Merge branch 'master' into patch-6

README.md

@@ -20,6 +20,8 @@ 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 with a lot of third party models
+    - SwinIR, neural network upscaler
+    - LDSR, Latent diffusion super resolution upscaling
 - Resizing aspect ratio options
 - Sampling method selection
 - Interrupt processing at any time
@@ -41,6 +43,10 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Seed resizing
 - CLIP interrogator
 - Prompt Editing
+- Batch Processing
+- Img2img Alternative
+- Highres Fix
+- LDSR Upscaling
 
 ## 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.
@@ -79,6 +85,8 @@ The documentation was moved from this README over to the project's [wiki](https:
 - GFPGAN - https://github.com/TencentARC/GFPGAN.git
 - CodeFormer - https://github.com/sczhou/CodeFormer
 - ESRGAN - https://github.com/xinntao/ESRGAN
+- SwinIR - https://github.com/JingyunLiang/SwinIR
+- LDSR - https://github.com/Hafiidz/latent-diffusion
 - Ideas for optimizations - https://github.com/basujindal/stable-diffusion
 - Doggettx - Cross Attention layer optimization - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
 - Idea for SD upscale - https://github.com/jquesnelle/txt2imghd

javascript/progressbar.js

@@ -1,27 +1,33 @@
 // code related to showing and updating progressbar shown as the image is being made
-
 global_progressbar = null
 
 onUiUpdate(function(){
-	progressbar = gradioApp().getElementById('progressbar')
+    progressbar = gradioApp().getElementById('progressbar')
+    progressDiv = gradioApp().querySelectorAll('.progressDiv').length > 0;
+    interrupt = gradioApp().getElementById('interrupt')
 	if(progressbar!= null && progressbar != global_progressbar){
 	    global_progressbar = progressbar
 
         var mutationObserver = new MutationObserver(function(m){
             txt2img_preview = gradioApp().getElementById('txt2img_preview')
             txt2img_gallery = gradioApp().getElementById('txt2img_gallery')
-
             img2img_preview = gradioApp().getElementById('img2img_preview')
             img2img_gallery = gradioApp().getElementById('img2img_gallery')
 
             if(txt2img_preview != null && txt2img_gallery != null){
                 txt2img_preview.style.width = txt2img_gallery.clientWidth + "px"
-                txt2img_preview.style.height = txt2img_gallery.clientHeight + "px"
+                txt2img_preview.style.height = txt2img_gallery.clientHeight + "px"  
+                if(!progressDiv){
+                    interrupt.style.display = "none"
+                }
             }
 
             if(img2img_preview != null && img2img_gallery != null){
                 img2img_preview.style.width = img2img_gallery.clientWidth + "px"
-                img2img_preview.style.height = img2img_gallery.clientHeight + "px"
+                img2img_preview.style.height = img2img_gallery.clientHeight + "px" 
+                if(!progressDiv){
+                    interrupt.style.display = "none"
+                }
             }
 
             window.setTimeout(requestMoreProgress, 500)
@@ -29,12 +35,15 @@ onUiUpdate(function(){
         mutationObserver.observe( progressbar, { childList:true, subtree:true })
 	}
 })
-
 function requestMoreProgress(){
     btn = gradioApp().getElementById("check_progress");
     if(btn==null) return;
 
     btn.click();
+    progressDiv = gradioApp().querySelectorAll('.progressDiv').length > 0;
+    if(progressDiv){
+        interrupt.style.display = "block"
+    }
 }
 
 function requestProgress(){
@@ -43,4 +52,3 @@ function requestProgress(){
 
     btn.click();
 }
-

modules/realesrgan_model.py

@@ -1,17 +1,66 @@
 import sys
 import traceback
 from collections import namedtuple
+
 import numpy as np
 from PIL import Image
+from realesrgan import RealESRGANer
 
 import modules.images
 from modules.shared import cmd_opts, opts
 
 RealesrganModelInfo = namedtuple("RealesrganModelInfo", ["name", "location", "model", "netscale"])
-
 realesrgan_models = []
 have_realesrgan = False
-RealESRGANer_constructor = None
+
+
+def get_realesrgan_models():
+    try:
+        from basicsr.archs.rrdbnet_arch import RRDBNet
+        from realesrgan import RealESRGANer
+        from realesrgan.archs.srvgg_arch import SRVGGNetCompact
+        models = [
+            RealesrganModelInfo(
+                name="Real-ESRGAN General x4x3",
+                location="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth",
+                netscale=4,
+                model=lambda: SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
+            ),
+            RealesrganModelInfo(
+                name="Real-ESRGAN General WDN x4x3",
+                location="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth",
+                netscale=4,
+                model=lambda: SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
+            ),
+            RealesrganModelInfo(
+                name="Real-ESRGAN AnimeVideo",
+                location="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth",
+                netscale=4,
+                model=lambda: SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=16, upscale=4, act_type='prelu')
+            ),
+            RealesrganModelInfo(
+                name="Real-ESRGAN 4x plus",
+                location="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth",
+                netscale=4,
+                model=lambda: RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
+            ),
+            RealesrganModelInfo(
+                name="Real-ESRGAN 4x plus anime 6B",
+                location="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth",
+                netscale=4,
+                model=lambda: RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
+            ),
+            RealesrganModelInfo(
+                name="Real-ESRGAN 2x plus",
+                location="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth",
+                netscale=2,
+                model=lambda: RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=2)
+            ),
+        ]
+        return models
+    except Exception as e:
+        print("Error makeing Real-ESRGAN midels list:", file=sys.stderr)
+        print(traceback.format_exc(), file=sys.stderr)
 
 
 class UpscalerRealESRGAN(modules.images.Upscaler):
@@ -27,35 +76,18 @@ class UpscalerRealESRGAN(modules.images.Upscaler):
 def setup_realesrgan():
     global realesrgan_models
     global have_realesrgan
-    global RealESRGANer_constructor
 
     try:
         from basicsr.archs.rrdbnet_arch import RRDBNet
         from realesrgan import RealESRGANer
         from realesrgan.archs.srvgg_arch import SRVGGNetCompact
 
-        realesrgan_models = [
+        realesrgan_models = get_realesrgan_models()
-            RealesrganModelInfo(
-                name="Real-ESRGAN 4x plus",
-                location="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth",
-                netscale=4, model=lambda: RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
-            ),
-            RealesrganModelInfo(
-                name="Real-ESRGAN 4x plus anime 6B",
-                location="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth",
-                netscale=4, model=lambda: RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4)
-            ),
-            RealesrganModelInfo(
-                name="Real-ESRGAN 2x plus",
-                location="https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth",
-                netscale=2, model=lambda: RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=2)
-            ),
-        ]
         have_realesrgan = True
-        RealESRGANer_constructor = RealESRGANer
 
         for i, model in enumerate(realesrgan_models):
-            modules.shared.sd_upscalers.append(UpscalerRealESRGAN(model.netscale, i))
+            if model.name in opts.realesrgan_enabled_models:
+                modules.shared.sd_upscalers.append(UpscalerRealESRGAN(model.netscale, i))
 
     except Exception:
         print("Error importing Real-ESRGAN:", file=sys.stderr)
@@ -66,13 +98,13 @@ def setup_realesrgan():
 
 
 def upscale_with_realesrgan(image, RealESRGAN_upscaling, RealESRGAN_model_index):
-    if not have_realesrgan or RealESRGANer_constructor is None:
+    if not have_realesrgan:
         return image
 
     info = realesrgan_models[RealESRGAN_model_index]
 
     model = info.model()
-    upsampler = RealESRGANer_constructor(
+    upsampler = RealESRGANer(
         scale=info.netscale,
         model_path=info.location,
         model=model,

modules/shared.py

@@ -95,6 +95,11 @@ face_restorers = []
 modules.sd_models.list_models()
 
 
+def realesrgan_models_names():
+    import modules.realesrgan_model
+    return [x.name for x in modules.realesrgan_model.get_realesrgan_models()]
+
+
 class Options:
     class OptionInfo:
         def __init__(self, default=None, label="", component=None, component_args=None, onchange=None):
@@ -142,14 +147,12 @@ class Options:
         "save_txt": OptionInfo(False, "Create a text file next to every image with generation parameters."),
         "ESRGAN_tile": OptionInfo(192, "Tile size for ESRGAN upscalers. 0 = no tiling.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
         "ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}),
+        "realesrgan_enabled_models": OptionInfo(["Real-ESRGAN 4x plus", "Real-ESRGAN 4x plus anime 6B"],"Select which RealESRGAN models to show in the web UI. (Requires restart)", gr.CheckboxGroup, lambda: {"choices": realesrgan_models_names()}),
         "SWIN_tile": OptionInfo(192, "Tile size for all SwinIR.", gr.Slider, {"minimum": 16, "maximum": 512, "step": 16}),
         "SWIN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for SwinIR. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}),
-        "ldsr_steps": OptionInfo(100, "LDSR processing steps. Lower = faster",
+        "ldsr_steps": OptionInfo(100, "LDSR processing steps. Lower = faster", gr.Slider, {"minimum": 1, "maximum": 200, "step": 1}),
-                                          gr.Slider, {"minimum": 1, "maximum": 200, "step": 1}),
+        "ldsr_pre_down":OptionInfo(1, "LDSR Pre-process downssample scale. 1 = no down-sampling, 4 = 1/4 scale.", gr.Slider, {"minimum": 1, "maximum": 4, "step": 1}),
-        "ldsr_pre_down":OptionInfo(1, "LDSR Pre-process downssample scale. 1 = no down-sampling, 4 = 1/4 scale.",
+        "ldsr_post_down":OptionInfo(1, "LDSR Post-process down-sample scale. 1 = no down-sampling, 4 = 1/4 scale.", gr.Slider, {"minimum": 1, "maximum": 4, "step": 1}),
-                                          gr.Slider, {"minimum": 1, "maximum": 4, "step": 1}),
-        "ldsr_post_down":OptionInfo(1, "LDSR Post-process down-sample scale. 1 = no down-sampling, 4 = 1/4 scale.",
-                                          gr.Slider, {"minimum": 1, "maximum": 4, "step": 1}),
         "random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}),
         "upscale_at_full_resolution_padding": OptionInfo(16, "Inpainting at full resolution: padding, in pixels, for the masked region.", gr.Slider, {"minimum": 0, "maximum": 128, "step": 4}),
         "upscaler_for_hires_fix": OptionInfo(None, "Upscaler for highres. fix", gr.Radio, lambda: {"choices": [x.name for x in sd_upscalers]}),

modules/ui.py

@@ -350,8 +350,15 @@ def create_toprow(is_img2img):
 
         with gr.Column(scale=1):
             with gr.Row():
+                interrupt = gr.Button('Interrupt', elem_id="interrupt")
                 submit = gr.Button('Generate', elem_id="generate", variant='primary')
 
+                interrupt.click(
+                    fn=lambda: shared.state.interrupt(),
+                    inputs=[],
+                    outputs=[],
+                )
+
             with gr.Row():
                 if is_img2img:
                     interrogate = gr.Button('Interrogate', elem_id="interrogate")
@@ -386,6 +393,15 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
         txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, txt2img_prompt_style_apply, txt2img_save_style = create_toprow(is_img2img=False)
         dummy_component = gr.Label(visible=False)
 
+        with gr.Row(elem_id='progressRow'):
+              with gr.Column(scale=1):
+                columnEmpty = "Empty"
+
+              with gr.Column(scale=1):
+                progressbar = gr.HTML(elem_id="progressbar")
+                txt2img_preview = gr.Image(elem_id='txt2img_preview', visible=False)
+                setup_progressbar(progressbar, txt2img_preview)
+
         with gr.Row().style(equal_height=False):
             with gr.Column(variant='panel'):
                 steps = gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=20)
@@ -416,21 +432,17 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                     custom_inputs = modules.scripts.scripts_txt2img.setup_ui(is_img2img=False)
 
             with gr.Column(variant='panel'):
-                progressbar = gr.HTML(elem_id="progressbar")
 
                 with gr.Group():
                     txt2img_preview = gr.Image(elem_id='txt2img_preview', visible=False)
                     txt2img_gallery = gr.Gallery(label='Output', elem_id='txt2img_gallery').style(grid=4)
 
-                setup_progressbar(progressbar, txt2img_preview)
-
                 with gr.Group():
                     with gr.Row():
                         save = gr.Button('Save')
                         send_to_img2img = gr.Button('Send to img2img')
                         send_to_inpaint = gr.Button('Send to inpaint')
                         send_to_extras = gr.Button('Send to extras')
-                        interrupt = gr.Button('Interrupt')
 
                 with gr.Group():
                     html_info = gr.HTML()
@@ -479,12 +491,6 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                 outputs=[hr_options],
             )
 
-            interrupt.click(
-                fn=lambda: shared.state.interrupt(),
-                inputs=[],
-                outputs=[],
-            )
-
             save.click(
                 fn=wrap_gradio_call(save_files),
                 _js="(x, y, z) => [x, y, selected_gallery_index()]",
@@ -513,6 +519,15 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
     with gr.Blocks(analytics_enabled=False) as img2img_interface:
         img2img_prompt, roll, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_prompt_style_apply, img2img_save_style = create_toprow(is_img2img=True)
 
+        with gr.Row(elem_id='progressRow'):
+              with gr.Column(scale=1):
+                columnEmpty = "Empty"
+
+              with gr.Column(scale=1):
+                progressbar = gr.HTML(elem_id="progressbar")
+                img2img_preview = gr.Image(elem_id='img2img_preview', visible=False)
+                setup_progressbar(progressbar, img2img_preview)
+        
         with gr.Row().style(equal_height=False):
             with gr.Column(variant='panel'):
                 with gr.Group():
@@ -561,21 +576,17 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                     custom_inputs = modules.scripts.scripts_img2img.setup_ui(is_img2img=True)
 
             with gr.Column(variant='panel'):
-                progressbar = gr.HTML(elem_id="progressbar")
 
                 with gr.Group():
                     img2img_preview = gr.Image(elem_id='img2img_preview', visible=False)
                     img2img_gallery = gr.Gallery(label='Output', elem_id='img2img_gallery').style(grid=4)
 
-                setup_progressbar(progressbar, img2img_preview)
-
                 with gr.Group():
                     with gr.Row():
                         save = gr.Button('Save')
                         img2img_send_to_img2img = gr.Button('Send to img2img')
                         img2img_send_to_inpaint = gr.Button('Send to inpaint')
                         img2img_send_to_extras = gr.Button('Send to extras')
-                        interrupt = gr.Button('Interrupt')
                         img2img_save_style = gr.Button('Save prompt as style')
 
 
@@ -689,12 +700,6 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                 outputs=[img2img_prompt],
             )
 
-            interrupt.click(
-                fn=lambda: shared.state.interrupt(),
-                inputs=[],
-                outputs=[],
-            )
-
             save.click(
                 fn=wrap_gradio_call(save_files),
                 _js="(x, y, z) => [x, y, selected_gallery_index()]",

requirements_versions.txt

@@ -1,18 +1,17 @@
 transformers==4.19.2
-diffusers==0.2.4
+diffusers==0.3.0
-basicsr==1.3.5
+basicsr==1.4.2
-gfpgan
+gfpgan==1.3.8
 gradio==3.3.1
 numpy==1.23.3
 Pillow==9.2.0
-realesrgan==0.2.5.0
+realesrgan==0.3.0
 torch
-transformers==4.19.2
+omegaconf==2.2.3
-omegaconf==2.1.1
+pytorch_lightning==1.7.6
-pytorch_lightning==1.7.2
 scikit-image==0.19.2
 fonts
 font-roboto
-timm==0.4.12
+timm==0.6.7
-fairscale==0.4.4
+fairscale==0.4.9
 piexif==1.1.3

style.css

@@ -86,7 +86,7 @@
 }
 
 #style_pos_col, #style_neg_col{
-    min-width: 4em !important;
+    min-width: 8em !important;
 }
 
 #style_index, #style2_index{
@@ -208,11 +208,19 @@ input[type="range"]{
   position: absolute;
   z-index: 1000;
   right: 0;
+  padding-left: 5px;
+  padding-right: 5px;
+  display: block;
+}
+
+#progressRow{
+  margin-bottom: 10px;
+  margin-top: -18px;
 }
 
 .progressDiv{
   width: 100%;
-  height: 30px;
+  height: 20px;
   background: #b4c0cc;
   border-radius: 8px;
 }
@@ -223,11 +231,11 @@ input[type="range"]{
 
 .progressDiv .progress{
   width: 0%;
-  height: 30px;
+  height: 20px;
   background: #0060df;
   color: white;
   font-weight: bold;
-  line-height: 30px;
+  line-height: 20px;
   padding: 0 8px 0 0;
   text-align: right;
   border-radius: 8px;
@@ -337,5 +345,14 @@ input[type="range"]{
     background:rgba(255, 0, 0, 0.3);
     z-index: 900;
     pointer-events:none;
-    display:none;
+    display:none
+}
+
+#interrupt{
+  position: absolute;
+  width: 100%;
+  height: 72px;
+  background: #b4c0cc;
+  border-radius: 8px;
+  display: none;
 }