Merge branch 'dev' into m9-240816-pnginfo-text-copy

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.EpsWeighting
+        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: True
+        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

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();
     }
 }
 

modules/extras.py

@@ -69,7 +69,7 @@ def run_pnginfo(image):
 
         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>

modules/sd_models.py

@@ -159,7 +159,7 @@ def list_models():
         model_url = None
         expected_sha256 = None
     else:
-        model_url = f"{shared.hf_endpoint}/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors"
+        model_url = f"{shared.hf_endpoint}/stable-diffusion-v1-5/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors"
         expected_sha256 = '6ce0161689b3853acaa03779ec93eafe75a02f4ced659bee03f50797806fa2fa'
 
     model_list = modelloader.load_models(model_path=model_path, model_url=model_url, command_path=shared.cmd_opts.ckpt_dir, ext_filter=[".ckpt", ".safetensors"], download_name="v1-5-pruned-emaonly.safetensors", ext_blacklist=[".vae.ckpt", ".vae.safetensors"], hash_prefix=expected_sha256)
@@ -783,7 +783,7 @@ def get_obj_from_str(string, reload=False):
     return getattr(importlib.import_module(module, package=None), cls)
 
 
-def load_model(checkpoint_info=None, already_loaded_state_dict=None):
+def load_model(checkpoint_info=None, already_loaded_state_dict=None, checkpoint_config=None):
     from modules import sd_hijack
     checkpoint_info = checkpoint_info or select_checkpoint()
 
@@ -801,7 +801,8 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None):
     else:
         state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
 
-    checkpoint_config = sd_models_config.find_checkpoint_config(state_dict, checkpoint_info)
+    if not checkpoint_config:
+        checkpoint_config = sd_models_config.find_checkpoint_config(state_dict, checkpoint_info)
     clip_is_included_into_sd = any(x for x in [sd1_clip_weight, sd2_clip_weight, sdxl_clip_weight, sdxl_refiner_clip_weight] if x in state_dict)
 
     timer.record("find config")
@@ -974,7 +975,7 @@ def reload_model_weights(sd_model=None, info=None, forced_reload=False):
         if sd_model is not None:
             send_model_to_trash(sd_model)
 
-        load_model(checkpoint_info, already_loaded_state_dict=state_dict)
+        load_model(checkpoint_info, already_loaded_state_dict=state_dict, checkpoint_config=checkpoint_config)
         return model_data.sd_model
 
     try:

modules/sd_models_config.py

@@ -14,6 +14,7 @@
 config_sd2v = os.path.join(sd_repo_configs_path, "v2-inference-v.yaml")
 config_sd2_inpainting = os.path.join(sd_repo_configs_path, "v2-inpainting-inference.yaml")
 config_sdxl = os.path.join(sd_xl_repo_configs_path, "sd_xl_base.yaml")
+config_sdxlv = os.path.join(sd_configs_path, "sd_xl_v.yaml")
 config_sdxl_refiner = os.path.join(sd_xl_repo_configs_path, "sd_xl_refiner.yaml")
 config_sdxl_inpainting = os.path.join(sd_configs_path, "sd_xl_inpaint.yaml")
 config_depth_model = os.path.join(sd_repo_configs_path, "v2-midas-inference.yaml")
@@ -81,6 +82,9 @@ def guess_model_config_from_state_dict(sd, filename):
         if diffusion_model_input.shape[1] == 9:
             return config_sdxl_inpainting
         else:
+            if ('v_pred' in sd):
+                del sd['v_pred']
+                return config_sdxlv
             return config_sdxl
 
     if sd.get('conditioner.embedders.0.model.ln_final.weight', None) is not None:

modules/shared_options.py

@@ -231,7 +231,7 @@
 
 options_templates.update(options_section(('optimizations', "Optimizations", "sd"), {
     "cross_attention_optimization": OptionInfo("Automatic", "Cross attention optimization", gr.Dropdown, lambda: {"choices": shared_items.cross_attention_optimizations()}),
-    "s_min_uncond": OptionInfo(0.0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 15.0, "step": 0.01}, infotext='NGMS').link("PR", "https://github.com/AUTOMATIC1111/stablediffusion-webui/pull/9177").info("skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster"),
+    "s_min_uncond": OptionInfo(0.0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 15.0, "step": 0.01}, infotext='NGMS').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9177").info("skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster"),
     "s_min_uncond_all": OptionInfo(False, "Negative Guidance minimum sigma all steps", infotext='NGMS all steps').info("By default, NGMS above skips every other step; this makes it skip all steps"),
     "token_merging_ratio": OptionInfo(0.0, "Token merging ratio", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9256").info("0=disable, higher=faster"),
     "token_merging_ratio_img2img": OptionInfo(0.0, "Token merging ratio for img2img", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).info("only applies if non-zero and overrides above"),
@@ -404,7 +404,7 @@
     'uni_pc_order': OptionInfo(3, "UniPC order", gr.Slider, {"minimum": 1, "maximum": 50, "step": 1}, infotext='UniPC order').info("must be < sampling steps"),
     'uni_pc_lower_order_final': OptionInfo(True, "UniPC lower order final", infotext='UniPC lower order final'),
     'sd_noise_schedule': OptionInfo("Default", "Noise schedule for sampling", gr.Radio, {"choices": ["Default", "Zero Terminal SNR"]}, infotext="Noise Schedule").info("for use with zero terminal SNR trained models"),
-    'skip_early_cond': OptionInfo(0.0, "Ignore negative prompt during early sampling", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext="Skip Early CFG").info("disables CFG on a proportion of steps at the beginning of generation; 0=skip none; 1=skip all; can both improve sample diversity/quality and speed up sampling"),
+    'skip_early_cond': OptionInfo(0.0, "Ignore negative prompt during early sampling", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext="Skip Early CFG").info("disables CFG on a proportion of steps at the beginning of generation; 0=skip none; 1=skip all; can both improve sample diversity/quality and speed up sampling; XYZ plot: Skip Early CFG"),
     'beta_dist_alpha': OptionInfo(0.6, "Beta scheduler - alpha", gr.Slider, {"minimum": 0.01, "maximum": 1.0, "step": 0.01}, infotext='Beta scheduler alpha').info('Default = 0.6; the alpha parameter of the beta distribution used in Beta sampling'),
     'beta_dist_beta': OptionInfo(0.6, "Beta scheduler - beta", gr.Slider, {"minimum": 0.01, "maximum": 1.0, "step": 0.01}, infotext='Beta scheduler beta').info('Default = 0.6; the beta parameter of the beta distribution used in Beta sampling'),
 }))

modules/ui.py

@@ -44,6 +44,9 @@
 mimetypes.add_type('image/webp', '.webp')
 mimetypes.add_type('image/avif', '.avif')
 
+# override potentially incorrect mimetypes
+mimetypes.add_type('text/css', '.css')
+
 if not cmd_opts.share and not cmd_opts.listen:
     # fix gradio phoning home
     gradio.utils.version_check = lambda: None

scripts/xyz_grid.py

@@ -259,6 +259,7 @@ def __init__(self, *args, **kwargs):
     AxisOption("Schedule min sigma", float, apply_override("sigma_min")),
     AxisOption("Schedule max sigma", float, apply_override("sigma_max")),
     AxisOption("Schedule rho", float, apply_override("rho")),
+    AxisOption("Skip Early CFG", float, apply_override('skip_early_cond')),
     AxisOption("Beta schedule alpha", float, apply_override("beta_dist_alpha")),
     AxisOption("Beta schedule beta", float, apply_override("beta_dist_beta")),
     AxisOption("Eta", float, apply_field("eta")),