Merge branch 'master' into img2img-enhance

README.md

@@ -13,9 +13,9 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Prompt Matrix
 - Stable Diffusion Upscale
 - Attention, specify parts of text that the model should pay more attention to
-    - a man in a ((tuxedo)) - will pay more attention to tuxedo
+    - a man in a `((tuxedo))` - will pay more attention to tuxedo
-    - a man in a (tuxedo:1.21) - alternative syntax
+    - a man in a `(tuxedo:1.21)` - alternative syntax
-    - select text and press ctrl+up or ctrl+down to automatically adjust attention to selected text (code contributed by anonymous user)
+    - select text and press `Ctrl+Up` or `Ctrl+Down` to automatically adjust attention to selected text (code contributed by anonymous user)
 - Loopback, run img2img processing multiple times
 - X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
 - Textual Inversion
@@ -28,7 +28,7 @@ A browser interface based on Gradio library for Stable Diffusion.
     - CodeFormer, face restoration tool as an alternative to GFPGAN
     - RealESRGAN, neural network upscaler
     - ESRGAN, neural network upscaler with a lot of third party models
-    - SwinIR and Swin2SR([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers
+    - SwinIR and Swin2SR ([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers
     - LDSR, Latent diffusion super resolution upscaling
 - Resizing aspect ratio options
 - Sampling method selection
@@ -46,7 +46,7 @@ A browser interface based on Gradio library for Stable Diffusion.
      - drag and drop an image/text-parameters to promptbox
 - Read Generation Parameters Button, loads parameters in promptbox to UI
 - Settings page
-- Running arbitrary python code from UI (must run with --allow-code to enable)
+- Running arbitrary python code from UI (must run with `--allow-code` to enable)
 - Mouseover hints for most UI elements
 - Possible to change defaults/mix/max/step values for UI elements via text config
 - Tiling support, a checkbox to create images that can be tiled like textures
@@ -69,7 +69,7 @@ A browser interface based on Gradio library for Stable Diffusion.
      - also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
 - No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
 - DeepDanbooru integration, creates danbooru style tags for anime prompts
-- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args)
+- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add `--xformers` to commandline args)
 - via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI
 - Generate forever option
 - Training tab
@@ -78,11 +78,11 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Clip skip
 - Hypernetworks
 - Loras (same as Hypernetworks but more pretty)
-- A sparate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt. 
+- A sparate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt 
 - Can select to load a different VAE from settings screen
 - Estimated completion time in progress bar
 - API
-- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML.
+- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML
 - via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embeds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
 - [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions
 - [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
@@ -91,7 +91,6 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Eased resolution restriction: generated image's domension must be a multiple of 8 rather than 64
 - Now with a license!
 - Reorder elements in the UI from settings screen
-- 
 
 ## Installation and Running
 Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
@@ -101,7 +100,7 @@ Alternatively, use online services (like Google Colab):
 - [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
 
 ### Automatic Installation on Windows
-1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH"
+1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH".
 2. Install [git](https://git-scm.com/download/win).
 3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.
 4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.

extensions-builtin/Lora/lora.py

@@ -2,20 +2,34 @@ import glob
 import os
 import re
 import torch
+from typing import Union
 
 from modules import shared, devices, sd_models, errors
 
 metadata_tags_order = {"ss_sd_model_name": 1, "ss_resolution": 2, "ss_clip_skip": 3, "ss_num_train_images": 10, "ss_tag_frequency": 20}
 
 re_digits = re.compile(r"\d+")
-re_unet_down_blocks = re.compile(r"lora_unet_down_blocks_(\d+)_attentions_(\d+)_(.+)")
+re_x_proj = re.compile(r"(.*)_([qkv]_proj)$")
-re_unet_mid_blocks = re.compile(r"lora_unet_mid_block_attentions_(\d+)_(.+)")
+re_compiled = {}
-re_unet_up_blocks = re.compile(r"lora_unet_up_blocks_(\d+)_attentions_(\d+)_(.+)")
+
-re_text_block = re.compile(r"lora_te_text_model_encoder_layers_(\d+)_(.+)")
+suffix_conversion = {
+    "attentions": {},
+    "resnets": {
+        "conv1": "in_layers_2",
+        "conv2": "out_layers_3",
+        "time_emb_proj": "emb_layers_1",
+        "conv_shortcut": "skip_connection",
+    }
+}
 
 
-def convert_diffusers_name_to_compvis(key):
+def convert_diffusers_name_to_compvis(key, is_sd2):
-    def match(match_list, regex):
+    def match(match_list, regex_text):
+        regex = re_compiled.get(regex_text)
+        if regex is None:
+            regex = re.compile(regex_text)
+            re_compiled[regex_text] = regex
+
         r = re.match(regex, key)
         if not r:
             return False
@@ -26,16 +40,33 @@ def convert_diffusers_name_to_compvis(key):
 
     m = []
 
-    if match(m, re_unet_down_blocks):
+    if match(m, r"lora_unet_down_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
-        return f"diffusion_model_input_blocks_{1 + m[0] * 3 + m[1]}_1_{m[2]}"
+        suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
+        return f"diffusion_model_input_blocks_{1 + m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
 
-    if match(m, re_unet_mid_blocks):
+    if match(m, r"lora_unet_mid_block_(attentions|resnets)_(\d+)_(.+)"):
-        return f"diffusion_model_middle_block_1_{m[1]}"
+        suffix = suffix_conversion.get(m[0], {}).get(m[2], m[2])
+        return f"diffusion_model_middle_block_{1 if m[0] == 'attentions' else m[1] * 2}_{suffix}"
 
-    if match(m, re_unet_up_blocks):
+    if match(m, r"lora_unet_up_blocks_(\d+)_(attentions|resnets)_(\d+)_(.+)"):
-        return f"diffusion_model_output_blocks_{m[0] * 3 + m[1]}_1_{m[2]}"
+        suffix = suffix_conversion.get(m[1], {}).get(m[3], m[3])
+        return f"diffusion_model_output_blocks_{m[0] * 3 + m[2]}_{1 if m[1] == 'attentions' else 0}_{suffix}"
+
+    if match(m, r"lora_unet_down_blocks_(\d+)_downsamplers_0_conv"):
+        return f"diffusion_model_input_blocks_{3 + m[0] * 3}_0_op"
+
+    if match(m, r"lora_unet_up_blocks_(\d+)_upsamplers_0_conv"):
+        return f"diffusion_model_output_blocks_{2 + m[0] * 3}_{2 if m[0]>0 else 1}_conv"
+
+    if match(m, r"lora_te_text_model_encoder_layers_(\d+)_(.+)"):
+        if is_sd2:
+            if 'mlp_fc1' in m[1]:
+                return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc1', 'mlp_c_fc')}"
+            elif 'mlp_fc2' in m[1]:
+                return f"model_transformer_resblocks_{m[0]}_{m[1].replace('mlp_fc2', 'mlp_c_proj')}"
+            else:
+                return f"model_transformer_resblocks_{m[0]}_{m[1].replace('self_attn', 'attn')}"
 
-    if match(m, re_text_block):
         return f"transformer_text_model_encoder_layers_{m[0]}_{m[1]}"
 
     return key
@@ -101,15 +132,22 @@ def load_lora(name, filename):
 
     sd = sd_models.read_state_dict(filename)
 
-    keys_failed_to_match = []
+    keys_failed_to_match = {}
+    is_sd2 = 'model_transformer_resblocks' in shared.sd_model.lora_layer_mapping
 
     for key_diffusers, weight in sd.items():
-        fullkey = convert_diffusers_name_to_compvis(key_diffusers)
+        key_diffusers_without_lora_parts, lora_key = key_diffusers.split(".", 1)
-        key, lora_key = fullkey.split(".", 1)
+        key = convert_diffusers_name_to_compvis(key_diffusers_without_lora_parts, is_sd2)
 
         sd_module = shared.sd_model.lora_layer_mapping.get(key, None)
+
         if sd_module is None:
-            keys_failed_to_match.append(key_diffusers)
+            m = re_x_proj.match(key)
+            if m:
+                sd_module = shared.sd_model.lora_layer_mapping.get(m.group(1), None)
+
+        if sd_module is None:
+            keys_failed_to_match[key_diffusers] = key
             continue
 
         lora_module = lora.modules.get(key, None)
@@ -123,15 +161,21 @@ def load_lora(name, filename):
 
         if type(sd_module) == torch.nn.Linear:
             module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
+        elif type(sd_module) == torch.nn.modules.linear.NonDynamicallyQuantizableLinear:
+            module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
+        elif type(sd_module) == torch.nn.MultiheadAttention:
+            module = torch.nn.Linear(weight.shape[1], weight.shape[0], bias=False)
         elif type(sd_module) == torch.nn.Conv2d:
             module = torch.nn.Conv2d(weight.shape[1], weight.shape[0], (1, 1), bias=False)
         else:
+            print(f'Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}')
+            continue
             assert False, f'Lora layer {key_diffusers} matched a layer with unsupported type: {type(sd_module).__name__}'
 
         with torch.no_grad():
             module.weight.copy_(weight)
 
-        module.to(device=devices.device, dtype=devices.dtype)
+        module.to(device=devices.cpu, dtype=devices.dtype)
 
         if lora_key == "lora_up.weight":
             lora_module.up = module
@@ -177,29 +221,120 @@ def load_loras(names, multipliers=None):
         loaded_loras.append(lora)
 
 
-def lora_forward(module, input, res):
+def lora_calc_updown(lora, module, target):
-    input = devices.cond_cast_unet(input)
+    with torch.no_grad():
-    if len(loaded_loras) == 0:
+        up = module.up.weight.to(target.device, dtype=target.dtype)
-        return res
+        down = module.down.weight.to(target.device, dtype=target.dtype)
+
+        if up.shape[2:] == (1, 1) and down.shape[2:] == (1, 1):
+            updown = (up.squeeze(2).squeeze(2) @ down.squeeze(2).squeeze(2)).unsqueeze(2).unsqueeze(3)
+        else:
+            updown = up @ down
+
+        updown = updown * lora.multiplier * (module.alpha / module.up.weight.shape[1] if module.alpha else 1.0)
+
+        return updown
+
+
+def lora_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.MultiheadAttention]):
+    """
+    Applies the currently selected set of Loras to the weights of torch layer self.
+    If weights already have this particular set of loras applied, does nothing.
+    If not, restores orginal weights from backup and alters weights according to loras.
+    """
+
+    lora_layer_name = getattr(self, 'lora_layer_name', None)
+    if lora_layer_name is None:
+        return
+
+    current_names = getattr(self, "lora_current_names", ())
+    wanted_names = tuple((x.name, x.multiplier) for x in loaded_loras)
+
+    weights_backup = getattr(self, "lora_weights_backup", None)
+    if weights_backup is None:
+        if isinstance(self, torch.nn.MultiheadAttention):
+            weights_backup = (self.in_proj_weight.to(devices.cpu, copy=True), self.out_proj.weight.to(devices.cpu, copy=True))
+        else:
+            weights_backup = self.weight.to(devices.cpu, copy=True)
+
+        self.lora_weights_backup = weights_backup
+
+    if current_names != wanted_names:
+        if weights_backup is not None:
+            if isinstance(self, torch.nn.MultiheadAttention):
+                self.in_proj_weight.copy_(weights_backup[0])
+                self.out_proj.weight.copy_(weights_backup[1])
+            else:
+                self.weight.copy_(weights_backup)
 
-    lora_layer_name = getattr(module, 'lora_layer_name', None)
         for lora in loaded_loras:
             module = lora.modules.get(lora_layer_name, None)
-        if module is not None:
+            if module is not None and hasattr(self, 'weight'):
-            if shared.opts.lora_apply_to_outputs and res.shape == input.shape:
+                self.weight += lora_calc_updown(lora, module, self.weight)
-                res = res + module.up(module.down(res)) * lora.multiplier * (module.alpha / module.up.weight.shape[1] if module.alpha else 1.0)
+                continue
-            else:
-                res = res + module.up(module.down(input)) * lora.multiplier * (module.alpha / module.up.weight.shape[1] if module.alpha else 1.0)
 
-    return res
+            module_q = lora.modules.get(lora_layer_name + "_q_proj", None)
+            module_k = lora.modules.get(lora_layer_name + "_k_proj", None)
+            module_v = lora.modules.get(lora_layer_name + "_v_proj", None)
+            module_out = lora.modules.get(lora_layer_name + "_out_proj", None)
+
+            if isinstance(self, torch.nn.MultiheadAttention) and module_q and module_k and module_v and module_out:
+                updown_q = lora_calc_updown(lora, module_q, self.in_proj_weight)
+                updown_k = lora_calc_updown(lora, module_k, self.in_proj_weight)
+                updown_v = lora_calc_updown(lora, module_v, self.in_proj_weight)
+                updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
+
+                self.in_proj_weight += updown_qkv
+                self.out_proj.weight += lora_calc_updown(lora, module_out, self.out_proj.weight)
+                continue
+
+            if module is None:
+                continue
+
+            print(f'failed to calculate lora weights for layer {lora_layer_name}')
+
+        setattr(self, "lora_current_names", wanted_names)
+
+
+def lora_reset_cached_weight(self: Union[torch.nn.Conv2d, torch.nn.Linear]):
+    setattr(self, "lora_current_names", ())
+    setattr(self, "lora_weights_backup", None)
 
 
 def lora_Linear_forward(self, input):
-    return lora_forward(self, input, torch.nn.Linear_forward_before_lora(self, input))
+    lora_apply_weights(self)
+
+    return torch.nn.Linear_forward_before_lora(self, input)
+
+
+def lora_Linear_load_state_dict(self, *args, **kwargs):
+    lora_reset_cached_weight(self)
+
+    return torch.nn.Linear_load_state_dict_before_lora(self, *args, **kwargs)
 
 
 def lora_Conv2d_forward(self, input):
-    return lora_forward(self, input, torch.nn.Conv2d_forward_before_lora(self, input))
+    lora_apply_weights(self)
+
+    return torch.nn.Conv2d_forward_before_lora(self, input)
+
+
+def lora_Conv2d_load_state_dict(self, *args, **kwargs):
+    lora_reset_cached_weight(self)
+
+    return torch.nn.Conv2d_load_state_dict_before_lora(self, *args, **kwargs)
+
+
+def lora_MultiheadAttention_forward(self, *args, **kwargs):
+    lora_apply_weights(self)
+
+    return torch.nn.MultiheadAttention_forward_before_lora(self, *args, **kwargs)
+
+
+def lora_MultiheadAttention_load_state_dict(self, *args, **kwargs):
+    lora_reset_cached_weight(self)
+
+    return torch.nn.MultiheadAttention_load_state_dict_before_lora(self, *args, **kwargs)
 
 
 def list_available_loras():
@@ -212,7 +347,7 @@ def list_available_loras():
         glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.safetensors'), recursive=True) + \
         glob.glob(os.path.join(shared.cmd_opts.lora_dir, '**/*.ckpt'), recursive=True)
 
-    for filename in sorted(candidates):
+    for filename in sorted(candidates, key=str.lower):
         if os.path.isdir(filename):
             continue
 

extensions-builtin/Lora/scripts/lora_script.py

@@ -9,7 +9,11 @@ from modules import script_callbacks, ui_extra_networks, extra_networks, shared
 
 def unload():
     torch.nn.Linear.forward = torch.nn.Linear_forward_before_lora
+    torch.nn.Linear._load_from_state_dict = torch.nn.Linear_load_state_dict_before_lora
     torch.nn.Conv2d.forward = torch.nn.Conv2d_forward_before_lora
+    torch.nn.Conv2d._load_from_state_dict = torch.nn.Conv2d_load_state_dict_before_lora
+    torch.nn.MultiheadAttention.forward = torch.nn.MultiheadAttention_forward_before_lora
+    torch.nn.MultiheadAttention._load_from_state_dict = torch.nn.MultiheadAttention_load_state_dict_before_lora
 
 
 def before_ui():
@@ -20,11 +24,27 @@ def before_ui():
 if not hasattr(torch.nn, 'Linear_forward_before_lora'):
     torch.nn.Linear_forward_before_lora = torch.nn.Linear.forward
 
+if not hasattr(torch.nn, 'Linear_load_state_dict_before_lora'):
+    torch.nn.Linear_load_state_dict_before_lora = torch.nn.Linear._load_from_state_dict
+
 if not hasattr(torch.nn, 'Conv2d_forward_before_lora'):
     torch.nn.Conv2d_forward_before_lora = torch.nn.Conv2d.forward
 
+if not hasattr(torch.nn, 'Conv2d_load_state_dict_before_lora'):
+    torch.nn.Conv2d_load_state_dict_before_lora = torch.nn.Conv2d._load_from_state_dict
+
+if not hasattr(torch.nn, 'MultiheadAttention_forward_before_lora'):
+    torch.nn.MultiheadAttention_forward_before_lora = torch.nn.MultiheadAttention.forward
+
+if not hasattr(torch.nn, 'MultiheadAttention_load_state_dict_before_lora'):
+    torch.nn.MultiheadAttention_load_state_dict_before_lora = torch.nn.MultiheadAttention._load_from_state_dict
+
 torch.nn.Linear.forward = lora.lora_Linear_forward
+torch.nn.Linear._load_from_state_dict = lora.lora_Linear_load_state_dict
 torch.nn.Conv2d.forward = lora.lora_Conv2d_forward
+torch.nn.Conv2d._load_from_state_dict = lora.lora_Conv2d_load_state_dict
+torch.nn.MultiheadAttention.forward = lora.lora_MultiheadAttention_forward
+torch.nn.MultiheadAttention._load_from_state_dict = lora.lora_MultiheadAttention_load_state_dict
 
 script_callbacks.on_model_loaded(lora.assign_lora_names_to_compvis_modules)
 script_callbacks.on_script_unloaded(unload)
@@ -33,6 +53,4 @@ script_callbacks.on_before_ui(before_ui)
 
 shared.options_templates.update(shared.options_section(('extra_networks', "Extra Networks"), {
     "sd_lora": shared.OptionInfo("None", "Add Lora to prompt", gr.Dropdown, lambda: {"choices": [""] + [x for x in lora.available_loras]}, refresh=lora.list_available_loras),
-    "lora_apply_to_outputs": shared.OptionInfo(False, "Apply Lora to outputs rather than inputs when possible (experimental)"),
-
 }))

javascript/aspectRatioOverlay.js

@@ -12,7 +12,7 @@ function dimensionChange(e, is_width, is_height){
 		currentHeight = e.target.value*1.0
 	}
 
-	var inImg2img   = Boolean(gradioApp().querySelector("button.rounded-t-lg.border-gray-200"))
+	var inImg2img = gradioApp().querySelector("#tab_img2img").style.display == "block";
 
 	if(!inImg2img){
 		return;
@@ -22,7 +22,7 @@ function dimensionChange(e, is_width, is_height){
 
     var tabIndex = get_tab_index('mode_img2img')
 	if(tabIndex == 0){ // img2img
-		targetElement = gradioApp().querySelector('div[data-testid=image] img');
+		targetElement = gradioApp().querySelector('#img2img_image div[data-testid=image] img');
 	} else if(tabIndex == 1){ //Sketch
 		targetElement = gradioApp().querySelector('#img2img_sketch div[data-testid=image] img');
 	} else if(tabIndex == 2){ // Inpaint
@@ -38,7 +38,7 @@ function dimensionChange(e, is_width, is_height){
 		if(!arPreviewRect){
 		    arPreviewRect = document.createElement('div')
 		    arPreviewRect.id = "imageARPreview";
-		    gradioApp().getRootNode().appendChild(arPreviewRect)
+		    gradioApp().appendChild(arPreviewRect)
 		}
 
 
@@ -91,7 +91,9 @@ onUiUpdate(function(){
 	if(arPreviewRect){
 		arPreviewRect.style.display = 'none';
 	}
-	var inImg2img   = Boolean(gradioApp().querySelector("button.rounded-t-lg.border-gray-200"))
+    var tabImg2img = gradioApp().querySelector("#tab_img2img");
+    if (tabImg2img) {
+        var inImg2img = tabImg2img.style.display == "block";
         if(inImg2img){
             let inputs = gradioApp().querySelectorAll('input');
             inputs.forEach(function(e){
@@ -110,4 +112,5 @@ onUiUpdate(function(){
                 }
             })
         }
+    }
 });

javascript/hints.js

@@ -21,8 +21,7 @@ titles = {
     "\u{1f5d1}\ufe0f": "Clear prompt",
     "\u{1f4cb}": "Apply selected styles to current prompt",
     "\u{1f4d2}": "Paste available values into the field",
-    "\u{1f3b4}": "Show extra networks",
+    "\u{1f3b4}": "Show/hide extra networks",
-
 
     "Inpaint a part of image": "Draw a mask over an image, and the script will regenerate the masked area with content according to prompt",
     "SD upscale": "Upscale image normally, split result into tiles, improve each tile using img2img, merge whole image back",

javascript/imageviewer.js

@@ -32,13 +32,7 @@ function negmod(n, m) {
 function updateOnBackgroundChange() {
     const modalImage = gradioApp().getElementById("modalImage")
     if (modalImage && modalImage.offsetParent) {
-        let allcurrentButtons = gradioApp().querySelectorAll(".gallery-item.transition-all.\\!ring-2")
+        let currentButton = selected_gallery_button();
-        let currentButton = null
-        allcurrentButtons.forEach(function(elem) {
-            if (elem.parentElement.offsetParent) {
-                currentButton = elem;
-            }
-        })
 
         if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
             modalImage.src = currentButton.children[0].src;
@@ -50,22 +44,10 @@ function updateOnBackgroundChange() {
 }
 
 function modalImageSwitch(offset) {
-    var allgalleryButtons = gradioApp().querySelectorAll(".gradio-gallery .thumbnail-item")
+    var galleryButtons = all_gallery_buttons();
-    var galleryButtons = []
-    allgalleryButtons.forEach(function(elem) {
-        if (elem.parentElement.offsetParent) {
-            galleryButtons.push(elem);
-        }
-    })
 
     if (galleryButtons.length > 1) {
-        var allcurrentButtons = gradioApp().querySelectorAll(".gradio-gallery .thumbnail-item.selected")
+        var currentButton = selected_gallery_button();
-        var currentButton = null
-        allcurrentButtons.forEach(function(elem) {
-            if (elem.parentElement.offsetParent) {
-                currentButton = elem;
-            }
-        })
 
         var result = -1
         galleryButtons.forEach(function(v, i) {

javascript/notification.js

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

javascript/ui.js

@@ -7,9 +7,31 @@ function set_theme(theme){
     }
 }
 
+function all_gallery_buttons() {
+    var allGalleryButtons = gradioApp().querySelectorAll('[style="display: block;"].tabitem div[id$=_gallery].gradio-gallery .thumbnails > .thumbnail-item.thumbnail-small');
+    var visibleGalleryButtons = [];
+    allGalleryButtons.forEach(function(elem) {
+        if (elem.parentElement.offsetParent) {
+            visibleGalleryButtons.push(elem);
+        }
+    })
+    return visibleGalleryButtons;
+}
+
+function selected_gallery_button() {
+    var allCurrentButtons = gradioApp().querySelectorAll('[style="display: block;"].tabitem div[id$=_gallery].gradio-gallery .thumbnail-item.thumbnail-small.selected');
+    var visibleCurrentButton = null;
+    allCurrentButtons.forEach(function(elem) {
+        if (elem.parentElement.offsetParent) {
+            visibleCurrentButton = elem;
+        }
+    })
+    return visibleCurrentButton;
+}
+
 function selected_gallery_index(){
-    var buttons = gradioApp().querySelectorAll('[style="display: block;"].tabitem div[id$=_gallery] .thumbnails > .thumbnail-item')
+    var buttons = all_gallery_buttons();
-    var button = gradioApp().querySelector('[style="display: block;"].tabitem div[id$=_gallery] .thumbnails > .thumbnail-item.selected')
+    var button = selected_gallery_button();
 
     var result = -1
     buttons.forEach(function(v, i){ if(v==button) { result = i } })
@@ -18,14 +40,18 @@ function selected_gallery_index(){
 }
 
 function extract_image_from_gallery(gallery){
-    if(gallery.length == 1){
+    if (gallery.length == 0){
-        return [gallery[0]]
+        return [null];
+    }
+    if (gallery.length == 1){
+        return [gallery[0]];
     }
 
     index = selected_gallery_index()
 
     if (index < 0 || index >= gallery.length){
-        return [null]
+        // Use the first image in the gallery as the default
+        index = 0;
     }
 
     return [gallery[index]];

modules/api/api.py

@@ -3,6 +3,7 @@ import io
 import time
 import datetime
 import uvicorn
+import gradio as gr
 from threading import Lock
 from io import BytesIO
 from gradio.processing_utils import decode_base64_to_file
@@ -197,6 +198,9 @@ class Api:
         self.add_api_route("/sdapi/v1/reload-checkpoint", self.reloadapi, methods=["POST"])
         self.add_api_route("/sdapi/v1/scripts", self.get_scripts_list, methods=["GET"], response_model=ScriptsList)
 
+        self.default_script_arg_txt2img = []
+        self.default_script_arg_img2img = []
+
     def add_api_route(self, path: str, endpoint, **kwargs):
         if shared.cmd_opts.api_auth:
             return self.app.add_api_route(path, endpoint, dependencies=[Depends(self.auth)], **kwargs)
@@ -230,7 +234,7 @@ class Api:
         script_idx = script_name_to_index(script_name, script_runner.scripts)
         return script_runner.scripts[script_idx]
 
-    def init_script_args(self, request, selectable_scripts, selectable_idx, script_runner):
+    def init_default_script_args(self, script_runner):
         #find max idx from the scripts in runner and generate a none array to init script_args
         last_arg_index = 1
         for script in script_runner.scripts:
@@ -238,13 +242,24 @@ class Api:
                 last_arg_index = script.args_to
         # None everywhere except position 0 to initialize script args
         script_args = [None]*last_arg_index
+        script_args[0] = 0
+
+        # get default values
+        with gr.Blocks(): # will throw errors calling ui function without this
+            for script in script_runner.scripts:
+                if script.ui(script.is_img2img):
+                    ui_default_values = []
+                    for elem in script.ui(script.is_img2img):
+                        ui_default_values.append(elem.value)
+                    script_args[script.args_from:script.args_to] = ui_default_values
+        return script_args
+
+    def init_script_args(self, request, default_script_args, selectable_scripts, selectable_idx, script_runner):
+        script_args = default_script_args.copy()
         # position 0 in script_arg is the idx+1 of the selectable script that is going to be run when using scripts.scripts_*2img.run()
         if selectable_scripts:
             script_args[selectable_scripts.args_from:selectable_scripts.args_to] = request.script_args
             script_args[0] = selectable_idx + 1
-        else:
-            # when [0] = 0 no selectable script to run
-            script_args[0] = 0
 
         # Now check for always on scripts
         if request.alwayson_scripts and (len(request.alwayson_scripts) > 0):
@@ -265,6 +280,8 @@ class Api:
         if not script_runner.scripts:
             script_runner.initialize_scripts(False)
             ui.create_ui()
+        if not self.default_script_arg_txt2img:
+            self.default_script_arg_txt2img = self.init_default_script_args(script_runner)
         selectable_scripts, selectable_script_idx = self.get_selectable_script(txt2imgreq.script_name, script_runner)
 
         populate = txt2imgreq.copy(update={  # Override __init__ params
@@ -280,7 +297,7 @@ class Api:
         args.pop('script_args', None) # will refeed them to the pipeline directly after initializing them
         args.pop('alwayson_scripts', None)
 
-        script_args = self.init_script_args(txt2imgreq, selectable_scripts, selectable_script_idx, script_runner)
+        script_args = self.init_script_args(txt2imgreq, self.default_script_arg_txt2img, selectable_scripts, selectable_script_idx, script_runner)
 
         send_images = args.pop('send_images', True)
         args.pop('save_images', None)
@@ -317,6 +334,8 @@ class Api:
         if not script_runner.scripts:
             script_runner.initialize_scripts(True)
             ui.create_ui()
+        if not self.default_script_arg_img2img:
+            self.default_script_arg_img2img = self.init_default_script_args(script_runner)
         selectable_scripts, selectable_script_idx = self.get_selectable_script(img2imgreq.script_name, script_runner)
 
         populate = img2imgreq.copy(update={  # Override __init__ params
@@ -334,7 +353,7 @@ class Api:
         args.pop('script_args', None)  # will refeed them to the pipeline directly after initializing them
         args.pop('alwayson_scripts', None)
 
-        script_args = self.init_script_args(img2imgreq, selectable_scripts, selectable_script_idx, script_runner)
+        script_args = self.init_script_args(img2imgreq, self.default_script_arg_img2img, selectable_scripts, selectable_script_idx, script_runner)
 
         send_images = args.pop('send_images', True)
         args.pop('save_images', None)

modules/cmd_args.py

@@ -4,6 +4,7 @@ from modules.paths_internal import models_path, script_path, data_path, extensio
 
 parser = argparse.ArgumentParser()
 
+parser.add_argument("-f", action='store_true', help=argparse.SUPPRESS)  # allows running as root; implemented outside of webui
 parser.add_argument("--update-all-extensions", action='store_true', help="launch.py argument: download updates for all extensions when starting the program")
 parser.add_argument("--skip-python-version-check", action='store_true', help="launch.py argument: do not check python version")
 parser.add_argument("--skip-torch-cuda-test", action='store_true', help="launch.py argument: do not check if CUDA is able to work properly")

modules/extensions.py

@@ -5,13 +5,14 @@ import traceback
 import time
 import git
 
-from modules import paths, shared
+from modules import shared
 from modules.paths_internal import extensions_dir, extensions_builtin_dir
 
 extensions = []
 
-if not os.path.exists(paths.extensions_dir):
+if not os.path.exists(extensions_dir):
-    os.makedirs(paths.extensions_dir)
+    os.makedirs(extensions_dir)
+
 
 def active():
     return [x for x in extensions if x.enabled]
@@ -26,21 +27,29 @@ class Extension:
         self.can_update = False
         self.is_builtin = is_builtin
         self.version = ''
+        self.remote = None
+        self.have_info_from_repo = False
+
+    def read_info_from_repo(self):
+        if self.have_info_from_repo:
+            return
+
+        self.have_info_from_repo = True
 
         repo = None
         try:
-            if os.path.exists(os.path.join(path, ".git")):
+            if os.path.exists(os.path.join(self.path, ".git")):
-                repo = git.Repo(path)
+                repo = git.Repo(self.path)
         except Exception:
-            print(f"Error reading github repository info from {path}:", file=sys.stderr)
+            print(f"Error reading github repository info from {self.path}:", file=sys.stderr)
             print(traceback.format_exc(), file=sys.stderr)
 
         if repo is None or repo.bare:
             self.remote = None
         else:
             try:
-                self.remote = next(repo.remote().urls, None)
                 self.status = 'unknown'
+                self.remote = next(repo.remote().urls, None)
                 head = repo.head.commit
                 ts = time.asctime(time.gmtime(repo.head.commit.committed_date))
                 self.version = f'{head.hexsha[:8]} ({ts})'
@@ -85,11 +94,11 @@ class Extension:
 def list_extensions():
     extensions.clear()
 
-    if not os.path.isdir(paths.extensions_dir):
+    if not os.path.isdir(extensions_dir):
         return
 
     extension_paths = []
-    for dirname in [paths.extensions_dir, paths.extensions_builtin_dir]:
+    for dirname in [extensions_dir, extensions_builtin_dir]:
         if not os.path.isdir(dirname):
             return
 
@@ -98,7 +107,7 @@ def list_extensions():
             if not os.path.isdir(path):
                 continue
 
-            extension_paths.append((extension_dirname, path, dirname == paths.extensions_builtin_dir))
+            extension_paths.append((extension_dirname, path, dirname == extensions_builtin_dir))
 
     for dirname, path, is_builtin in extension_paths:
         extension = Extension(name=dirname, path=path, enabled=dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin)

modules/images.py

@@ -261,9 +261,12 @@ def resize_image(resize_mode, im, width, height, upscaler_name=None):
 
         if scale > 1.0:
             upscalers = [x for x in shared.sd_upscalers if x.name == upscaler_name]
-            assert len(upscalers) > 0, f"could not find upscaler named {upscaler_name}"
+            if len(upscalers) == 0:
-
+                upscaler = shared.sd_upscalers[0]
+                print(f"could not find upscaler named {upscaler_name or '<empty string>'}, using {upscaler.name} as a fallback")
+            else:
                 upscaler = upscalers[0]
+
             im = upscaler.scaler.upscale(im, scale, upscaler.data_path)
 
         if im.width != w or im.height != h:

modules/scripts.py

@@ -553,3 +553,15 @@ def IOComponent_init(self, *args, **kwargs):
 
 original_IOComponent_init = gr.components.IOComponent.__init__
 gr.components.IOComponent.__init__ = IOComponent_init
+
+
+def BlockContext_init(self, *args, **kwargs):
+    res = original_BlockContext_init(self, *args, **kwargs)
+
+    add_classes_to_gradio_component(self)
+
+    return res
+
+
+original_BlockContext_init = gr.blocks.BlockContext.__init__
+gr.blocks.BlockContext.__init__ = BlockContext_init

modules/shared.py

@@ -640,7 +640,7 @@ mem_mon.start()
 
 
 def listfiles(dirname):
-    filenames = [os.path.join(dirname, x) for x in sorted(os.listdir(dirname)) if not x.startswith(".")]
+    filenames = [os.path.join(dirname, x) for x in sorted(os.listdir(dirname), key=str.lower) if not x.startswith(".")]
     return [file for file in filenames if os.path.isfile(file)]
 
 

modules/ui_common.py

@@ -145,7 +145,6 @@ Requested path was: {f}
             )
 
             if tabname != "extras":
-                with gr.Row():
                 download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False, elem_id=f'download_files_{tabname}')
 
                 with gr.Group():

modules/ui_extensions.py

@@ -63,6 +63,9 @@ def check_updates(id_task, disable_list):
 
         try:
             ext.check_updates()
+        except FileNotFoundError as e:
+            if 'FETCH_HEAD' not in str(e):
+                raise
         except Exception:
             print(f"Error checking updates for {ext.name}:", file=sys.stderr)
             print(traceback.format_exc(), file=sys.stderr)
@@ -87,6 +90,8 @@ def extension_table():
     """
 
     for ext in extensions.extensions:
+        ext.read_info_from_repo()
+
         remote = f"""<a href="{html.escape(ext.remote or '')}" target="_blank">{html.escape("built-in" if ext.is_builtin else ext.remote or '')}</a>"""
 
         if ext.can_update:

modules/ui_extra_networks.py

@@ -2,8 +2,10 @@ import glob
 import os.path
 import urllib.parse
 from pathlib import Path
+from PIL import PngImagePlugin
 
 from modules import shared
+from modules.images import read_info_from_image
 import gradio as gr
 import json
 import html
@@ -252,10 +254,10 @@ def create_ui(container, button, tabname):
 
     def toggle_visibility(is_visible):
         is_visible = not is_visible
-        return is_visible, gr.update(visible=is_visible)
+        return is_visible, gr.update(visible=is_visible), gr.update(variant=("secondary-down" if is_visible else "secondary"))
 
     state_visible = gr.State(value=False)
-    button.click(fn=toggle_visibility, inputs=[state_visible], outputs=[state_visible, container])
+    button.click(fn=toggle_visibility, inputs=[state_visible], outputs=[state_visible, container, button])
 
     def refresh():
         res = []
@@ -290,6 +292,7 @@ def setup_ui(ui, gallery):
 
         img_info = images[index if index >= 0 else 0]
         image = image_from_url_text(img_info)
+        geninfo, items = read_info_from_image(image)
 
         is_allowed = False
         for extra_page in ui.stored_extra_pages:
@@ -299,6 +302,11 @@ def setup_ui(ui, gallery):
 
         assert is_allowed, f'writing to {filename} is not allowed'
 
+        if geninfo:
+            pnginfo_data = PngImagePlugin.PngInfo()
+            pnginfo_data.add_text('parameters', geninfo)
+            image.save(filename, pnginfo=pnginfo_data)
+        else:
             image.save(filename)
 
         return [page.create_html(ui.tabname) for page in ui.stored_extra_pages]

scripts/loopback.py

@@ -54,14 +54,11 @@ class Script(scripts.Script):
                 return strength
 
             progress = loop / (loops - 1)
-            match denoising_curve:
+            if denoising_curve == "Aggressive":
-                case "Aggressive":
                 strength = math.sin((progress) * math.pi * 0.5)
-
+            elif denoising_curve == "Lazy":
-                case "Lazy":
                 strength = 1 - math.cos((progress) * math.pi * 0.5)
-
+            else:
-                case _:
                 strength = progress
 
             change = (final_denoising_strength - initial_denoising_strength) * strength

style.css

@@ -7,7 +7,7 @@
     --block-background-fill: transparent;
 }
 
-.block.padded{
+.block.padded:not(.gradio-accordion) {
     padding: 0 !important;
 }
 
@@ -54,10 +54,6 @@ div.compact{
     gap: 1em;
 }
 
-.gradio-dropdown ul.options{
-    z-index: 3000;
-}
-
 .gradio-dropdown label span:not(.has-info),
 .gradio-textbox label span:not(.has-info),
 .gradio-number label span:not(.has-info)
@@ -65,11 +61,30 @@ div.compact{
     margin-bottom: 0;
 }
 
+.gradio-dropdown ul.options{
+    z-index: 3000;
+    min-width: fit-content;
+    max-width: inherit;
+    white-space: nowrap;
+}
+
+.gradio-dropdown ul.options li.item {
+    padding: 0.05em 0;
+}
+
+.gradio-dropdown ul.options li.item.selected {
+    background-color: var(--neutral-100);
+}
+
+.dark .gradio-dropdown ul.options li.item.selected {
+    background-color: var(--neutral-900);
+}
+
 .gradio-dropdown div.wrap.wrap.wrap.wrap{
     box-shadow: 0 1px 2px 0 rgba(0, 0, 0, 0.05);
 }
 
-.gradio-dropdown .wrap-inner.wrap-inner.wrap-inner{
+.gradio-dropdown:not(.multiselect) .wrap-inner.wrap-inner.wrap-inner{
     flex-wrap: unset;
 }
 
@@ -123,6 +138,18 @@ div.gradio-html.min{
     border-radius: 0.5em;
 }
 
+.gradio-button.secondary-down{
+    background: var(--button-secondary-background-fill);
+    color: var(--button-secondary-text-color);
+}
+.gradio-button.secondary-down, .gradio-button.secondary-down:hover{
+    box-shadow: 1px 1px 1px rgba(0,0,0,0.25) inset, 0px 0px 3px rgba(0,0,0,0.15) inset;
+}
+.gradio-button.secondary-down:hover{
+    background: var(--button-secondary-background-fill-hover);
+    color: var(--button-secondary-text-color-hover);
+}
+
 .checkboxes-row{
     margin-bottom: 0.5em;
     margin-left: 0em;
@@ -507,6 +534,17 @@ div.dimensions-tools{
   background-color: rgba(0, 0, 0, 0.8);
 }
 
+#imageARPreview {
+    position: absolute;
+    top: 0px;
+    left: 0px;
+    border: 2px solid red;
+    background: rgba(255, 0, 0, 0.3);
+    z-index: 900;
+    pointer-events: none;
+    display: none;
+}
+
 /* context menu (ie for the generate button) */
 
 #context-menu{

webui.py

@@ -265,9 +265,6 @@ def webui():
             inbrowser=cmd_opts.autolaunch,
             prevent_thread_lock=True
         )
-        for dep in shared.demo.dependencies:
-            dep['show_progress'] = False  # disable gradio css animation on component update
-
         # after initial launch, disable --autolaunch for subsequent restarts
         cmd_opts.autolaunch = False