Merge pull request #1 from AUTOMATIC1111/dev

Dev

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

@@ -4,11 +4,11 @@
 // 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;
+    const counts = {};
+    textArea.value.matchAll(/(?<!\\)(?:\\\\)*?([(){}[\]])/g).forEach(bracket => {
+        counts[bracket[1]] = (counts[bracket[1]] || 0) + 1;
     });
-    var errors = [];
+    const errors = [];
 
     function checkPair(open, close, kind) {
         if (counts[open] !== counts[close]) {

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);

modules/api/api.py

@@ -122,7 +122,7 @@ def encode_pil_to_base64(image):
             if opts.samples_format.lower() in ("jpg", "jpeg"):
                 image.save(output_bytes, format="JPEG", exif = exif_bytes, quality=opts.jpeg_quality)
             else:
-                image.save(output_bytes, format="WEBP", exif = exif_bytes, quality=opts.jpeg_quality)
+                image.save(output_bytes, format="WEBP", exif = exif_bytes, quality=opts.jpeg_quality, lossless=opts.webp_lossless)
 
         else:
             raise HTTPException(status_code=500, detail="Invalid image format")

modules/dat_model.py

@@ -1,7 +1,7 @@
 import os
 
 from modules import modelloader, errors
-from modules.shared import cmd_opts, opts
+from modules.shared import cmd_opts, opts, hf_endpoint
 from modules.upscaler import Upscaler, UpscalerData
 from modules.upscaler_utils import upscale_with_model
 
@@ -49,7 +49,18 @@ def load_model(self, path):
                     scaler.local_data_path = modelloader.load_file_from_url(
                         scaler.data_path,
                         model_dir=self.model_download_path,
+                        hash_prefix=scaler.sha256,
                     )
+
+                    if os.path.getsize(scaler.local_data_path) < 200:
+                        # Re-download if the file is too small, probably an LFS pointer
+                        scaler.local_data_path = modelloader.load_file_from_url(
+                            scaler.data_path,
+                            model_dir=self.model_download_path,
+                            hash_prefix=scaler.sha256,
+                            re_download=True,
+                        )
+
                 if not os.path.exists(scaler.local_data_path):
                     raise FileNotFoundError(f"DAT data missing: {scaler.local_data_path}")
                 return scaler
@@ -60,20 +71,23 @@ def get_dat_models(scaler):
     return [
         UpscalerData(
             name="DAT x2",
-            path="https://github.com/n0kovo/dat_upscaler_models/raw/main/DAT/DAT_x2.pth",
+            path=f"{hf_endpoint}/w-e-w/DAT/resolve/main/experiments/pretrained_models/DAT/DAT_x2.pth",
             scale=2,
             upscaler=scaler,
+            sha256='7760aa96e4ee77e29d4f89c3a4486200042e019461fdb8aa286f49aa00b89b51',
         ),
         UpscalerData(
             name="DAT x3",
-            path="https://github.com/n0kovo/dat_upscaler_models/raw/main/DAT/DAT_x3.pth",
+            path=f"{hf_endpoint}/w-e-w/DAT/resolve/main/experiments/pretrained_models/DAT/DAT_x3.pth",
             scale=3,
             upscaler=scaler,
+            sha256='581973e02c06f90d4eb90acf743ec9604f56f3c2c6f9e1e2c2b38ded1f80d197',
         ),
         UpscalerData(
             name="DAT x4",
-            path="https://github.com/n0kovo/dat_upscaler_models/raw/main/DAT/DAT_x4.pth",
+            path=f"{hf_endpoint}/w-e-w/DAT/resolve/main/experiments/pretrained_models/DAT/DAT_x4.pth",
             scale=4,
             upscaler=scaler,
+            sha256='391a6ce69899dff5ea3214557e9d585608254579217169faf3d4c353caff049e',
         ),
     ]

modules/extras.py

@@ -23,7 +23,7 @@ def run_pnginfo(image):
     info = ''
     for key, text in items.items():
         info += f"""
-<div>
+<div class="infotext">
 <p><b>{plaintext_to_html(str(key))}</b></p>
 <p>{plaintext_to_html(str(text))}</p>
 </div>