Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui

README.md

@@ -157,5 +157,6 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al
 - Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
 - Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
 - Security advice - RyotaK
+- UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
 - Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
 - (You)

extensions-builtin/Lora/ui_extra_networks_lora.py

@@ -15,21 +15,14 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
     def list_items(self):
         for name, lora_on_disk in lora.available_loras.items():
             path, ext = os.path.splitext(lora_on_disk.filename)
-            previews = [path + ".png", path + ".preview.png"]
-
-            preview = None
-            for file in previews:
-                if os.path.isfile(file):
-                    preview = self.link_preview(file)
-                    break
-
             yield {
                 "name": name,
                 "filename": path,
-                "preview": preview,
+                "preview": self.find_preview(path),
+                "description": self.find_description(path),
                 "search_term": self.search_terms_from_path(lora_on_disk.filename),
                 "prompt": json.dumps(f"<lora:{name}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
-                "local_preview": path + ".png",
+                "local_preview": f"{path}.{shared.opts.samples_format}",
             }
 
     def allowed_directories_for_previews(self):

html/extra-networks-card.html

@@ -7,6 +7,7 @@
 			<span style="display:none" class='search_term'>{search_term}</span>
 		</div>
 		<span class='name'>{name}</span>
+		<span class='description'>{description}</span>
 	</div>
 </div>
 

javascript/extraNetworks.js

@@ -78,7 +78,7 @@ function cardClicked(tabname, textToAdd, allowNegativePrompt){
     var textarea = allowNegativePrompt ? activePromptTextarea[tabname] : gradioApp().querySelector("#" + tabname + "_prompt > label > textarea")
 
     if(! tryToRemoveExtraNetworkFromPrompt(textarea, textToAdd)){
-        textarea.value = textarea.value + " " + textToAdd
+        textarea.value = textarea.value + opts.extra_networks_add_text_separator + textToAdd
     }
 
     updateInput(textarea)

javascript/hints.js

@@ -6,6 +6,7 @@ titles = {
 	"GFPGAN": "Restore low quality faces using GFPGAN neural network",
 	"Euler a": "Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps higher than 30-40 does not help",
 	"DDIM": "Denoising Diffusion Implicit Models - best at inpainting",
+	"UniPC": "Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models",
 	"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 (has no impact on generation performance or VRAM usage)",

javascript/notification.js

@@ -15,7 +15,7 @@ onUiUpdate(function(){
         }
     }
 
-    const galleryPreviews = gradioApp().querySelectorAll('div[id^="tab_"][style*="display: block"] img.h-full.w-full.overflow-hidden');
+    const galleryPreviews = gradioApp().querySelectorAll('div[id^="tab_"][style*="display: block"] div[id$="_results"] img.h-full.w-full.overflow-hidden');
 
     if (galleryPreviews == null) return;
 

javascript/progressbar.js

@@ -139,7 +139,7 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
 
     var divProgress = document.createElement('div')
     divProgress.className='progressDiv'
-    divProgress.style.display = opts.show_progressbar ? "" : "none"
+    divProgress.style.display = opts.show_progressbar ? "block" : "none"
     var divInner = document.createElement('div')
     divInner.className='progress'
 

launch.py

@@ -161,7 +161,17 @@ def git_clone(url, dir, name, commithash=None):
     if commithash is not None:
         run(f'"{git}" -C "{dir}" checkout {commithash}', None, "Couldn't checkout {name}'s hash: {commithash}")
 
-        
+
+def git_pull_recursive(dir):
+    for subdir, _, _ in os.walk(dir):
+        if os.path.exists(os.path.join(subdir, '.git')):
+            try:
+                output = subprocess.check_output([git, '-C', subdir, 'pull', '--autostash'])
+                print(f"Pulled changes for repository in '{subdir}':\n{output.decode('utf-8').strip()}\n")
+            except subprocess.CalledProcessError as e:
+                print(f"Couldn't perform 'git pull' on repository in '{subdir}':\n{e.output.decode('utf-8').strip()}\n")
+
+
 def version_check(commit):
     try:
         import requests
@@ -247,6 +257,7 @@ def prepare_environment():
     args, _ = parser.parse_known_args(sys.argv)
 
     sys.argv, _ = extract_arg(sys.argv, '-f')
+    sys.argv, update_all_extensions = extract_arg(sys.argv, '--update-all-extensions')
     sys.argv, skip_torch_cuda_test = extract_arg(sys.argv, '--skip-torch-cuda-test')
     sys.argv, skip_python_version_check = extract_arg(sys.argv, '--skip-python-version-check')
     sys.argv, reinstall_xformers = extract_arg(sys.argv, '--reinstall-xformers')
@@ -312,6 +323,9 @@ def prepare_environment():
 
     if update_check:
         version_check(commit)
+
+    if update_all_extensions:
+        git_pull_recursive(dir_extensions)
     
     if "--exit" in sys.argv:
         print("Exiting because of --exit argument")

modules/api/api.py

@@ -150,6 +150,7 @@ class Api:
         self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=TrainResponse)
         self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=TrainResponse)
         self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=MemoryResponse)
+        self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=ScriptsList)
 
     def add_api_route(self, path: str, endpoint, **kwargs):
         if shared.cmd_opts.api_auth:
@@ -170,6 +171,12 @@ class Api:
         script_idx = script_name_to_index(script_name, script_runner.selectable_scripts)
         script = script_runner.selectable_scripts[script_idx]
         return script, script_idx
+    
+    def get_scripts_list(self):
+        t2ilist = [str(title.lower()) for title in scripts.scripts_txt2img.titles]
+        i2ilist = [str(title.lower()) for title in scripts.scripts_img2img.titles]
+
+        return ScriptsList(txt2img = t2ilist, img2img = i2ilist)  
 
     def get_script(self, script_name, script_runner):
         if script_name is None or script_name == "":
@@ -215,12 +222,11 @@ class Api:
             ui.create_ui()
         selectable_scripts, selectable_script_idx = self.get_selectable_script(txt2imgreq.script_name, script_runner)
 
-        populate = txt2imgreq.copy(update={ # Override __init__ params
+        populate = txt2imgreq.copy(update={  # Override __init__ params
             "sampler_name": validate_sampler_name(txt2imgreq.sampler_name or txt2imgreq.sampler_index),
-            "do_not_save_samples": True,
-            "do_not_save_grid": True
-            }
-        )
+            "do_not_save_samples": not txt2imgreq.save_images,
+            "do_not_save_grid": not txt2imgreq.save_images,
+        })
         if populate.sampler_name:
             populate.sampler_index = None  # prevent a warning later on
 
@@ -231,22 +237,25 @@ class Api:
 
         script_args = self.init_script_args(txt2imgreq, selectable_scripts, selectable_script_idx, script_runner)
 
+        send_images = args.pop('send_images', True)
+        args.pop('save_images', None)
+
         with self.queue_lock:
             p = StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)
             p.scripts = script_runner
+            p.outpath_grids = opts.outdir_txt2img_grids
+            p.outpath_samples = opts.outdir_txt2img_samples
 
             shared.state.begin()
             if selectable_scripts != None:
                 p.script_args = script_args
-                p.outpath_grids = opts.outdir_txt2img_grids
-                p.outpath_samples = opts.outdir_txt2img_samples
                 processed = scripts.scripts_txt2img.run(p, *p.script_args) # Need to pass args as list here
             else:
                 p.script_args = tuple(script_args) # Need to pass args as tuple here
                 processed = process_images(p)
             shared.state.end()
 
-        b64images = list(map(encode_pil_to_base64, processed.images))
+        b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else []
 
         return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
 
@@ -267,11 +276,10 @@ class Api:
 
         populate = img2imgreq.copy(update={ # Override __init__ params
             "sampler_name": validate_sampler_name(img2imgreq.sampler_name or img2imgreq.sampler_index),
-            "do_not_save_samples": True,
-            "do_not_save_grid": True,
-            "mask": mask
-            }
-        )
+            "do_not_save_samples": not img2imgreq.save_images,
+            "do_not_save_grid": not img2imgreq.save_images,
+            "mask": mask,
+        })
         if populate.sampler_name:
             populate.sampler_index = None  # prevent a warning later on
 
@@ -283,23 +291,26 @@ class Api:
 
         script_args = self.init_script_args(img2imgreq, selectable_scripts, selectable_script_idx, script_runner)
 
+        send_images = args.pop('send_images', True)
+        args.pop('save_images', None)
+
         with self.queue_lock:
             p = StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)
             p.init_images = [decode_base64_to_image(x) for x in init_images]
             p.scripts = script_runner
+            p.outpath_grids = opts.outdir_img2img_grids
+            p.outpath_samples = opts.outdir_img2img_samples
 
             shared.state.begin()
             if selectable_scripts != None:
                 p.script_args = script_args
-                p.outpath_grids = opts.outdir_img2img_grids
-                p.outpath_samples = opts.outdir_img2img_samples
                 processed = scripts.scripts_img2img.run(p, *p.script_args) # Need to pass args as list here
             else:
                 p.script_args = tuple(script_args) # Need to pass args as tuple here
                 processed = process_images(p)
             shared.state.end()
 
-        b64images = list(map(encode_pil_to_base64, processed.images))
+        b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else []
 
         if not img2imgreq.include_init_images:
             img2imgreq.init_images = None

modules/api/models.py

@@ -14,8 +14,8 @@ API_NOT_ALLOWED = [
     "outpath_samples",
     "outpath_grids",
     "sampler_index",
-    "do_not_save_samples",
-    "do_not_save_grid",
+    # "do_not_save_samples",
+    # "do_not_save_grid",
     "extra_generation_params",
     "overlay_images",
     "do_not_reload_embeddings",
@@ -100,13 +100,32 @@ class PydanticModelGenerator:
 StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
     "StableDiffusionProcessingTxt2Img",
     StableDiffusionProcessingTxt2Img,
-    [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "script_name", "type": str, "default": None}, {"key": "script_args", "type": list, "default": []}, {"key": "alwayson_scripts", "type": dict, "default": {}}]
+    [
+        {"key": "sampler_index", "type": str, "default": "Euler"},
+        {"key": "script_name", "type": str, "default": None},
+        {"key": "script_args", "type": list, "default": []},
+        {"key": "send_images", "type": bool, "default": True},
+        {"key": "save_images", "type": bool, "default": False},
+        {"key": "alwayson_scripts", "type": dict, "default": {}},
+    ]
 ).generate_model()
 
 StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
     "StableDiffusionProcessingImg2Img",
     StableDiffusionProcessingImg2Img,
-    [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}, {"key": "include_init_images", "type": bool, "default": False, "exclude" : True}, {"key": "script_name", "type": str, "default": None}, {"key": "script_args", "type": list, "default": []}, {"key": "alwayson_scripts", "type": dict, "default": {}}]
+
+    [
+        {"key": "sampler_index", "type": str, "default": "Euler"},
+        {"key": "init_images", "type": list, "default": None},
+        {"key": "denoising_strength", "type": float, "default": 0.75},
+        {"key": "mask", "type": str, "default": None},
+        {"key": "include_init_images", "type": bool, "default": False, "exclude" : True},
+        {"key": "script_name", "type": str, "default": None},
+        {"key": "script_args", "type": list, "default": []},
+        {"key": "send_images", "type": bool, "default": True},
+        {"key": "save_images", "type": bool, "default": False},
+        {"key": "alwayson_scripts", "type": dict, "default": {}},
+    ]
 ).generate_model()
 
 class TextToImageResponse(BaseModel):
@@ -267,3 +286,7 @@ class EmbeddingsResponse(BaseModel):
 class MemoryResponse(BaseModel):
     ram: dict = Field(title="RAM", description="System memory stats")
     cuda: dict = Field(title="CUDA", description="nVidia CUDA memory stats")
+
+class ScriptsList(BaseModel):
+    txt2img: list = Field(default=None,title="Txt2img", description="Titles of scripts (txt2img)")
+    img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)")
\ No newline at end of file

modules/codeformer_model.py

@@ -55,7 +55,7 @@ def setup_model(dirname):
                 if self.net is not None and self.face_helper is not None:
                     self.net.to(devices.device_codeformer)
                     return self.net, self.face_helper
-                model_paths = modelloader.load_models(model_path, model_url, self.cmd_dir, download_name='codeformer-v0.1.0.pth')
+                model_paths = modelloader.load_models(model_path, model_url, self.cmd_dir, download_name='codeformer-v0.1.0.pth', ext_filter=['.pth'])
                 if len(model_paths) != 0:
                     ckpt_path = model_paths[0]
                 else:

modules/extensions.py

@@ -66,7 +66,7 @@ class Extension:
 
     def check_updates(self):
         repo = git.Repo(self.path)
-        for fetch in repo.remote().fetch("--dry-run"):
+        for fetch in repo.remote().fetch(dry_run=True):
             if fetch.flags != fetch.HEAD_UPTODATE:
                 self.can_update = True
                 self.status = "behind"
@@ -79,8 +79,8 @@ class Extension:
         repo = git.Repo(self.path)
         # Fix: `error: Your local changes to the following files would be overwritten by merge`,
         # because WSL2 Docker set 755 file permissions instead of 644, this results to the error.
-        repo.git.fetch('--all')
-        repo.git.reset('--hard', 'origin')
+        repo.git.fetch(all=True)
+        repo.git.reset('origin', hard=True)
 
 
 def list_extensions():

modules/generation_parameters_copypaste.py

@@ -23,13 +23,14 @@ registered_param_bindings = []
 
 
 class ParamBinding:
-    def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None):
+    def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None, paste_field_names=[]):
         self.paste_button = paste_button
         self.tabname = tabname
         self.source_text_component = source_text_component
         self.source_image_component = source_image_component
         self.source_tabname = source_tabname
         self.override_settings_component = override_settings_component
+        self.paste_field_names = paste_field_names
 
 
 def reset():
@@ -134,7 +135,7 @@ def connect_paste_params_buttons():
             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 [])
+            paste_field_names = ['Prompt', 'Negative prompt', 'Steps', 'Face restoration'] + (["Seed"] if shared.opts.send_seed else []) + binding.paste_field_names
             binding.paste_button.click(
                 fn=lambda *x: x,
                 inputs=[field for field, name in paste_fields[binding.source_tabname]["fields"] if name in paste_field_names],
@@ -288,6 +289,8 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
 
 settings_map = {}
 
+
+
 infotext_to_setting_name_mapping = [
     ('Clip skip', 'CLIP_stop_at_last_layers', ),
     ('Conditional mask weight', 'inpainting_mask_weight'),
@@ -296,7 +299,11 @@ infotext_to_setting_name_mapping = [
     ('Noise multiplier', 'initial_noise_multiplier'),
     ('Eta', 'eta_ancestral'),
     ('Eta DDIM', 'eta_ddim'),
-    ('Discard penultimate sigma', 'always_discard_next_to_last_sigma')
+    ('Discard penultimate sigma', 'always_discard_next_to_last_sigma'),
+    ('UniPC variant', 'uni_pc_variant'),
+    ('UniPC skip type', 'uni_pc_skip_type'),
+    ('UniPC order', 'uni_pc_order'),
+    ('UniPC lower order final', 'uni_pc_lower_order_final'),
 ]
 
 

modules/images.py

@@ -556,7 +556,7 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
             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)
+            image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality, lossless=opts.webp_lossless)
 
             if opts.enable_pnginfo and info is not None:
                 exif_bytes = piexif.dump({

modules/modelloader.py

@@ -6,7 +6,7 @@ from urllib.parse import urlparse
 
 from basicsr.utils.download_util import load_file_from_url
 from modules import shared
-from modules.upscaler import Upscaler
+from modules.upscaler import Upscaler, UpscalerLanczos, UpscalerNearest, UpscalerNone
 from modules.paths import script_path, models_path
 
 
@@ -169,4 +169,8 @@ def load_upscalers():
         scaler = cls(commandline_options.get(cmd_name, None))
         datas += scaler.scalers
 
-    shared.sd_upscalers = datas
+    shared.sd_upscalers = sorted(
+        datas,
+        # Special case for UpscalerNone keeps it at the beginning of the list.
+        key=lambda x: x.name.lower() if not isinstance(x.scaler, (UpscalerNone, UpscalerLanczos, UpscalerNearest)) else ""
+    )

modules/models/diffusion/uni_pc/__init__.py

+from .sampler import UniPCSampler

modules/models/diffusion/uni_pc/sampler.py

+"""SAMPLING ONLY."""
+
+import torch
+
+from .uni_pc import NoiseScheduleVP, model_wrapper, UniPC
+from modules import shared, devices
+
+
+class UniPCSampler(object):
+    def __init__(self, model, **kwargs):
+        super().__init__()
+        self.model = model
+        to_torch = lambda x: x.clone().detach().to(torch.float32).to(model.device)
+        self.before_sample = None
+        self.after_sample = None
+        self.register_buffer('alphas_cumprod', to_torch(model.alphas_cumprod))
+
+    def register_buffer(self, name, attr):
+        if type(attr) == torch.Tensor:
+            if attr.device != devices.device:
+                attr = attr.to(devices.device)
+        setattr(self, name, attr)
+
+    def set_hooks(self, before_sample, after_sample, after_update):
+        self.before_sample = before_sample
+        self.after_sample = after_sample
+        self.after_update = after_update
+
+    @torch.no_grad()
+    def sample(self,
+               S,
+               batch_size,
+               shape,
+               conditioning=None,
+               callback=None,
+               normals_sequence=None,
+               img_callback=None,
+               quantize_x0=False,
+               eta=0.,
+               mask=None,
+               x0=None,
+               temperature=1.,
+               noise_dropout=0.,
+               score_corrector=None,
+               corrector_kwargs=None,
+               verbose=True,
+               x_T=None,
+               log_every_t=100,
+               unconditional_guidance_scale=1.,
+               unconditional_conditioning=None,
+               # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
+               **kwargs
+               ):
+        if conditioning is not None:
+            if isinstance(conditioning, dict):
+                ctmp = conditioning[list(conditioning.keys())[0]]
+                while isinstance(ctmp, list): ctmp = ctmp[0]
+                cbs = ctmp.shape[0]
+                if cbs != batch_size:
+                    print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
+
+            elif isinstance(conditioning, list):
+                for ctmp in conditioning:
+                    if ctmp.shape[0] != batch_size:
+                        print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
+
+            else:
+                if conditioning.shape[0] != batch_size:
+                    print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
+
+        # sampling
+        C, H, W = shape
+        size = (batch_size, C, H, W)
+        print(f'Data shape for UniPC sampling is {size}')
+
+        device = self.model.betas.device
+        if x_T is None:
+            img = torch.randn(size, device=device)
+        else:
+            img = x_T
+
+        ns = NoiseScheduleVP('discrete', alphas_cumprod=self.alphas_cumprod)
+
+        # SD 1.X is "noise", SD 2.X is "v"
+        model_type = "v" if self.model.parameterization == "v" else "noise"
+
+        model_fn = model_wrapper(
+            lambda x, t, c: self.model.apply_model(x, t, c),
+            ns,
+            model_type=model_type,
+            guidance_type="classifier-free",
+            #condition=conditioning,
+            #unconditional_condition=unconditional_conditioning,
+            guidance_scale=unconditional_guidance_scale,
+        )
+
+        uni_pc = UniPC(model_fn, ns, predict_x0=True, thresholding=False, variant=shared.opts.uni_pc_variant, condition=conditioning, unconditional_condition=unconditional_conditioning, before_sample=self.before_sample, after_sample=self.after_sample, after_update=self.after_update)
+        x = uni_pc.sample(img, steps=S, skip_type=shared.opts.uni_pc_skip_type, method="multistep", order=shared.opts.uni_pc_order, lower_order_final=shared.opts.uni_pc_lower_order_final)
+
+        return x.to(device), None

modules/processing.py

@@ -597,6 +597,9 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             seeds = p.all_seeds[n * p.batch_size:(n + 1) * p.batch_size]
             subseeds = p.all_subseeds[n * p.batch_size:(n + 1) * p.batch_size]
 
+            if p.scripts is not None:
+                p.scripts.before_process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds)
+
             if len(prompts) == 0:
                 break
 
@@ -888,7 +891,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         shared.state.nextjob()
 
-        img2img_sampler_name = self.sampler_name if self.sampler_name != 'PLMS' else 'DDIM'  # PLMS does not support img2img so we just silently switch ot DDIM
+        img2img_sampler_name = self.sampler_name
+        if self.sampler_name in ['PLMS', 'UniPC']:  # PLMS/UniPC do not support img2img so we just silently switch to DDIM
+            img2img_sampler_name = 'DDIM'
         self.sampler = sd_samplers.create_sampler(img2img_sampler_name, self.sd_model)
 
         samples = samples[:, :, self.truncate_y//2:samples.shape[2]-(self.truncate_y+1)//2, self.truncate_x//2:samples.shape[3]-(self.truncate_x+1)//2]

modules/script_callbacks.py

@@ -29,7 +29,7 @@ class ImageSaveParams:
 
 
 class CFGDenoiserParams:
-    def __init__(self, x, image_cond, sigma, sampling_step, total_sampling_steps):
+    def __init__(self, x, image_cond, sigma, sampling_step, total_sampling_steps, text_cond, text_uncond):
         self.x = x
         """Latent image representation in the process of being denoised"""
         
@@ -44,6 +44,12 @@ class CFGDenoiserParams:
         
         self.total_sampling_steps = total_sampling_steps
         """Total number of sampling steps planned"""
+        
+        self.text_cond = text_cond
+        """ Encoder hidden states of text conditioning from prompt"""
+        
+        self.text_uncond = text_uncond
+        """ Encoder hidden states of text conditioning from negative prompt"""
 
 
 class CFGDenoisedParams:

modules/scripts.py

@@ -33,6 +33,11 @@ class Script:
     parsing infotext to set the value for the component; see ui.py's txt2img_paste_fields for an example
     """
 
+    paste_field_names = None
+    """if set in ui(), this is a list of names of infotext fields; the fields will be sent through the
+    various "Send to <X>" buttons when clicked
+    """
+
     def title(self):
         """this function should return the title of the script. This is what will be displayed in the dropdown menu."""
 
@@ -80,6 +85,20 @@ class Script:
 
         pass
 
+    def before_process_batch(self, p, *args, **kwargs):
+        """
+        Called before extra networks are parsed from the prompt, so you can add
+        new extra network keywords to the prompt with this callback.
+
+        **kwargs will have those items:
+          - batch_number - index of current batch, from 0 to number of batches-1
+          - prompts - list of prompts for current batch; you can change contents of this list but changing the number of entries will likely break things
+          - seeds - list of seeds for current batch
+          - subseeds - list of subseeds for current batch
+        """
+
+        pass
+
     def process_batch(self, p, *args, **kwargs):
         """
         Same as process(), but called for every batch.
@@ -256,6 +275,7 @@ class ScriptRunner:
         self.alwayson_scripts = []
         self.titles = []
         self.infotext_fields = []
+        self.paste_field_names = []
 
     def initialize_scripts(self, is_img2img):
         from modules import scripts_auto_postprocessing
@@ -304,6 +324,9 @@ class ScriptRunner:
             if script.infotext_fields is not None:
                 self.infotext_fields += script.infotext_fields
 
+            if script.paste_field_names is not None:
+                self.paste_field_names += script.paste_field_names
+
             inputs += controls
             inputs_alwayson += [script.alwayson for _ in controls]
             script.args_to = len(inputs)
@@ -388,6 +411,15 @@ class ScriptRunner:
                 print(f"Error running process: {script.filename}", file=sys.stderr)
                 print(traceback.format_exc(), file=sys.stderr)
 
+    def before_process_batch(self, p, **kwargs):
+        for script in self.alwayson_scripts:
+            try:
+                script_args = p.script_args[script.args_from:script.args_to]
+                script.before_process_batch(p, *script_args, **kwargs)
+            except Exception:
+                print(f"Error running before_process_batch: {script.filename}", file=sys.stderr)
+                print(traceback.format_exc(), file=sys.stderr)
+
     def process_batch(self, p, **kwargs):
         for script in self.alwayson_scripts:
             try:

modules/sd_hijack.py

@@ -37,11 +37,23 @@ def apply_optimizations():
     
     optimization_method = None
 
+    can_use_sdp = hasattr(torch.nn.functional, "scaled_dot_product_attention") and callable(getattr(torch.nn.functional, "scaled_dot_product_attention")) # not everyone has torch 2.x to use sdp
+
     if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)):
         print("Applying xformers cross attention optimization.")
         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
         ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
         optimization_method = 'xformers'
+    elif cmd_opts.opt_sdp_no_mem_attention and can_use_sdp:
+        print("Applying scaled dot product cross attention optimization (without memory efficient attention).")
+        ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.scaled_dot_product_no_mem_attention_forward
+        ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.sdp_no_mem_attnblock_forward
+        optimization_method = 'sdp-no-mem'
+    elif cmd_opts.opt_sdp_attention and can_use_sdp:
+        print("Applying scaled dot product cross attention optimization.")
+        ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.scaled_dot_product_attention_forward
+        ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.sdp_attnblock_forward
+        optimization_method = 'sdp'
     elif cmd_opts.opt_sub_quad_attention:
         print("Applying sub-quadratic cross attention optimization.")
         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.sub_quad_attention_forward

modules/sd_hijack_optimizations.py

@@ -346,6 +346,52 @@ def xformers_attention_forward(self, x, context=None, mask=None):
     out = rearrange(out, 'b n h d -> b n (h d)', h=h)
     return self.to_out(out)
 
+# Based on Diffusers usage of scaled dot product attention from https://github.com/huggingface/diffusers/blob/c7da8fd23359a22d0df2741688b5b4f33c26df21/src/diffusers/models/cross_attention.py
+# The scaled_dot_product_attention_forward function contains parts of code under Apache-2.0 license listed under Scaled Dot Product Attention in the Licenses section of the web UI interface
+def scaled_dot_product_attention_forward(self, x, context=None, mask=None):
+    batch_size, sequence_length, inner_dim = x.shape
+
+    if mask is not None:
+        mask = self.prepare_attention_mask(mask, sequence_length, batch_size)
+        mask = mask.view(batch_size, self.heads, -1, mask.shape[-1])
+
+    h = self.heads
+    q_in = self.to_q(x)
+    context = default(context, x)
+
+    context_k, context_v = hypernetwork.apply_hypernetworks(shared.loaded_hypernetworks, context)
+    k_in = self.to_k(context_k)
+    v_in = self.to_v(context_v)
+
+    head_dim = inner_dim // h
+    q = q_in.view(batch_size, -1, h, head_dim).transpose(1, 2)
+    k = k_in.view(batch_size, -1, h, head_dim).transpose(1, 2)
+    v = v_in.view(batch_size, -1, h, head_dim).transpose(1, 2)
+    
+    del q_in, k_in, v_in
+
+    dtype = q.dtype
+    if shared.opts.upcast_attn:
+        q, k = q.float(), k.float()
+
+    # the output of sdp = (batch, num_heads, seq_len, head_dim)
+    hidden_states = torch.nn.functional.scaled_dot_product_attention(
+        q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False
+    )
+
+    hidden_states = hidden_states.transpose(1, 2).reshape(batch_size, -1, h * head_dim)
+    hidden_states = hidden_states.to(dtype)
+
+    # linear proj
+    hidden_states = self.to_out[0](hidden_states)
+    # dropout
+    hidden_states = self.to_out[1](hidden_states)
+    return hidden_states
+
+def scaled_dot_product_no_mem_attention_forward(self, x, context=None, mask=None):
+    with torch.backends.cuda.sdp_kernel(enable_flash=True, enable_math=True, enable_mem_efficient=False):
+        return scaled_dot_product_attention_forward(self, x, context, mask)
+
 def cross_attention_attnblock_forward(self, x):
         h_ = x
         h_ = self.norm(h_)
@@ -427,6 +473,30 @@ def xformers_attnblock_forward(self, x):
     except NotImplementedError:
         return cross_attention_attnblock_forward(self, x)
 
+def sdp_attnblock_forward(self, x):
+    h_ = x
+    h_ = self.norm(h_)
+    q = self.q(h_)
+    k = self.k(h_)
+    v = self.v(h_)
+    b, c, h, w = q.shape
+    q, k, v = map(lambda t: rearrange(t, 'b c h w -> b (h w) c'), (q, k, v))
+    dtype = q.dtype
+    if shared.opts.upcast_attn:
+        q, k = q.float(), k.float()
+    q = q.contiguous()
+    k = k.contiguous()
+    v = v.contiguous()
+    out = torch.nn.functional.scaled_dot_product_attention(q, k, v, dropout_p=0.0, is_causal=False)
+    out = out.to(dtype)
+    out = rearrange(out, 'b (h w) c -> b c h w', h=h)
+    out = self.proj_out(out)
+    return x + out
+
+def sdp_no_mem_attnblock_forward(self, x):
+    with torch.backends.cuda.sdp_kernel(enable_flash=True, enable_math=True, enable_mem_efficient=False):
+        return sdp_attnblock_forward(self, x)
+
 def sub_quad_attnblock_forward(self, x):
     h_ = x
     h_ = self.norm(h_)

modules/sd_samplers.py

@@ -32,7 +32,7 @@ def set_samplers():
     global samplers, samplers_for_img2img
 
     hidden = set(shared.opts.hide_samplers)
-    hidden_img2img = set(shared.opts.hide_samplers + ['PLMS'])
+    hidden_img2img = set(shared.opts.hide_samplers + ['PLMS', 'UniPC'])
 
     samplers = [x for x in all_samplers if x.name not in hidden]
     samplers_for_img2img = [x for x in all_samplers if x.name not in hidden_img2img]

modules/sd_samplers_compvis.py

@@ -7,19 +7,27 @@ import torch
 
 from modules.shared import state
 from modules import sd_samplers_common, prompt_parser, shared
+import modules.models.diffusion.uni_pc
 
 
 samplers_data_compvis = [
     sd_samplers_common.SamplerData('DDIM', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {}),
     sd_samplers_common.SamplerData('PLMS', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.plms.PLMSSampler, model), [], {}),
+    sd_samplers_common.SamplerData('UniPC', lambda model: VanillaStableDiffusionSampler(modules.models.diffusion.uni_pc.UniPCSampler, model), [], {}),
 ]
 
 
 class VanillaStableDiffusionSampler:
     def __init__(self, constructor, sd_model):
         self.sampler = constructor(sd_model)
+        self.is_ddim = hasattr(self.sampler, 'p_sample_ddim')
         self.is_plms = hasattr(self.sampler, 'p_sample_plms')
-        self.orig_p_sample_ddim = self.sampler.p_sample_plms if self.is_plms else self.sampler.p_sample_ddim
+        self.is_unipc = isinstance(self.sampler, modules.models.diffusion.uni_pc.UniPCSampler)
+        self.orig_p_sample_ddim = None
+        if self.is_plms:
+            self.orig_p_sample_ddim = self.sampler.p_sample_plms
+        elif self.is_ddim:
+            self.orig_p_sample_ddim = self.sampler.p_sample_ddim
         self.mask = None
         self.nmask = None
         self.init_latent = None
@@ -45,6 +53,15 @@ class VanillaStableDiffusionSampler:
             return self.last_latent
 
     def p_sample_ddim_hook(self, x_dec, cond, ts, unconditional_conditioning, *args, **kwargs):
+        x_dec, ts, cond, unconditional_conditioning = self.before_sample(x_dec, ts, cond, unconditional_conditioning)
+
+        res = self.orig_p_sample_ddim(x_dec, cond, ts, unconditional_conditioning=unconditional_conditioning, *args, **kwargs)
+
+        x_dec, ts, cond, unconditional_conditioning, res = self.after_sample(x_dec, ts, cond, unconditional_conditioning, res)
+
+        return res
+
+    def before_sample(self, x, ts, cond, unconditional_conditioning):
         if state.interrupted or state.skipped:
             raise sd_samplers_common.InterruptedException
 
@@ -76,7 +93,7 @@ class VanillaStableDiffusionSampler:
 
         if self.mask is not None:
             img_orig = self.sampler.model.q_sample(self.init_latent, ts)
-            x_dec = img_orig * self.mask + self.nmask * x_dec
+            x = img_orig * self.mask + self.nmask * x
 
         # 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.
@@ -84,12 +101,13 @@ class VanillaStableDiffusionSampler:
             cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]}
             unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
 
-        res = self.orig_p_sample_ddim(x_dec, cond, ts, unconditional_conditioning=unconditional_conditioning, *args, **kwargs)
+        return x, ts, cond, unconditional_conditioning
 
+    def update_step(self, last_latent):
         if self.mask is not None:
-            self.last_latent = self.init_latent * self.mask + self.nmask * res[1]
+            self.last_latent = self.init_latent * self.mask + self.nmask * last_latent
         else:
-            self.last_latent = res[1]
+            self.last_latent = last_latent
 
         sd_samplers_common.store_latent(self.last_latent)
 
@@ -97,26 +115,51 @@ class VanillaStableDiffusionSampler:
         state.sampling_step = self.step
         shared.total_tqdm.update()
 
-        return res
+    def after_sample(self, x, ts, cond, uncond, res):
+        if not self.is_unipc:
+            self.update_step(res[1])
+
+        return x, ts, cond, uncond, res
+
+    def unipc_after_update(self, x, model_x):
+        self.update_step(x)
 
     def initialize(self, p):
         self.eta = p.eta if p.eta is not None else shared.opts.eta_ddim
         if self.eta != 0.0:
             p.extra_generation_params["Eta DDIM"] = self.eta
 
+        if self.is_unipc:
+            keys = [
+                ('UniPC variant', 'uni_pc_variant'),
+                ('UniPC skip type', 'uni_pc_skip_type'),
+                ('UniPC order', 'uni_pc_order'),
+                ('UniPC lower order final', 'uni_pc_lower_order_final'),
+            ]
+
+            for name, key in keys:
+                v = getattr(shared.opts, key)
+                if v != shared.opts.get_default(key):
+                    p.extra_generation_params[name] = v
+
         for fieldname in ['p_sample_ddim', 'p_sample_plms']:
             if hasattr(self.sampler, fieldname):
                 setattr(self.sampler, fieldname, self.p_sample_ddim_hook)
+        if self.is_unipc:
+            self.sampler.set_hooks(lambda x, t, c, u: self.before_sample(x, t, c, u), lambda x, t, c, u, r: self.after_sample(x, t, c, u, r), lambda x, mx: self.unipc_after_update(x, mx))
 
         self.mask = p.mask if hasattr(p, 'mask') else None
         self.nmask = p.nmask if hasattr(p, 'nmask') else None
 
+
     def adjust_steps_if_invalid(self, p, num_steps):
-        if (self.config.name == 'DDIM' and p.ddim_discretize == 'uniform') or (self.config.name == 'PLMS'):
+        if ((self.config.name == 'DDIM') and p.ddim_discretize == 'uniform') or (self.config.name == 'PLMS') or (self.config.name == 'UniPC'):
+            if self.config.name == 'UniPC' and num_steps < shared.opts.uni_pc_order:
+                num_steps = shared.opts.uni_pc_order
             valid_step = 999 / (1000 // num_steps)
             if valid_step == math.floor(valid_step):
                 return int(valid_step) + 1
-        
+
         return num_steps
 
     def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):

modules/sd_samplers_kdiffusion.py

@@ -101,11 +101,13 @@ class CFGDenoiser(torch.nn.Module):
             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)])
 
-        denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)
+        denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps, tensor, uncond)
         cfg_denoiser_callback(denoiser_params)
         x_in = denoiser_params.x
         image_cond_in = denoiser_params.image_cond
         sigma_in = denoiser_params.sigma
+        tensor = denoiser_params.text_cond
+        uncond = denoiser_params.text_uncond
 
         if tensor.shape[1] == uncond.shape[1]:
             if not is_edit_model:

modules/shared.py

@@ -69,6 +69,8 @@ parser.add_argument("--sub-quad-kv-chunk-size", type=int, help="kv chunk size fo
 parser.add_argument("--sub-quad-chunk-threshold", type=int, help="the percentage of VRAM threshold for the sub-quadratic cross-attention layer optimization to use chunking", default=None)
 parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
 parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
+parser.add_argument("--opt-sdp-attention", action='store_true', help="enable scaled dot product cross-attention layer optimization; requires PyTorch 2.*")
+parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="enable scaled dot product cross-attention layer optimization without memory efficient attention, makes image generation deterministic; requires PyTorch 2.*")
 parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
 parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
 parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
@@ -305,6 +307,7 @@ def list_samplers():
 
 
 hide_dirs = {"visible": not cmd_opts.hide_ui_dir_config}
+tab_names = []
 
 options_templates = {}
 
@@ -327,9 +330,11 @@ 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}),
+    "webp_lossless": OptionInfo(False, "Use lossless compression for webp images"),
     "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),
+    "img_max_size_mp": OptionInfo(200, "Maximum image size, in megapixels", 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"),
@@ -440,6 +445,7 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"),
 options_templates.update(options_section(('extra_networks', "Extra Networks"), {
     "extra_networks_default_view": OptionInfo("cards", "Default view for Extra Networks", gr.Dropdown, {"choices": ["cards", "thumbs"]}),
     "extra_networks_default_multiplier": OptionInfo(1.0, "Multiplier for extra networks", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
+    "extra_networks_add_text_separator": OptionInfo(" ", "Extra text to add before <...> when adding extra network to prompt"),
     "sd_hypernetwork": OptionInfo("None", "Add hypernetwork to prompt", gr.Dropdown, lambda: {"choices": [""] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks),
 }))
 
@@ -460,6 +466,7 @@ options_templates.update(options_section(('ui', "User interface"), {
     "keyedit_precision_attention": OptionInfo(0.1, "Ctrl+up/down precision when editing (attention:1.1)", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
     "keyedit_precision_extra": OptionInfo(0.05, "Ctrl+up/down precision when editing <extra networks:0.9>", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
     "quicksettings": OptionInfo("sd_model_checkpoint", "Quicksettings list"),
+    "hidden_tabs": OptionInfo([], "Hidden UI tabs (requires restart)", ui_components.DropdownMulti, lambda: {"choices": [x for x in tab_names]}),
     "ui_reorder": OptionInfo(", ".join(ui_reorder_categories), "txt2img/img2img UI item order"),
     "ui_extra_networks_tab_reorder": OptionInfo("", "Extra networks tab order"),
     "localization": OptionInfo("None", "Localization (requires restart)", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)),
@@ -485,6 +492,10 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters"
     's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
     'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}),
     'always_discard_next_to_last_sigma': OptionInfo(False, "Always discard next-to-last sigma"),
+    'uni_pc_variant': OptionInfo("bh1", "UniPC variant", gr.Radio, {"choices": ["bh1", "bh2", "vary_coeff"]}),
+    'uni_pc_skip_type': OptionInfo("time_uniform", "UniPC skip type", gr.Radio, {"choices": ["time_uniform", "time_quadratic", "logSNR"]}),
+    'uni_pc_order': OptionInfo(3, "UniPC order (must be < sampling steps)", gr.Slider, {"minimum": 1, "maximum": 50, "step": 1}),
+    'uni_pc_lower_order_final': OptionInfo(True, "UniPC lower order final"),
 }))
 
 options_templates.update(options_section(('postprocessing', "Postprocessing"), {
@@ -559,6 +570,15 @@ class Options:
 
         return True
 
+    def get_default(self, key):
+        """returns the default value for the key"""
+
+        data_label = self.data_labels.get(key)
+        if data_label is None:
+            return None
+
+        return data_label.default
+
     def save(self, filename):
         assert not cmd_opts.freeze_settings, "saving settings is disabled"
 

modules/ui.py

@@ -939,7 +939,7 @@ def create_ui():
                 )
 
             token_button.click(fn=update_token_counter, inputs=[img2img_prompt, steps], outputs=[token_counter])
-            negative_token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[txt2img_negative_prompt, steps], outputs=[negative_token_counter])
+            negative_token_button.click(fn=wrap_queued_call(update_token_counter), inputs=[img2img_negative_prompt, steps], outputs=[negative_token_counter])
 
             ui_extra_networks.setup_ui(extra_networks_ui_img2img, img2img_gallery)
 
@@ -1563,6 +1563,10 @@ def create_ui():
     extensions_interface = ui_extensions.create_ui()
     interfaces += [(extensions_interface, "Extensions", "extensions")]
 
+    shared.tab_names = []
+    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.Row(elem_id="quicksettings", variant="compact"):
             for i, k, item in sorted(quicksettings_list, key=lambda x: quicksettings_names.get(x[1], x[0])):
@@ -1573,6 +1577,8 @@ def create_ui():
 
         with gr.Tabs(elem_id="tabs") as tabs:
             for interface, label, ifid in interfaces:
+                if label in shared.opts.hidden_tabs:
+                    continue
                 with gr.TabItem(label, id=ifid, elem_id='tab_' + ifid):
                     interface.render()
 
@@ -1754,6 +1760,9 @@ def reload_javascript():
     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'
 
+    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="text/javascript">{inline}</script>\n'
 
     def template_response(*args, **kwargs):

modules/ui_common.py

@@ -198,9 +198,16 @@ Requested path was: {f}
                 html_info = gr.HTML(elem_id=f'html_info_{tabname}')
                 html_log = gr.HTML(elem_id=f'html_log_{tabname}')
 
+            paste_field_names = []
+            if tabname == "txt2img":
+                paste_field_names = modules.scripts.scripts_txt2img.paste_field_names
+            elif tabname == "img2img":
+                paste_field_names = modules.scripts.scripts_img2img.paste_field_names
+
             for paste_tabname, paste_button in buttons.items():
                 parameters_copypaste.register_paste_params_button(parameters_copypaste.ParamBinding(
-                    paste_button=paste_button, tabname=paste_tabname, source_tabname="txt2img" if tabname == "txt2img" else None, source_image_component=result_gallery
+                    paste_button=paste_button, tabname=paste_tabname, source_tabname="txt2img" if tabname == "txt2img" else None, source_image_component=result_gallery,
+                    paste_field_names=paste_field_names
                 ))
 
             return result_gallery, generation_info if tabname != "extras" else html_info_x, html_info, html_log

modules/ui_extra_networks.py

@@ -130,6 +130,7 @@ class ExtraNetworksPage:
             "tabname": json.dumps(tabname),
             "local_preview": json.dumps(item["local_preview"]),
             "name": item["name"],
+            "description": (item.get("description") or ""),
             "card_clicked": onclick,
             "save_card_preview": '"' + html.escape(f"""return saveCardPreview(event, {json.dumps(tabname)}, {json.dumps(item["local_preview"])})""") + '"',
             "search_term": item.get("search_term", ""),
@@ -137,6 +138,35 @@ class ExtraNetworksPage:
 
         return self.card_page.format(**args)
 
+    def find_preview(self, path):
+        """
+        Find a preview PNG for a given path (without extension) and call link_preview on it.
+        """
+
+        preview_extensions = ["png", "jpg", "webp"]
+        if shared.opts.samples_format not in preview_extensions:
+            preview_extensions.append(shared.opts.samples_format)
+
+        potential_files = sum([[path + "." + ext, path + ".preview." + ext] for ext in preview_extensions], [])
+
+        for file in potential_files:
+            if os.path.isfile(file):
+                return self.link_preview(file)
+
+        return None
+
+    def find_description(self, path):
+        """
+        Find and read a description file for a given path (without extension).
+        """
+        for file in [f"{path}.txt", f"{path}.description.txt"]:
+            try:
+                with open(file, "r", encoding="utf-8", errors="replace") as f:
+                    return f.read()
+            except OSError:
+                pass
+        return None
+
 
 def intialize():
     extra_pages.clear()

modules/ui_extra_networks_checkpoints.py

 import html
 import json
 import os
-import urllib.parse
 
 from modules import shared, ui_extra_networks, sd_models
 
@@ -17,21 +16,14 @@ class ExtraNetworksPageCheckpoints(ui_extra_networks.ExtraNetworksPage):
         checkpoint: sd_models.CheckpointInfo
         for name, checkpoint in sd_models.checkpoints_list.items():
             path, ext = os.path.splitext(checkpoint.filename)
-            previews = [path + ".png", path + ".preview.png"]
-
-            preview = None
-            for file in previews:
-                if os.path.isfile(file):
-                    preview = self.link_preview(file)
-                    break
-
             yield {
                 "name": checkpoint.name_for_extra,
                 "filename": path,
-                "preview": preview,
+                "preview": self.find_preview(path),
+                "description": self.find_description(path),
                 "search_term": self.search_terms_from_path(checkpoint.filename) + " " + (checkpoint.sha256 or ""),
                 "onclick": '"' + html.escape(f"""return selectCheckpoint({json.dumps(name)})""") + '"',
-                "local_preview": path + ".png",
+                "local_preview": f"{path}.{shared.opts.samples_format}",
             }
 
     def allowed_directories_for_previews(self):

modules/ui_extra_networks_hypernets.py

@@ -14,21 +14,15 @@ class ExtraNetworksPageHypernetworks(ui_extra_networks.ExtraNetworksPage):
     def list_items(self):
         for name, path in shared.hypernetworks.items():
             path, ext = os.path.splitext(path)
-            previews = [path + ".png", path + ".preview.png"]
-
-            preview = None
-            for file in previews:
-                if os.path.isfile(file):
-                    preview = self.link_preview(file)
-                    break
 
             yield {
                 "name": name,
                 "filename": path,
-                "preview": preview,
+                "preview": self.find_preview(path),
+                "description": self.find_description(path),
                 "search_term": self.search_terms_from_path(path),
                 "prompt": json.dumps(f"<hypernet:{name}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
-                "local_preview": path + ".png",
+                "local_preview": f"{path}.preview.{shared.opts.samples_format}",
             }
 
     def allowed_directories_for_previews(self):

modules/ui_extra_networks_textual_inversion.py

 import json
 import os
 
-from modules import ui_extra_networks, sd_hijack
+from modules import ui_extra_networks, sd_hijack, shared
 
 
 class ExtraNetworksPageTextualInversion(ui_extra_networks.ExtraNetworksPage):
@@ -15,19 +15,14 @@ class ExtraNetworksPageTextualInversion(ui_extra_networks.ExtraNetworksPage):
     def list_items(self):
         for embedding in sd_hijack.model_hijack.embedding_db.word_embeddings.values():
             path, ext = os.path.splitext(embedding.filename)
-            preview_file = path + ".preview.png"
-
-            preview = None
-            if os.path.isfile(preview_file):
-                preview = self.link_preview(preview_file)
-
             yield {
                 "name": embedding.name,
                 "filename": embedding.filename,
-                "preview": preview,
+                "preview": self.find_preview(path),
+                "description": self.find_description(path),
                 "search_term": self.search_terms_from_path(embedding.filename),
                 "prompt": json.dumps(embedding.name),
-                "local_preview": path + ".preview.png",
+                "local_preview": f"{path}.preview.{shared.opts.samples_format}",
             }
 
     def allowed_directories_for_previews(self):

requirements_versions.txt

@@ -23,7 +23,7 @@ torchdiffeq==0.2.3
 kornia==0.6.7
 lark==1.1.2
 inflection==0.5.1
-GitPython==3.1.27
+GitPython==3.1.30
 torchsde==0.2.5
 safetensors==0.2.7
 httpcore<=0.15

scripts/prompt_matrix.py

@@ -100,7 +100,7 @@ class Script(scripts.Script):
         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, processed.images[0].width, processed.images[1].height, prompt_matrix_parts, margin_size)
+        grid = images.draw_prompt_matrix(grid, processed.images[0].width, processed.images[0].height, prompt_matrix_parts, margin_size)
         processed.images.insert(0, grid)
         processed.index_of_first_image = 1
         processed.infotexts.insert(0, processed.infotexts[0])

style.css

@@ -856,7 +856,7 @@ footer {
 }
 
 .extra-network-thumbs .card:hover .additional a {
-    display: block;
+    display: inline-block;
 }
 
 .extra-network-thumbs .actions .additional a {
@@ -939,6 +939,17 @@ footer {
     line-break: anywhere;
 }
 
+.extra-network-cards .card .actions .description {
+    display: block;
+    max-height: 3em;
+    white-space: pre-wrap;
+    line-height: 1.1;
+}
+
+.extra-network-cards .card .actions .description:hover {
+    max-height: none;
+}
+
 .extra-network-cards .card .actions:hover .additional{
     display: block;
 }

test/basic_features/txt2img_test.py

@@ -66,6 +66,8 @@ class TestTxt2ImgWorking(unittest.TestCase):
         self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
         self.simple_txt2img["sampler_index"] = "DDIM"
         self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
+        self.simple_txt2img["sampler_index"] = "UniPC"
+        self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
 
     def test_txt2img_multiple_batches_performed(self):
         self.simple_txt2img["n_iter"] = 2

webui.py

@@ -12,11 +12,22 @@ from packaging import version
 import logging
 logging.getLogger("xformers").addFilter(lambda record: 'A matching Triton is not available' not in record.getMessage())
 
-from modules import import_hook, errors, extra_networks, ui_extra_networks_checkpoints
-from modules import extra_networks_hypernet, ui_extra_networks_hypernets, ui_extra_networks_textual_inversion
-from modules.call_queue import wrap_queued_call, queue_lock, wrap_gradio_gpu_call
+from modules import paths, timer, import_hook, errors
+
+startup_timer = timer.Timer()
 
 import torch
+startup_timer.record("import torch")
+
+import gradio
+startup_timer.record("import gradio")
+
+import ldm.modules.encoders.modules
+startup_timer.record("import ldm")
+
+from modules import extra_networks, ui_extra_networks_checkpoints
+from modules import extra_networks_hypernet, ui_extra_networks_hypernets, ui_extra_networks_textual_inversion
+from modules.call_queue import wrap_queued_call, queue_lock, wrap_gradio_gpu_call
 
 # 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__:
@@ -30,7 +41,6 @@ import modules.gfpgan_model as gfpgan
 import modules.img2img
 
 import modules.lowvram
-import modules.paths
 import modules.scripts
 import modules.sd_hijack
 import modules.sd_models
@@ -45,6 +55,8 @@ from modules import modelloader
 from modules.shared import cmd_opts
 import modules.hypernetworks.hypernetwork
 
+startup_timer.record("other imports")
+
 
 if cmd_opts.server_name:
     server_name = cmd_opts.server_name
@@ -88,6 +100,7 @@ def initialize():
 
     extensions.list_extensions()
     localization.list_localizations(cmd_opts.localizations_dir)
+    startup_timer.record("list extensions")
 
     if cmd_opts.ui_debug_mode:
         shared.sd_upscalers = upscaler.UpscalerLanczos().scalers
@@ -96,16 +109,28 @@ def initialize():
 
     modelloader.cleanup_models()
     modules.sd_models.setup_model()
+    startup_timer.record("list SD models")
+
     codeformer.setup_model(cmd_opts.codeformer_models_path)
+    startup_timer.record("setup codeformer")
+
     gfpgan.setup_model(cmd_opts.gfpgan_models_path)
+    startup_timer.record("setup gfpgan")
 
     modelloader.list_builtin_upscalers()
+    startup_timer.record("list builtin upscalers")
+
     modules.scripts.load_scripts()
+    startup_timer.record("load scripts")
+
     modelloader.load_upscalers()
+    startup_timer.record("load upscalers")
 
     modules.sd_vae.refresh_vae_list()
+    startup_timer.record("refresh VAE")
 
     modules.textual_inversion.textual_inversion.list_textual_inversion_templates()
+    startup_timer.record("refresh textual inversion templates")
 
     try:
         modules.sd_models.load_model()
@@ -114,6 +139,7 @@ def initialize():
         print("", file=sys.stderr)
         print("Stable diffusion model failed to load, exiting", file=sys.stderr)
         exit(1)
+    startup_timer.record("load SD checkpoint")
 
     shared.opts.data["sd_model_checkpoint"] = shared.sd_model.sd_checkpoint_info.title
 
@@ -121,8 +147,10 @@ def initialize():
     shared.opts.onchange("sd_vae", wrap_queued_call(lambda: modules.sd_vae.reload_vae_weights()), call=False)
     shared.opts.onchange("sd_vae_as_default", wrap_queued_call(lambda: modules.sd_vae.reload_vae_weights()), call=False)
     shared.opts.onchange("temp_dir", ui_tempdir.on_tmpdir_changed)
+    startup_timer.record("opts onchange")
 
     shared.reload_hypernetworks()
+    startup_timer.record("reload hypernets")
 
     ui_extra_networks.intialize()
     ui_extra_networks.register_page(ui_extra_networks_textual_inversion.ExtraNetworksPageTextualInversion())
@@ -131,6 +159,7 @@ def initialize():
 
     extra_networks.initialize()
     extra_networks.register_extra_network(extra_networks_hypernet.ExtraNetworkHypernet())
+    startup_timer.record("extra networks")
 
     if cmd_opts.tls_keyfile is not None and cmd_opts.tls_keyfile is not None:
 
@@ -144,6 +173,7 @@ def initialize():
             print("TLS setup invalid, running webui without TLS")
         else:
             print("Running with TLS")
+        startup_timer.record("TLS")
 
     # make the program just exit at ctrl+c without waiting for anything
     def sigint_handler(sig, frame):
@@ -189,6 +219,7 @@ def api_only():
 
     modules.script_callbacks.app_started_callback(None, app)
 
+    print(f"Startup time: {startup_timer.summary()}.")
     api.launch(server_name="0.0.0.0" if cmd_opts.listen else "127.0.0.1", port=cmd_opts.port if cmd_opts.port else 7861)
 
 
@@ -199,21 +230,24 @@ def webui():
     while 1:
         if shared.opts.clean_temp_dir_at_start:
             ui_tempdir.cleanup_tmpdr()
+            startup_timer.record("cleanup temp dir")
 
         modules.script_callbacks.before_ui_callback()
+        startup_timer.record("scripts before_ui_callback")
 
         shared.demo = modules.ui.create_ui()
+        startup_timer.record("create ui")
 
         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(',')
+            gradio_auth_creds += [x.strip() for x in cmd_opts.gradio_auth.strip('"').replace('\n', '').split(',') if x.strip()]
         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(',')]
+                    gradio_auth_creds += [x.strip() for x in line.split(',') if x.strip()]
 
         app, local_url, share_url = shared.demo.launch(
             share=cmd_opts.share,
@@ -229,6 +263,8 @@ def webui():
         # after initial launch, disable --autolaunch for subsequent restarts
         cmd_opts.autolaunch = False
 
+        startup_timer.record("gradio launch")
+
         # gradio uses a very open CORS policy via app.user_middleware, which makes it possible for
         # an attacker to trick the user into opening a malicious HTML page, which makes a request to the
         # running web ui and do whatever the attacker wants, including installing an extension and
@@ -247,6 +283,9 @@ def webui():
         ui_extra_networks.add_pages_to_demo(app)
 
         modules.script_callbacks.app_started_callback(shared.demo, app)
+        startup_timer.record("scripts app_started_callback")
+
+        print(f"Startup time: {startup_timer.summary()}.")
 
         wait_on_server(shared.demo)
         print('Restarting UI...')