s_tmax:
extra_params_kwargs['s_tmax'] = s_tmax
p.s_tmax = s_tmax
p.extra_generation_params['Sigma tmax'] = s_tmax
- if s_noise != self.s_noise:
+ if 's_noise' in extra_params_kwargs and s_noise != self.s_noise:
extra_params_kwargs['s_noise'] = s_noise
p.s_noise = s_noise
p.extra_generation_params['Sigma noise'] = s_noise
diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py
index 1f8e9c4b..0bacfe8d 100644
--- a/modules/sd_samplers_kdiffusion.py
+++ b/modules/sd_samplers_kdiffusion.py
@@ -22,6 +22,9 @@ samplers_k_diffusion = [
('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),
('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {"second_order": True, "brownian_noise": True}),
('DPM++ 2M SDE', 'sample_dpmpp_2m_sde', ['k_dpmpp_2m_sde_ka'], {"brownian_noise": True}),
+ ('DPM++ 3M SDE', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde'], {'discard_next_to_last_sigma': True, "brownian_noise": True}),
+ ('DPM++ 3M SDE Karras', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True, "brownian_noise": True}),
+ ('DPM++ 3M SDE Exponential', 'sample_dpmpp_3m_sde', ['k_dpmpp_3m_sde_exp'], {'scheduler': 'exponential', 'discard_next_to_last_sigma': True, "brownian_noise": True}),
('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {"uses_ensd": True}),
('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {"uses_ensd": True}),
('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),
@@ -42,6 +45,12 @@ sampler_extra_params = {
'sample_euler': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
'sample_heun': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
'sample_dpm_2': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
+ 'sample_dpm_fast': ['s_noise'],
+ 'sample_dpm_2_ancestral': ['s_noise'],
+ 'sample_dpmpp_2s_ancestral': ['s_noise'],
+ 'sample_dpmpp_sde': ['s_noise'],
+ 'sample_dpmpp_2m_sde': ['s_noise'],
+ 'sample_dpmpp_3m_sde': ['s_noise'],
}
k_diffusion_samplers_map = {x.name: x for x in samplers_data_k_diffusion}
@@ -67,6 +76,8 @@ class KDiffusionSampler(sd_samplers_common.Sampler):
def __init__(self, funcname, sd_model, options=None):
super().__init__(funcname)
+ self.extra_params = sampler_extra_params.get(funcname, [])
+
self.options = options or {}
self.func = funcname if callable(funcname) else getattr(k_diffusion.sampling, self.funcname)
diff --git a/modules/shared_options.py b/modules/shared_options.py
index 9ae51f18..7f6c3658 100644
--- a/modules/shared_options.py
+++ b/modules/shared_options.py
@@ -285,12 +285,12 @@ options_templates.update(options_section(('ui', "Live previews"), {
options_templates.update(options_section(('sampler-params', "Sampler parameters"), {
"hide_samplers": OptionInfo([], "Hide samplers in user interface", gr.CheckboxGroup, lambda: {"choices": [x.name for x in shared_items.list_samplers()]}).needs_reload_ui(),
"eta_ddim": OptionInfo(0.0, "Eta for DDIM", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta DDIM').info("noise multiplier; higher = more unperdictable results"),
- "eta_ancestral": OptionInfo(1.0, "Eta for ancestral samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta').info("noise multiplier; applies to Euler a and other samplers that have a in them"),
+ "eta_ancestral": OptionInfo(1.0, "Eta for k-diffusion samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta').info("noise multiplier; currently only applies to ancestral samplers (i.e. Euler a) and SDE samplers"),
"ddim_discretize": OptionInfo('uniform', "img2img DDIM discretize", gr.Radio, {"choices": ['uniform', 'quad']}),
's_churn': OptionInfo(0.0, "sigma churn", gr.Slider, {"minimum": 0.0, "maximum": 100.0, "step": 0.01}, infotext='Sigma churn').info('amount of stochasticity; only applies to Euler, Heun, and DPM2'),
's_tmin': OptionInfo(0.0, "sigma tmin", gr.Slider, {"minimum": 0.0, "maximum": 10.0, "step": 0.01}, infotext='Sigma tmin').info('enable stochasticity; start value of the sigma range; only applies to Euler, Heun, and DPM2'),
's_tmax': OptionInfo(0.0, "sigma tmax", gr.Slider, {"minimum": 0.0, "maximum": 999.0, "step": 0.01}, infotext='Sigma tmax').info("0 = inf; end value of the sigma range; only applies to Euler, Heun, and DPM2"),
- 's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.1, "step": 0.001}, infotext='Sigma noise').info('amount of additional noise to counteract loss of detail during sampling; only applies to Euler, Heun, and DPM2'),
+ 's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.1, "step": 0.001}, infotext='Sigma noise').info('amount of additional noise to counteract loss of detail during sampling'),
'k_sched_type': OptionInfo("Automatic", "Scheduler type", gr.Dropdown, {"choices": ["Automatic", "karras", "exponential", "polyexponential"]}, infotext='Schedule type').info("lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below"),
'sigma_min': OptionInfo(0.0, "sigma min", gr.Number, infotext='Schedule max sigma').info("0 = default (~0.03); minimum noise strength for k-diffusion noise scheduler"),
'sigma_max': OptionInfo(0.0, "sigma max", gr.Number, infotext='Schedule min sigma').info("0 = default (~14.6); maximum noise strength for k-diffusion noise scheduler"),
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-24 12:25:43 +0000