Merge pull request #66 from AUTOMATIC1111/master

merge from upstream

javascript/extensions.js

@@ -1,5 +1,5 @@
 
-function extensions_apply(_, _){
+function extensions_apply(_, _, disable_all){
     var disable = []
     var update = []
 
@@ -13,10 +13,10 @@ function extensions_apply(_, _){
 
     restart_reload()
 
-    return [JSON.stringify(disable), JSON.stringify(update)]
+    return [JSON.stringify(disable), JSON.stringify(update), disable_all]
 }
 
-function extensions_check(){
+function extensions_check(_, _){
     var disable = []
 
     gradioApp().querySelectorAll('#extensions input[type="checkbox"]').forEach(function(x){

launch.py

@@ -206,6 +206,10 @@ def list_extensions(settings_file):
         print(e, file=sys.stderr)
 
     disabled_extensions = set(settings.get('disabled_extensions', []))
+    disable_all_extensions = settings.get('disable_all_extensions', 'none')
+
+    if disable_all_extensions != 'none':
+        return []
 
     return [x for x in os.listdir(extensions_dir) if x not in disabled_extensions]
 
@@ -235,7 +239,7 @@ def prepare_environment():
     codeformer_repo = os.environ.get('CODEFORMER_REPO', 'https://github.com/sczhou/CodeFormer.git')
     blip_repo = os.environ.get('BLIP_REPO', 'https://github.com/salesforce/BLIP.git')
 
-    stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "47b6b607fdd31875c9279cd2f4f16b92e4ea958e")
+    stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf")
     taming_transformers_commit_hash = os.environ.get('TAMING_TRANSFORMERS_COMMIT_HASH', "24268930bf1dce879235a7fddd0b2355b84d7ea6")
     k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "5b3af030dd83e0297272d861c19477735d0317ec")
     codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")

modules/extensions.py

@@ -14,7 +14,12 @@ if not os.path.exists(extensions_dir):
 
 
 def active():
-    return [x for x in extensions if x.enabled]
+    if shared.opts.disable_all_extensions == "all":
+        return []
+    elif 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]
 
 
 class Extension:
@@ -96,6 +101,11 @@ def list_extensions():
     if not os.path.isdir(extensions_dir):
         return
 
+    if shared.opts.disable_all_extensions == "all":
+        print("*** \"Disable all extensions\" option was set, will not load any extensions ***")
+    elif shared.opts.disable_all_extensions == "extra":
+        print("*** \"Disable all extensions\" option was set, will only load built-in extensions ***")
+
     extension_paths = []
     for dirname in [extensions_dir, extensions_builtin_dir]:
         if not os.path.isdir(dirname):

modules/hypernetworks/hypernetwork.py

@@ -311,7 +311,7 @@ class Hypernetwork:
 
 def list_hypernetworks(path):
     res = {}
-    for filename in sorted(glob.iglob(os.path.join(path, '**/*.pt'), recursive=True)):
+    for filename in sorted(glob.iglob(os.path.join(path, '**/*.pt'), recursive=True), key=str.lower):
         name = os.path.splitext(os.path.basename(filename))[0]
         # Prevent a hypothetical "None.pt" from being listed.
         if name != "None":

modules/img2img.py

@@ -156,7 +156,8 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
     if shared.cmd_opts.enable_console_prompts:
         print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
 
-    p.extra_generation_params["Mask blur"] = mask_blur
+    if mask:
+        p.extra_generation_params["Mask blur"] = mask_blur
 
     if is_batch:
         assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"

modules/lowvram.py

@@ -55,12 +55,12 @@ def setup_for_low_vram(sd_model, use_medvram):
     if hasattr(sd_model.cond_stage_model, 'model'):
         sd_model.cond_stage_model.transformer = sd_model.cond_stage_model.model
 
-    # remove four big modules, cond, first_stage, depth (if applicable), and unet from the model and then
+    # remove several big modules: cond, first_stage, depth/embedder (if applicable), and unet from the model and then
     # send the model to GPU. Then put modules back. the modules will be in CPU.
-    stored = sd_model.cond_stage_model.transformer, sd_model.first_stage_model, getattr(sd_model, 'depth_model', None), sd_model.model
-    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.model = None, None, None, None
+    stored = sd_model.cond_stage_model.transformer, sd_model.first_stage_model, getattr(sd_model, 'depth_model', None), getattr(sd_model, 'embedder', None), sd_model.model
+    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.embedder, sd_model.model = None, None, None, None, None
     sd_model.to(devices.device)
-    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.model = stored
+    sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.depth_model, sd_model.embedder, sd_model.model = stored
 
     # register hooks for those the first three models
     sd_model.cond_stage_model.transformer.register_forward_pre_hook(send_me_to_gpu)
@@ -69,6 +69,8 @@ def setup_for_low_vram(sd_model, use_medvram):
     sd_model.first_stage_model.decode = first_stage_model_decode_wrap
     if sd_model.depth_model:
         sd_model.depth_model.register_forward_pre_hook(send_me_to_gpu)
+    if sd_model.embedder:
+        sd_model.embedder.register_forward_pre_hook(send_me_to_gpu)
     parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
 
     if hasattr(sd_model.cond_stage_model, 'model'):

modules/processing.py

@@ -78,22 +78,28 @@ def apply_overlay(image, paste_loc, index, overlays):
 
 
 def txt2img_image_conditioning(sd_model, x, width, height):
-    if sd_model.model.conditioning_key not in {'hybrid', 'concat'}:
-        # Dummy zero conditioning if we're not using inpainting model.
+    if sd_model.model.conditioning_key in {'hybrid', 'concat'}: # Inpainting models
+
+        # The "masked-image" in this case will just be all zeros since the entire image is masked.
+        image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
+        image_conditioning = sd_model.get_first_stage_encoding(sd_model.encode_first_stage(image_conditioning))
+
+        # Add the fake full 1s mask to the first dimension.
+        image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
+        image_conditioning = image_conditioning.to(x.dtype)
+
+        return image_conditioning
+
+    elif sd_model.model.conditioning_key == "crossattn-adm": # UnCLIP models
+
+        return x.new_zeros(x.shape[0], 2*sd_model.noise_augmentor.time_embed.dim, dtype=x.dtype, device=x.device)
+
+    else:
+        # Dummy zero conditioning if we're not using inpainting or unclip models.
         # Still takes up a bit of memory, but no encoder call.
         # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
         return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
 
-    # The "masked-image" in this case will just be all zeros since the entire image is masked.
-    image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
-    image_conditioning = sd_model.get_first_stage_encoding(sd_model.encode_first_stage(image_conditioning))
-
-    # Add the fake full 1s mask to the first dimension.
-    image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
-    image_conditioning = image_conditioning.to(x.dtype)
-
-    return image_conditioning
-
 
 class StableDiffusionProcessing:
     """
@@ -190,6 +196,14 @@ class StableDiffusionProcessing:
 
         return conditioning_image
 
+    def unclip_image_conditioning(self, source_image):
+        c_adm = self.sd_model.embedder(source_image)
+        if self.sd_model.noise_augmentor is not None:
+            noise_level = 0 # TODO: Allow other noise levels?
+            c_adm, noise_level_emb = self.sd_model.noise_augmentor(c_adm, noise_level=repeat(torch.tensor([noise_level]).to(c_adm.device), '1 -> b', b=c_adm.shape[0]))
+            c_adm = torch.cat((c_adm, noise_level_emb), 1)
+        return c_adm
+
     def inpainting_image_conditioning(self, source_image, latent_image, image_mask=None):
         self.is_using_inpainting_conditioning = True
 
@@ -241,6 +255,9 @@ class StableDiffusionProcessing:
         if self.sampler.conditioning_key in {'hybrid', 'concat'}:
             return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
 
+        if self.sampler.conditioning_key == "crossattn-adm":
+            return self.unclip_image_conditioning(source_image)
+
         # Dummy zero conditioning if we're not using inpainting or depth model.
         return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)
 

modules/sd_models.py

@@ -125,7 +125,7 @@ def list_models():
     elif cmd_ckpt is not None and cmd_ckpt != shared.default_sd_model_file:
         print(f"Checkpoint in --ckpt argument not found (Possible it was moved to {model_path}: {cmd_ckpt}", file=sys.stderr)
 
-    for filename in model_list:
+    for filename in sorted(model_list, key=str.lower):
         checkpoint_info = CheckpointInfo(filename)
         checkpoint_info.register()
 
@@ -389,6 +389,14 @@ def repair_config(sd_config):
     elif shared.cmd_opts.upcast_sampling:
         sd_config.model.params.unet_config.params.use_fp16 = True
 
+    if getattr(sd_config.model.params.first_stage_config.params.ddconfig, "attn_type", None) == "vanilla-xformers" and not shared.xformers_available:
+        sd_config.model.params.first_stage_config.params.ddconfig.attn_type = "vanilla"
+
+    # For UnCLIP-L, override the hardcoded karlo directory
+    if hasattr(sd_config.model.params, "noise_aug_config") and hasattr(sd_config.model.params.noise_aug_config.params, "clip_stats_path"):
+        karlo_path = os.path.join(paths.models_path, 'karlo')
+        sd_config.model.params.noise_aug_config.params.clip_stats_path = sd_config.model.params.noise_aug_config.params.clip_stats_path.replace("checkpoints/karlo_models", karlo_path)
+
 
 sd1_clip_weight = 'cond_stage_model.transformer.text_model.embeddings.token_embedding.weight'
 sd2_clip_weight = 'cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight'

modules/sd_models_config.py

@@ -14,6 +14,8 @@ config_sd2 = os.path.join(sd_repo_configs_path, "v2-inference.yaml")
 config_sd2v = os.path.join(sd_repo_configs_path, "v2-inference-v.yaml")
 config_sd2_inpainting = os.path.join(sd_repo_configs_path, "v2-inpainting-inference.yaml")
 config_depth_model = os.path.join(sd_repo_configs_path, "v2-midas-inference.yaml")
+config_unclip = os.path.join(sd_repo_configs_path, "v2-1-stable-unclip-l-inference.yaml")
+config_unopenclip = os.path.join(sd_repo_configs_path, "v2-1-stable-unclip-h-inference.yaml")
 config_inpainting = os.path.join(sd_configs_path, "v1-inpainting-inference.yaml")
 config_instruct_pix2pix = os.path.join(sd_configs_path, "instruct-pix2pix.yaml")
 config_alt_diffusion = os.path.join(sd_configs_path, "alt-diffusion-inference.yaml")
@@ -67,9 +69,14 @@ def guess_model_config_from_state_dict(sd, filename):
         return None
     sd2_cond_proj_weight = sd.get('cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight', None)
     diffusion_model_input = sd.get('model.diffusion_model.input_blocks.0.0.weight', None)
+    sd2_variations_weight = sd.get('embedder.model.ln_final.weight', None)
 
     if sd.get('depth_model.model.pretrained.act_postprocess3.0.project.0.bias', None) is not None:
         return config_depth_model
+    elif sd2_variations_weight is not None and sd2_variations_weight.shape[0] == 768:
+        return config_unclip
+    elif sd2_variations_weight is not None and sd2_variations_weight.shape[0] == 1024:
+        return config_unopenclip
 
     if sd2_cond_proj_weight is not None and sd2_cond_proj_weight.shape[1] == 1024:
         if diffusion_model_input.shape[1] == 9:

modules/sd_samplers_compvis.py

@@ -70,8 +70,13 @@ class VanillaStableDiffusionSampler:
 
         # Have to unwrap the inpainting conditioning here to perform pre-processing
         image_conditioning = None
+        uc_image_conditioning = None
         if isinstance(cond, dict):
-            image_conditioning = cond["c_concat"][0]
+            if self.conditioning_key == "crossattn-adm":
+                image_conditioning = cond["c_adm"]
+                uc_image_conditioning = unconditional_conditioning["c_adm"]
+            else:
+                image_conditioning = cond["c_concat"][0]
             cond = cond["c_crossattn"][0]
             unconditional_conditioning = unconditional_conditioning["c_crossattn"][0]
 
@@ -98,8 +103,12 @@ class VanillaStableDiffusionSampler:
         # Wrap the image conditioning back up since the DDIM code can accept the dict directly.
         # Note that they need to be lists because it just concatenates them later.
         if image_conditioning is not None:
-            cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]}
-            unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
+            if self.conditioning_key == "crossattn-adm":
+                cond = {"c_adm": image_conditioning, "c_crossattn": [cond]}
+                unconditional_conditioning = {"c_adm": uc_image_conditioning, "c_crossattn": [unconditional_conditioning]}
+            else:
+                cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]}
+                unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
 
         return x, ts, cond, unconditional_conditioning
 
@@ -176,8 +185,12 @@ class VanillaStableDiffusionSampler:
 
         # Wrap the conditioning models with additional image conditioning for inpainting model
         if image_conditioning is not None:
-            conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
-            unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
+            if self.conditioning_key == "crossattn-adm":
+                conditioning = {"c_adm": image_conditioning, "c_crossattn": [conditioning]}
+                unconditional_conditioning = {"c_adm": torch.zeros_like(image_conditioning), "c_crossattn": [unconditional_conditioning]}
+            else:
+                conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
+                unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
 
         samples = self.launch_sampling(t_enc + 1, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning))
 
@@ -195,8 +208,12 @@ class VanillaStableDiffusionSampler:
         # Wrap the conditioning models with additional image conditioning for inpainting model
         # dummy_for_plms is needed because PLMS code checks the first item in the dict to have the right shape
         if image_conditioning is not None:
-            conditioning = {"dummy_for_plms": np.zeros((conditioning.shape[0],)), "c_crossattn": [conditioning], "c_concat": [image_conditioning]}
-            unconditional_conditioning = {"c_crossattn": [unconditional_conditioning], "c_concat": [image_conditioning]}
+            if self.conditioning_key == "crossattn-adm":
+                conditioning = {"dummy_for_plms": np.zeros((conditioning.shape[0],)), "c_crossattn": [conditioning], "c_adm": image_conditioning}
+                unconditional_conditioning = {"c_crossattn": [unconditional_conditioning], "c_adm": torch.zeros_like(image_conditioning)}
+            else:
+                conditioning = {"dummy_for_plms": np.zeros((conditioning.shape[0],)), "c_crossattn": [conditioning], "c_concat": [image_conditioning]}
+                unconditional_conditioning = {"c_crossattn": [unconditional_conditioning], "c_concat": [image_conditioning]}
 
         samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
 

modules/sd_samplers_kdiffusion.py

@@ -92,14 +92,21 @@ class CFGDenoiser(torch.nn.Module):
         batch_size = len(conds_list)
         repeats = [len(conds_list[i]) for i in range(batch_size)]
 
+        if shared.sd_model.model.conditioning_key == "crossattn-adm":
+            image_uncond = torch.zeros_like(image_cond)
+            make_condition_dict = lambda c_crossattn, c_adm: {"c_crossattn": c_crossattn, "c_adm": c_adm} 
+        else:
+            image_uncond = image_cond
+            make_condition_dict = lambda c_crossattn, c_concat: {"c_crossattn": c_crossattn, "c_concat": [c_concat]} 
+
         if not is_edit_model:
             x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
             sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
-            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
+            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_uncond])
         else:
             x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x] + [x])
             sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma] + [sigma])
-            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond] + [torch.zeros_like(self.init_latent)])
+            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_uncond] + [torch.zeros_like(self.init_latent)])
 
         denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps, tensor, uncond)
         cfg_denoiser_callback(denoiser_params)
@@ -116,13 +123,13 @@ class CFGDenoiser(torch.nn.Module):
                 cond_in = torch.cat([tensor, uncond, uncond])
 
             if shared.batch_cond_uncond:
-                x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
+                x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict([cond_in], image_cond_in))
             else:
                 x_out = torch.zeros_like(x_in)
                 for batch_offset in range(0, x_out.shape[0], batch_size):
                     a = batch_offset
                     b = a + batch_size
-                    x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [cond_in[a:b]], "c_concat": [image_cond_in[a:b]]})
+                    x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict([cond_in[a:b]], image_cond_in[a:b]))
         else:
             x_out = torch.zeros_like(x_in)
             batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
@@ -135,9 +142,9 @@ class CFGDenoiser(torch.nn.Module):
                 else:
                     c_crossattn = torch.cat([tensor[a:b]], uncond)
 
-                x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": c_crossattn, "c_concat": [image_cond_in[a:b]]})
+                x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(c_crossattn, image_cond_in[a:b]))
 
-            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]:]]})
+            x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond=make_condition_dict([uncond], image_cond_in[-uncond.shape[0]:]))
 
         denoised_params = CFGDenoisedParams(x_out, state.sampling_step, state.sampling_steps)
         cfg_denoised_callback(denoised_params)

modules/shared.py

@@ -431,7 +431,8 @@ options_templates.update(options_section(('postprocessing', "Postprocessing"), {
 }))
 
 options_templates.update(options_section((None, "Hidden options"), {
-    "disabled_extensions": OptionInfo([], "Disable those extensions"),
+    "disabled_extensions": OptionInfo([], "Disable these extensions"),
+    "disable_all_extensions": OptionInfo("none", "Disable all extensions (preserves the list of disabled extensions)", gr.Radio, {"choices": ["none", "extra", "all"]}),
     "sd_checkpoint_hash": OptionInfo("", "SHA256 hash of the current checkpoint"),
 }))
 

modules/ui.py

@@ -70,17 +70,6 @@ def gr_show(visible=True):
 sample_img2img = "assets/stable-samples/img2img/sketch-mountains-input.jpg"
 sample_img2img = sample_img2img if os.path.exists(sample_img2img) else None
 
-css_hide_progressbar = """
-.wrap .m-12 svg { display:none!important; }
-.wrap .m-12::before { content:"Loading..." }
-.wrap .z-20 svg { display:none!important; }
-.wrap .z-20::before { content:"Loading..." }
-.wrap.cover-bg .z-20::before { content:"" }
-.progress-bar { display:none!important; }
-.meta-text { display:none!important; }
-.meta-text-center { display:none!important; }
-"""
-
 # Using constants for these since the variation selector isn't visible.
 # Important that they exactly match script.js for tooltip to work.
 random_symbol = '\U0001f3b2\ufe0f'  # 🎲️
@@ -1552,22 +1541,6 @@ def create_ui():
         (train_interface, "Train", "ti"),
     ]
 
-    css = ""
-
-    for cssfile in modules.scripts.list_files_with_name("style.css"):
-        if not os.path.isfile(cssfile):
-            continue
-
-        with open(cssfile, "r", encoding="utf8") as file:
-            css += file.read() + "\n"
-
-    if os.path.exists(os.path.join(data_path, "user.css")):
-        with open(os.path.join(data_path, "user.css"), "r", encoding="utf8") as file:
-            css += file.read() + "\n"
-
-    if not cmd_opts.no_progressbar_hiding:
-        css += css_hide_progressbar
-
     interfaces += script_callbacks.ui_tabs_callback()
     interfaces += [(settings_interface, "Settings", "settings")]
 
@@ -1578,7 +1551,7 @@ def create_ui():
     for _interface, label, _ifid in interfaces:
         shared.tab_names.append(label)
 
-    with gr.Blocks(css=css, analytics_enabled=False, title="Stable Diffusion") as demo:
+    with gr.Blocks(analytics_enabled=False, title="Stable Diffusion") as demo:
         with gr.Row(elem_id="quicksettings", variant="compact"):
             for i, k, item in sorted(quicksettings_list, key=lambda x: quicksettings_names.get(x[1], x[0])):
                 component = create_setting_component(k, is_quicksettings=True)
@@ -1763,25 +1736,60 @@ def create_ui():
     return demo
 
 
-def reload_javascript():
+def webpath(fn):
+    if fn.startswith(script_path):
+        web_path = os.path.relpath(fn, script_path).replace('\\', '/')
+    else:
+        web_path = os.path.abspath(fn)
+
+    return f'file={web_path}?{os.path.getmtime(fn)}'
+
+
+def javascript_html():
     script_js = os.path.join(script_path, "script.js")
-    head = f'<script type="text/javascript" src="file={os.path.abspath(script_js)}?{os.path.getmtime(script_js)}"></script>\n'
+    head = f'<script type="text/javascript" src="{webpath(script_js)}"></script>\n'
 
     inline = f"{localization.localization_js(shared.opts.localization)};"
     if cmd_opts.theme is not None:
         inline += f"set_theme('{cmd_opts.theme}');"
 
     for script in modules.scripts.list_scripts("javascript", ".js"):
-        head += f'<script type="text/javascript" src="file={script.path}?{os.path.getmtime(script.path)}"></script>\n'
+        head += f'<script type="text/javascript" src="{webpath(script.path)}"></script>\n'
 
     for script in modules.scripts.list_scripts("javascript", ".mjs"):
-        head += f'<script type="module" src="file={script.path}?{os.path.getmtime(script.path)}"></script>\n'
+        head += f'<script type="module" src="{webpath(script.path)}"></script>\n'
 
     head += f'<script type="text/javascript">{inline}</script>\n'
 
+    return head
+
+
+def css_html():
+    head = ""
+
+    def stylesheet(fn):
+        return f'<link rel="stylesheet" property="stylesheet" href="{webpath(fn)}">'
+
+    for cssfile in modules.scripts.list_files_with_name("style.css"):
+        if not os.path.isfile(cssfile):
+            continue
+
+        head += stylesheet(cssfile)
+
+    if os.path.exists(os.path.join(data_path, "user.css")):
+        head += stylesheet(os.path.join(data_path, "user.css"))
+
+    return head
+
+
+def reload_javascript():
+    js = javascript_html()
+    css = css_html()
+
     def template_response(*args, **kwargs):
         res = shared.GradioTemplateResponseOriginal(*args, **kwargs)
-        res.body = res.body.replace(b'</head>', f'{head}</head>'.encode("utf8"))
+        res.body = res.body.replace(b'</head>', f'{js}</head>'.encode("utf8"))
+        res.body = res.body.replace(b'</body>', f'{css}</body>'.encode("utf8"))
         res.init_headers()
         return res
 

modules/ui_extensions.py

@@ -20,7 +20,7 @@ def check_access():
     assert not shared.cmd_opts.disable_extension_access, "extension access disabled because of command line flags"
 
 
-def apply_and_restart(disable_list, update_list):
+def apply_and_restart(disable_list, update_list, disable_all):
     check_access()
 
     disabled = json.loads(disable_list)
@@ -42,6 +42,7 @@ def apply_and_restart(disable_list, update_list):
             shared.exception()
 
     shared.opts.disabled_extensions = disabled
+    shared.opts.disable_all_extensions = disable_all
     shared.opts.save(shared.config_filename)
 
     shared.state.interrupt()
@@ -98,9 +99,13 @@ def extension_table():
         else:
             ext_status = ext.status
 
+        style = ""
+        if shared.opts.disable_all_extensions == "extra" and not ext.is_builtin or shared.opts.disable_all_extensions == "all":
+            style = ' style="color: var(--primary-400)"'
+
         code += f"""
             <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><label{style}><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>
@@ -293,16 +298,24 @@ def create_ui():
                 with gr.Row(elem_id="extensions_installed_top"):
                     apply = gr.Button(value="Apply (restart required)", 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)
 
-                info = gr.HTML()
+                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>
+                    """
+                info = gr.HTML(html)
                 extensions_table = gr.HTML(lambda: extension_table())
 
                 apply.click(
                     fn=apply_and_restart,
                     _js="extensions_apply",
-                    inputs=[extensions_disabled_list, extensions_update_list],
+                    inputs=[extensions_disabled_list, extensions_update_list, extensions_disable_all],
                     outputs=[],
                 )
 

style.css

@@ -318,6 +318,13 @@ div.dimensions-tools{
     min-height: 480px !important;
 }
 
+#img2img_sketch, #img2maskimg, #inpaint_sketch {
+    overflow: overlay !important;
+    resize: auto;
+    background: var(--panel-background-fill);
+    z-index: 5;
+}
+
 .image-buttons button{
     min-width: auto;
 }
@@ -329,6 +336,7 @@ div.dimensions-tools{
 /* settings */
 #quicksettings {
     width: fit-content;
+    align-items: end;
 }
 
 #quicksettings > div, #quicksettings > fieldset{