Merge branch 'master' into test_resolve_conflicts

launch.py

@@ -104,6 +104,7 @@ def prepare_enviroment():
     args = shlex.split(commandline_args)
 
     args, skip_torch_cuda_test = extract_arg(args, '--skip-torch-cuda-test')
+    args, reinstall_xformers = extract_arg(args, '--reinstall-xformers')
     xformers = '--xformers' in args
     deepdanbooru = '--deepdanbooru' in args
     ngrok = '--ngrok' in args
@@ -128,9 +129,9 @@ def prepare_enviroment():
     if not is_installed("clip"):
         run_pip(f"install {clip_package}", "clip")
 
-    if not is_installed("xformers") and xformers and platform.python_version().startswith("3.10"):
+    if (not is_installed("xformers") or reinstall_xformers) and xformers and platform.python_version().startswith("3.10"):
         if platform.system() == "Windows":
-            run_pip("install https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/c/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl", "xformers")
+            run_pip("install -U -I --no-deps https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/f/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl", "xformers")
         elif platform.system() == "Linux":
             run_pip("install xformers", "xformers")
 

modules/hypernetworks/hypernetwork.py

@@ -272,15 +272,17 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
             optimizer.zero_grad()
             loss.backward()
             optimizer.step()
-
-        pbar.set_description(f"loss: {losses.mean():.7f}")
+        mean_loss = losses.mean()
+        if torch.isnan(mean_loss):
+            raise RuntimeError("Loss diverged.")
+        pbar.set_description(f"loss: {mean_loss:.7f}")
 
         if hypernetwork.step > 0 and hypernetwork_dir is not None and hypernetwork.step % save_hypernetwork_every == 0:
             last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name}-{hypernetwork.step}.pt')
             hypernetwork.save(last_saved_file)
 
         textual_inversion.write_loss(log_directory, "hypernetwork_loss.csv", hypernetwork.step, len(ds), {
-            "loss": f"{losses.mean():.7f}",
+            "loss": f"{mean_loss:.7f}",
             "learn_rate": scheduler.learn_rate
         })
 
@@ -328,7 +330,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
 
         shared.state.textinfo = f"""
 <p>
-Loss: {losses.mean():.7f}<br/>
+Loss: {mean_loss:.7f}<br/>
 Step: {hypernetwork.step}<br/>
 Last prompt: {html.escape(entries[0].cond_text)}<br/>
 Last saved embedding: {html.escape(last_saved_file)}<br/>

modules/sd_hijack.py

@@ -29,8 +29,8 @@ def apply_optimizations():
 
     ldm.modules.diffusionmodules.model.nonlinearity = silu
 
-    if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (
-            6, 0) <= torch.cuda.get_device_capability(shared.device) <= (8, 6)):
+
+    if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)):
         print("Applying xformers cross attention optimization.")
         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
         ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward

modules/textual_inversion/textual_inversion.py

@@ -88,9 +88,9 @@ class EmbeddingDatabase:
 
             data = []
 
-            if filename.upper().endswith('.PNG'):
+            if os.path.splitext(filename.upper())[-1] in ['.PNG', '.WEBP', '.JXL', '.AVIF']:
                 embed_image = Image.open(path)
-                if 'sd-ti-embedding' in embed_image.text:
+                if hasattr(embed_image, 'text') and 'sd-ti-embedding' in embed_image.text:
                     data = embedding_from_b64(embed_image.text['sd-ti-embedding'])
                     name = data.get('name', name)
                 else:
@@ -242,6 +242,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
 
     last_saved_file = "<none>"
     last_saved_image = "<none>"
+    embedding_yet_to_be_embedded = False
 
     ititial_step = embedding.step or 0
     if ititial_step > steps:
@@ -283,6 +284,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
         if embedding.step > 0 and embedding_dir is not None and embedding.step % save_embedding_every == 0:
             last_saved_file = os.path.join(embedding_dir, f'{embedding_name}-{embedding.step}.pt')
             embedding.save(last_saved_file)
+            embedding_yet_to_be_embedded = True
 
         write_loss(log_directory, "textual_inversion_loss.csv", embedding.step, len(ds), {
             "loss": f"{losses.mean():.7f}",
@@ -320,7 +322,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
 
             shared.state.current_image = image
 
-            if save_image_with_stored_embedding and os.path.exists(last_saved_file):
+            if save_image_with_stored_embedding and os.path.exists(last_saved_file) and embedding_yet_to_be_embedded:
 
                 last_saved_image_chunks = os.path.join(images_embeds_dir, f'{embedding_name}-{embedding.step}.png')
 
@@ -329,15 +331,22 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
                 info.add_text("sd-ti-embedding", embedding_to_b64(data))
 
                 title = "<{}>".format(data.get('name', '???'))
+
+                try:
+                    vectorSize = list(data['string_to_param'].values())[0].shape[0]
+                except Exception as e:
+                    vectorSize = '?'
+
                 checkpoint = sd_models.select_checkpoint()
                 footer_left = checkpoint.model_name
                 footer_mid = '[{}]'.format(checkpoint.hash)
-                footer_right = '{}'.format(embedding.step)
+                footer_right = '{}v {}s'.format(vectorSize, embedding.step)
 
                 captioned_image = caption_image_overlay(image, title, footer_left, footer_mid, footer_right)
                 captioned_image = insert_image_data_embed(captioned_image, data)
 
                 captioned_image.save(last_saved_image_chunks, "PNG", pnginfo=info)
+                embedding_yet_to_be_embedded = False
 
             image.save(last_saved_image)
 

modules/ui.py

@@ -158,10 +158,7 @@ def save_files(js_data, images, do_make_zip, index):
             writer.writerow(["prompt", "seed", "width", "height", "sampler", "cfgs", "steps", "filename", "negative_prompt"])
 
         for image_index, filedata in enumerate(images, start_index):
-            if filedata.startswith("data:image/png;base64,"):
-                filedata = filedata[len("data:image/png;base64,"):]
-
-            image = Image.open(io.BytesIO(base64.decodebytes(filedata.encode('utf-8'))))
+            image = image_from_url_text(filedata)
 
             is_grid = image_index < p.index_of_first_image
             i = 0 if is_grid else (image_index - p.index_of_first_image)
@@ -638,7 +635,7 @@ def create_ui(wrap_gradio_gpu_call):
                     txt2img_preview = gr.Image(elem_id='txt2img_preview', visible=False)
                     txt2img_gallery = gr.Gallery(label='Output', show_label=False, elem_id='txt2img_gallery').style(grid=4)
 
-                with gr.Group():
+                with gr.Column():
                     with gr.Row():
                         save = gr.Button('Save')
                         send_to_img2img = gr.Button('Send to img2img')
@@ -862,7 +859,7 @@ def create_ui(wrap_gradio_gpu_call):
                     img2img_preview = gr.Image(elem_id='img2img_preview', visible=False)
                     img2img_gallery = gr.Gallery(label='Output', show_label=False, elem_id='img2img_gallery').style(grid=4)
 
-                with gr.Group():
+                with gr.Column():
                     with gr.Row():
                         save = gr.Button('Save')
                         img2img_send_to_img2img = gr.Button('Send to img2img')

style.css

@@ -237,13 +237,6 @@ fieldset span.text-gray-500, .gr-block.gr-box span.text-gray-500,  label.block s
     margin: 0;
 }
 
-.gr-panel div.flex-col div.justify-between div{
-  position: absolute;
-  top: -0.1em;
-  right: 1em;
-  padding: 0 0.5em;
-}
-
 #settings .gr-panel div.flex-col div.justify-between div{
     position: relative;
     z-index: 200;
@@ -316,6 +309,8 @@ input[type="range"]{
   height: 100%;
   overflow: auto;
   background-color: rgba(20, 20, 20, 0.95);
+  user-select: none;
+  -webkit-user-select: none;
 }
 
 .modalControls {
@@ -520,4 +515,4 @@ img2maskimg, #img2maskimg > .h-60, #img2maskimg > .h-60 > div, #img2maskimg > .h
     height: 480px !important;
     max-height: 480px !important;
     min-height: 480px !important;
-}
+}