[Edited] Refactor code to optimize performance

.github/workflows/on_pull_request.yaml

@@ -22,7 +22,7 @@ jobs:
       - name: Install Ruff
         run: pip install ruff==0.3.3
       - name: Run Ruff
-        run: ruff .
+        run: ruff check .
   lint-js:
     name: eslint
     runs-on: ubuntu-latest

CODEOWNERS

@@ -1,12 +1 @@
-*       @AUTOMATIC1111
-
-# if you were managing a localization and were removed from this file, this is because
-# the intended way to do localizations now is via extensions. See:
-# https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Developing-extensions
-# Make a repo with your localization and since you are still listed as a collaborator
-# you can add it to the wiki page yourself. This change is because some people complained
-# the git commit log is cluttered with things unrelated to almost everyone and
-# because I believe this is the best overall for the project to handle localizations almost
-# entirely without my oversight.
-
-
+*       @AUTOMATIC1111 @w-e-w @catboxanon

README.md

@@ -148,6 +148,7 @@ python_cmd="python3.11"
 2. Navigate to the directory you would like the webui to be installed and execute the following command:
 ```bash
 wget -q https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
+chmod +x webui.sh
 ```
 Or just clone the repo wherever you want:
 ```bash

configs/sd_xl_v.yaml

@@ -0,0 +1,98 @@
+model:
+  target: sgm.models.diffusion.DiffusionEngine
+  params:
+    scale_factor: 0.13025
+    disable_first_stage_autocast: True
+
+    denoiser_config:
+      target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
+      params:
+        num_idx: 1000
+
+        weighting_config:
+          target: sgm.modules.diffusionmodules.denoiser_weighting.VWeighting
+        scaling_config:
+          target: sgm.modules.diffusionmodules.denoiser_scaling.VScaling
+        discretization_config:
+          target: sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization
+
+    network_config:
+      target: sgm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        adm_in_channels: 2816
+        num_classes: sequential
+        use_checkpoint: False
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [4, 2]
+        num_res_blocks: 2
+        channel_mult: [1, 2, 4]
+        num_head_channels: 64
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: [1, 2, 10]  # note: the first is unused (due to attn_res starting at 2) 32, 16, 8 --> 64, 32, 16
+        context_dim: 2048
+        spatial_transformer_attn_type: softmax-xformers
+        legacy: False
+
+    conditioner_config:
+      target: sgm.modules.GeneralConditioner
+      params:
+        emb_models:
+          # crossattn cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenCLIPEmbedder
+            params:
+              layer: hidden
+              layer_idx: 11
+          # crossattn and vector cond
+          - is_trainable: False
+            input_key: txt
+            target: sgm.modules.encoders.modules.FrozenOpenCLIPEmbedder2
+            params:
+              arch: ViT-bigG-14
+              version: laion2b_s39b_b160k
+              freeze: True
+              layer: penultimate
+              always_return_pooled: True
+              legacy: False
+          # vector cond
+          - is_trainable: False
+            input_key: original_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: crop_coords_top_left
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+          # vector cond
+          - is_trainable: False
+            input_key: target_size_as_tuple
+            target: sgm.modules.encoders.modules.ConcatTimestepEmbedderND
+            params:
+              outdim: 256  # multiplied by two
+
+    first_stage_config:
+      target: sgm.models.autoencoder.AutoencoderKLInferenceWrapper
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          attn_type: vanilla-xformers
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult: [1, 2, 4, 4]
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity

extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js

@@ -816,7 +816,7 @@ onUiLoaded(async() => {
                 // Increase or decrease brush size based on scroll direction
                 adjustBrushSize(elemId, e.deltaY);
             }
-        });
+        }, {passive: false});
 
         // Handle the move event for pan functionality. Updates the panX and panY variables and applies the new transform to the target element.
         function handleMoveKeyDown(e) {

extensions-builtin/hypertile/hypertile.py

@@ -1,7 +1,7 @@
 """
 Hypertile module for splitting attention layers in SD-1.5 U-Net and SD-1.5 VAE
 Warn: The patch works well only if the input image has a width and height that are multiples of 128
-Original author: @tfernd Github: https://github.com/tfernd/HyperTile
+Original author: @tfernd GitHub: https://github.com/tfernd/HyperTile
 """
 
 from __future__ import annotations

extensions-builtin/postprocessing-for-training/scripts/postprocessing_autosized_crop.py

@@ -34,14 +34,14 @@ def ui(self):
         with ui_components.InputAccordion(False, label="Auto-sized crop") as enable:
             gr.Markdown('Each image is center-cropped with an automatically chosen width and height.')
             with gr.Row():
-                mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="postprocess_multicrop_mindim")
-                maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="postprocess_multicrop_maxdim")
+                mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id=self.elem_id_suffix("postprocess_multicrop_mindim"))
+                maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id=self.elem_id_suffix("postprocess_multicrop_maxdim"))
             with gr.Row():
-                minarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area lower bound", value=64 * 64, elem_id="postprocess_multicrop_minarea")
-                maxarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area upper bound", value=640 * 640, elem_id="postprocess_multicrop_maxarea")
+                minarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area lower bound", value=64 * 64, elem_id=self.elem_id_suffix("postprocess_multicrop_minarea"))
+                maxarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area upper bound", value=640 * 640, elem_id=self.elem_id_suffix("postprocess_multicrop_maxarea"))
             with gr.Row():
-                objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="postprocess_multicrop_objective")
-                threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="postprocess_multicrop_threshold")
+                objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id=self.elem_id_suffix("postprocess_multicrop_objective"))
+                threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id=self.elem_id_suffix("postprocess_multicrop_threshold"))
 
         return {
             "enable": enable,

extensions-builtin/postprocessing-for-training/scripts/postprocessing_focal_crop.py

@@ -11,10 +11,10 @@ class ScriptPostprocessingFocalCrop(scripts_postprocessing.ScriptPostprocessing)
 
     def ui(self):
         with ui_components.InputAccordion(False, label="Auto focal point crop") as enable:
-            face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_face_weight")
-            entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_entropy_weight")
-            edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_edges_weight")
-            debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug")
+            face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id=self.elem_id_suffix("postprocess_focal_crop_face_weight"))
+            entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id=self.elem_id_suffix("postprocess_focal_crop_entropy_weight"))
+            edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id=self.elem_id_suffix("postprocess_focal_crop_edges_weight"))
+            debug = gr.Checkbox(label='Create debug image', elem_id=self.elem_id_suffix("train_process_focal_crop_debug"))
 
         return {
             "enable": enable,

extensions-builtin/postprocessing-for-training/scripts/postprocessing_split_oversized.py

@@ -35,8 +35,8 @@ class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostproces
     def ui(self):
         with ui_components.InputAccordion(False, label="Split oversized images") as enable:
             with gr.Row():
-                split_threshold = gr.Slider(label='Threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_split_threshold")
-                overlap_ratio = gr.Slider(label='Overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="postprocess_overlap_ratio")
+                split_threshold = gr.Slider(label='Threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id=self.elem_id_suffix("postprocess_split_threshold"))
+                overlap_ratio = gr.Slider(label='Overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id=self.elem_id_suffix("postprocess_overlap_ratio"))
 
         return {
             "enable": enable,

extensions-builtin/prompt-bracket-checker/javascript/prompt-bracket-checker.js

@@ -1,36 +1,69 @@
-// Stable Diffusion WebUI - Bracket checker
-// By Hingashi no Florin/Bwin4L & @akx
+// Stable Diffusion WebUI - Bracket Checker
+// By @Bwin4L, @akx, @w-e-w, @Haoming02
 // Counts open and closed brackets (round, square, curly) in the prompt and negative prompt text boxes in the txt2img and img2img tabs.
-// If there's a mismatch, the keyword counter turns red and if you hover on it, a tooltip tells you what's wrong.
-
-function checkBrackets(textArea, counterElt) {
-    var counts = {};
-    (textArea.value.match(/[(){}[\]]/g) || []).forEach(bracket => {
-        counts[bracket] = (counts[bracket] || 0) + 1;
-    });
-    var errors = [];
-
-    function checkPair(open, close, kind) {
-        if (counts[open] !== counts[close]) {
-            errors.push(
-                `${open}...${close} - Detected ${counts[open] || 0} opening and ${counts[close] || 0} closing ${kind}.`
-            );
+// If there's a mismatch, the keyword counter turns red, and if you hover on it, a tooltip tells you what's wrong.
+
+function checkBrackets(textArea, counterElem) {
+    const pairs = [
+        ['(', ')', 'round brackets'],
+        ['[', ']', 'square brackets'],
+        ['{', '}', 'curly brackets']
+    ];
+
+    const counts = {};
+    const errors = new Set();
+    let i = 0;
+
+    while (i < textArea.value.length) {
+        let char = textArea.value[i];
+        let escaped = false;
+        while (char === '\\' && i + 1 < textArea.value.length) {
+            escaped = !escaped;
+            i++;
+            char = textArea.value[i];
+        }
+
+        if (escaped) {
+            i++;
+            continue;
+        }
+
+        for (const [open, close, label] of pairs) {
+            if (char === open) {
+                counts[label] = (counts[label] || 0) + 1;
+            } else if (char === close) {
+                counts[label] = (counts[label] || 0) - 1;
+                if (counts[label] < 0) {
+                    errors.add(`Incorrect order of ${label}.`);
+                }
+            }
+        }
+
+        i++;
+    }
+
+    for (const [open, close, label] of pairs) {
+        if (counts[label] == undefined) {
+            continue;
+        }
+
+        if (counts[label] > 0) {
+            errors.add(`${open} ... ${close} - Detected ${counts[label]} more opening than closing ${label}.`);
+        } else if (counts[label] < 0) {
+            errors.add(`${open} ... ${close} - Detected ${-counts[label]} more closing than opening ${label}.`);
         }
     }
 
-    checkPair('(', ')', 'round brackets');
-    checkPair('[', ']', 'square brackets');
-    checkPair('{', '}', 'curly brackets');
-    counterElt.title = errors.join('\n');
-    counterElt.classList.toggle('error', errors.length !== 0);
+    counterElem.title = [...errors].join('\n');
+    counterElem.classList.toggle('error', errors.size !== 0);
 }
 
 function setupBracketChecking(id_prompt, id_counter) {
-    var textarea = gradioApp().querySelector("#" + id_prompt + " > label > textarea");
-    var counter = gradioApp().getElementById(id_counter);
+    const textarea = gradioApp().querySelector(`#${id_prompt} > label > textarea`);
+    const counter = gradioApp().getElementById(id_counter);
 
     if (textarea && counter) {
-        textarea.addEventListener("input", () => checkBrackets(textarea, counter));
+        onEdit(`${id_prompt}_BracketChecking`, textarea, 400, () => checkBrackets(textarea, counter));
     }
 }
 

html/footer.html

@@ -1,7 +1,7 @@
 <div>
         <a href="{api_docs}">API</a>
          • 
-        <a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">Github</a>
+        <a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">GitHub</a>
          • 
         <a href="https://gradio.app">Gradio</a>
          • 

javascript/contextMenus.js

@@ -104,7 +104,7 @@ var contextMenuInit = function() {
                         e.preventDefault();
                     }
                 });
-            });
+            }, {passive: false});
         });
         eventListenerApplied = true;
 

javascript/extraNetworks.js

@@ -201,7 +201,7 @@ function setupExtraNetworks() {
     setupExtraNetworksForTab('img2img');
 }
 
-var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/;
+var re_extranet = /<([^:^>]+:[^:]+):[\d.]+>(.*)/s;
 var re_extranet_g = /<([^:^>]+:[^:]+):[\d.]+>/g;
 
 var re_extranet_neg = /\(([^:^>]+:[\d.]+)\)/;

javascript/imageviewer.js

@@ -13,6 +13,7 @@ function showModal(event) {
     if (modalImage.style.display === 'none') {
         lb.style.setProperty('background-image', 'url(' + source.src + ')');
     }
+    updateModalImage();
     lb.style.display = "flex";
     lb.focus();
 
@@ -31,21 +32,26 @@ function negmod(n, m) {
     return ((n % m) + m) % m;
 }
 
+function updateModalImage() {
+    const modalImage = gradioApp().getElementById("modalImage");
+    let currentButton = selected_gallery_button();
+    let preview = gradioApp().querySelectorAll('.livePreview > img');
+    if (opts.js_live_preview_in_modal_lightbox && preview.length > 0) {
+        // show preview image if available
+        modalImage.src = preview[preview.length - 1].src;
+    } else if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
+        modalImage.src = currentButton.children[0].src;
+        if (modalImage.style.display === 'none') {
+            const modal = gradioApp().getElementById("lightboxModal");
+            modal.style.setProperty('background-image', `url(${modalImage.src})`);
+        }
+    }
+}
+
 function updateOnBackgroundChange() {
     const modalImage = gradioApp().getElementById("modalImage");
     if (modalImage && modalImage.offsetParent) {
-        let currentButton = selected_gallery_button();
-        let preview = gradioApp().querySelectorAll('.livePreview > img');
-        if (opts.js_live_preview_in_modal_lightbox && preview.length > 0) {
-            // show preview image if available
-            modalImage.src = preview[preview.length - 1].src;
-        } else if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {
-            modalImage.src = currentButton.children[0].src;
-            if (modalImage.style.display === 'none') {
-                const modal = gradioApp().getElementById("lightboxModal");
-                modal.style.setProperty('background-image', `url(${modalImage.src})`);
-            }
-        }
+        updateModalImage();
     }
 }
 

javascript/progressbar.js

@@ -79,11 +79,12 @@ function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgre
     var wakeLock = null;
 
     var requestWakeLock = async function() {
-        if (!opts.prevent_screen_sleep_during_generation || wakeLock) return;
+        if (!opts.prevent_screen_sleep_during_generation || wakeLock !== null) return;
         try {
             wakeLock = await navigator.wakeLock.request('screen');
         } catch (err) {
             console.error('Wake Lock is not supported.');
+            wakeLock = false;
         }
     };
 

javascript/resizeHandle.js

@@ -124,7 +124,7 @@
                 } else {
                     R.screenX = evt.changedTouches[0].screenX;
                 }
-            });
+            }, {passive: false});
         });
 
         resizeHandle.addEventListener('dblclick', onDoubleClick);