fixes?

app.py

@@ -6,7 +6,6 @@ import utils
 
 is_colab = utils.is_google_colab()
 
-
 class Model:
     def __init__(self, name, path, prefix):
         self.name = name
@@ -15,7 +14,6 @@ class Model:
         self.pipe_t2i = None
         self.pipe_i2i = None
 
-
 models = [
     Model("Beeple", "riccardogiorato/beeple-diffusion", "beeple style "),
     Model("Avatar", "riccardogiorato/avatar-diffusion", "avatartwow style "),
@@ -23,8 +21,8 @@ models = [
     Model("Poolsuite", "prompthero/poolsuite", "poolsuite style "),
     Model("Robo Diffusion", "nousr/robo-diffusion", ""),
     Model("Guohua", "Langboat/Guohua-Diffusion", "guohua style ")
-]
-
+  ]
+     
 scheduler = DPMSolverMultistepScheduler(
     beta_start=0.00085,
     beta_end=0.012,
@@ -38,51 +36,53 @@ scheduler = DPMSolverMultistepScheduler(
     lower_order_final=True,
 )
 
+custom_model = None
+if is_colab:
+  models.insert(0, Model("Custom model", "", ""))
+  custom_model = models[0]
+
 last_mode = "txt2img"
-current_model = models[0]
+current_model = models[1] if is_colab else models[0]
 current_model_path = current_model.path
 
 if is_colab:
-    pipe = StableDiffusionPipeline.from_pretrained(
-        current_model.path, torch_dtype=torch.float16, scheduler=scheduler)
-
-else:  # download all models
-    vae = AutoencoderKL.from_pretrained(
-        current_model.path, subfolder="vae", torch_dtype=torch.float16)
-    for model in models:
-        try:
-            unet = UNet2DConditionModel.from_pretrained(
-                model.path, subfolder="unet", torch_dtype=torch.float16)
-            model.pipe_t2i = StableDiffusionPipeline.from_pretrained(
-                model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler)
-            model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(
-                model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler)
-        except:
-            models.remove(model)
-    pipe = models[0].pipe_t2i
-
+  pipe = StableDiffusionPipeline.from_pretrained(current_model.path, torch_dtype=torch.float16, scheduler=scheduler)
+
+else: # download all models
+  vae = AutoencoderKL.from_pretrained(current_model.path, subfolder="vae", torch_dtype=torch.float16)
+  for model in models:
+    try:
+        unet = UNet2DConditionModel.from_pretrained(model.path, subfolder="unet", torch_dtype=torch.float16)
+        model.pipe_t2i = StableDiffusionPipeline.from_pretrained(model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler)
+        model.pipe_i2i = StableDiffusionImg2ImgPipeline.from_pretrained(model.path, unet=unet, vae=vae, torch_dtype=torch.float16, scheduler=scheduler)
+    except:
+        models.remove(model)
+  pipe = models[0].pipe_t2i
+  
 if torch.cuda.is_available():
-    pipe = pipe.to("cuda")
+  pipe = pipe.to("cuda")
 
 device = "GPU 🔥" if torch.cuda.is_available() else "CPU 🥶"
 
+def custom_model_changed(path):
+  models[0].path = path
+  global current_model
+  current_model = models[0]
 
 def inference(model_name, prompt, guidance, steps, width=512, height=512, seed=0, img=None, strength=0.5, neg_prompt=""):
 
-    global current_model
-    for model in models:
-        if model.name == model_name:
-            current_model = model
-            model_path = current_model.path
-
-    generator = torch.Generator('cuda').manual_seed(
-        seed) if seed != 0 else None
+  global current_model
+  for model in models:
+    if model.name == model_name:
+      current_model = model
+      model_path = current_model.path
 
-    if img is not None:
-        return img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height, generator)
-    else:
-        return txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator)
+  generator = torch.Generator('cuda').manual_seed(seed) if seed != 0 else None
 
+  if img is not None:
+    return img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height, generator)
+  else:
+    return txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator)
 
 def txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, generator=None):
 
@@ -92,31 +92,29 @@ def txt_to_img(model_path, prompt, neg_prompt, guidance, steps, width, height, g
     if model_path != current_model_path or last_mode != "txt2img":
         current_model_path = model_path
 
-        if is_colab:
-            pipe = StableDiffusionPipeline.from_pretrained(
-                current_model_path, torch_dtype=torch.float16, scheduler=scheduler)
+        if is_colab or current_model == custom_model:
+          pipe = StableDiffusionPipeline.from_pretrained(current_model_path, torch_dtype=torch.float16, scheduler=scheduler)
         else:
-            pipe.to("cpu")
-            pipe = current_model.pipe_t2i
+          pipe.to("cpu")
+          pipe = current_model.pipe_t2i
 
         if torch.cuda.is_available():
-            pipe = pipe.to("cuda")
+          pipe = pipe.to("cuda")
         last_mode = "txt2img"
 
-    prompt = current_model.prefix + prompt
+    prompt = current_model.prefix + prompt  
     result = pipe(
-        prompt,
-        negative_prompt=neg_prompt,
-        # num_images_per_prompt=n_images,
-        num_inference_steps=int(steps),
-        guidance_scale=guidance,
-        width=width,
-        height=height,
-        generator=generator)
-
+      prompt,
+      negative_prompt = neg_prompt,
+      # num_images_per_prompt=n_images,
+      num_inference_steps = int(steps),
+      guidance_scale = guidance,
+      width = width,
+      height = height,
+      generator = generator)
+    
     return replace_nsfw_images(result)
 
-
 def img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, width, height, generator=None):
 
     global last_mode
@@ -125,126 +123,118 @@ def img_to_img(model_path, prompt, neg_prompt, img, strength, guidance, steps, w
     if model_path != current_model_path or last_mode != "img2img":
         current_model_path = model_path
 
-        if is_colab:
-            pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
-                current_model_path, torch_dtype=torch.float16, scheduler=scheduler)
+        if is_colab or current_model == custom_model:
+          pipe = StableDiffusionImg2ImgPipeline.from_pretrained(current_model_path, torch_dtype=torch.float16, scheduler=scheduler)
         else:
-            pipe.to("cpu")
-            pipe = current_model.pipe_i2i
-
+          pipe.to("cpu")
+          pipe = current_model.pipe_i2i
+        
         if torch.cuda.is_available():
-            pipe = pipe.to("cuda")
+          pipe = pipe.to("cuda")
         last_mode = "img2img"
 
     prompt = current_model.prefix + prompt
     ratio = min(height / img.height, width / img.width)
-    img = img.resize(
-        (int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
+    img = img.resize((int(img.width * ratio), int(img.height * ratio)), Image.LANCZOS)
     result = pipe(
         prompt,
-        negative_prompt=neg_prompt,
+        negative_prompt = neg_prompt,
         # num_images_per_prompt=n_images,
-        init_image=img,
-        num_inference_steps=int(steps),
-        strength=strength,
-        guidance_scale=guidance,
-        width=width,
-        height=height,
-        generator=generator)
-
+        init_image = img,
+        num_inference_steps = int(steps),
+        strength = strength,
+        guidance_scale = guidance,
+        width = width,
+        height = height,
+        generator = generator)
+        
     return replace_nsfw_images(result)
 
-
 def replace_nsfw_images(results):
     for i in range(len(results.images)):
-        if results.nsfw_content_detected[i]:
-            results.images[i] = Image.open("nsfw.png")
+      if results.nsfw_content_detected[i]:
+        results.images[i] = Image.open("nsfw.png")
     return results.images[0]
 
-
-css = """.playground-diffusion-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.playground-diffusion-div div h1{font-weight:900;margin-bottom:7px}.playground-diffusion-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem}
+css = """.finetuned-diffusion-div div{display:inline-flex;align-items:center;gap:.8rem;font-size:1.75rem}.finetuned-diffusion-div div h1{font-weight:900;margin-bottom:7px}.finetuned-diffusion-div p{margin-bottom:10px;font-size:94%}a{text-decoration:underline}.tabs{margin-top:0;margin-bottom:0}#gallery{min-height:20rem}
 """
 with gr.Blocks(css=css) as demo:
     gr.HTML(
         f"""
-            <div class="playground-diffusion-div">
+            <div class="finetuned-diffusion-div">
               <div>
                 <h1>Playground Diffusion</h1>
               </div>
               <p>
                Demo for multiple fine-tuned Stable Diffusion models, trained on different styles: <br>
-               <a href="https://huggingface.co/riccardogiorato/avatar-diffusion">Avatar</a>,<br/>
+                <a href="https://huggingface.co/riccardogiorato/avatar-diffusion">Avatar</a>,<br/>
                <a href="https://huggingface.co/riccardogiorato/beeple-diffusion">Beeple</a>,<br/>
                <a href="https://huggingface.co/s3nh/beksinski-style-stable-diffusion">Beksinski</a>,<br/>
                Diffusers 🧨 SD model hosted on HuggingFace 🤗.
-              </p>
                Running on <b>{device}</b>{(" in a <b>Google Colab</b>." if is_colab else "")}
               </p>
             </div>
         """
     )
     with gr.Row():
-
+        
         with gr.Column(scale=55):
+          with gr.Group():
+              model_name = gr.Dropdown(label="Model", choices=[m.name for m in models], value=current_model.name)
+              with gr.Box(visible=False) as custom_model_group:
+                custom_model_path = gr.Textbox(label="Custom model path", placeholder="Path to model, e.g. nitrosocke/Arcane-Diffusion", interactive=True)
+                gr.HTML("<div><font size='2'>Custom models have to be downloaded first, so give it some time.</font></div>")
+              
+              with gr.Row():
+                prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,placeholder="Enter prompt. Style applied automatically").style(container=False)
+                generate = gr.Button(value="Generate").style(rounded=(False, True, True, False))
+
+
+              image_out = gr.Image(height=512)
+              # gallery = gr.Gallery(
+              #     label="Generated images", show_label=False, elem_id="gallery"
+              # ).style(grid=[1], height="auto")
+
+        with gr.Column(scale=45):
+          with gr.Tab("Options"):
             with gr.Group():
-                model_name = gr.Dropdown(label="Model", choices=[
-                                         m.name for m in models], value=current_model.name)
+              neg_prompt = gr.Textbox(label="Negative prompt", placeholder="What to exclude from the image")
 
-                with gr.Row():
-                    prompt = gr.Textbox(label="Prompt", show_label=False, max_lines=2,
-                                        placeholder="Enter prompt. Style applied automatically").style(container=False)
-                    generate = gr.Button(value="Generate").style(
-                        rounded=(False, True, True, False))
+              # n_images = gr.Slider(label="Images", value=1, minimum=1, maximum=4, step=1)
 
-                image_out = gr.Image(height=512)
-                # gallery = gr.Gallery(
-                #     label="Generated images", show_label=False, elem_id="gallery"
-                # ).style(grid=[1], height="auto")
+              with gr.Row():
+                guidance = gr.Slider(label="Guidance scale", value=7.5, maximum=15)
+                steps = gr.Slider(label="Steps", value=25, minimum=2, maximum=75, step=1)
 
-        with gr.Column(scale=45):
-            with gr.Tab("Options"):
-                with gr.Group():
-                    neg_prompt = gr.Textbox(
-                        label="Negative prompt", placeholder="What to exclude from the image")
-
-                    # n_images = gr.Slider(label="Images", value=1, minimum=1, maximum=4, step=1)
-
-                    with gr.Row():
-                        guidance = gr.Slider(
-                            label="Guidance scale", value=7.5, maximum=15)
-                        steps = gr.Slider(
-                            label="Steps", value=25, minimum=2, maximum=75, step=1)
-
-                    with gr.Row():
-                        width = gr.Slider(
-                            label="Width", value=512, minimum=64, maximum=1024, step=8)
-                        height = gr.Slider(
-                            label="Height", value=512, minimum=64, maximum=1024, step=8)
-
-                    seed = gr.Slider(
-                        0, 2147483647, label='Seed (0 = random)', value=0, step=1)
-
-            with gr.Tab("Image to image"):
-                with gr.Group():
-                    image = gr.Image(label="Image", height=256,
-                                     tool="editor", type="pil")
-                    strength = gr.Slider(
-                        label="Transformation strength", minimum=0, maximum=1, step=0.01, value=0.5)
-
-    inputs = [model_name, prompt, guidance, steps,
-              width, height, seed, image, strength, neg_prompt]
+              with gr.Row():
+                width = gr.Slider(label="Width", value=512, minimum=64, maximum=1024, step=8)
+                height = gr.Slider(label="Height", value=512, minimum=64, maximum=1024, step=8)
+
+              seed = gr.Slider(0, 2147483647, label='Seed (0 = random)', value=0, step=1)
+
+          with gr.Tab("Image to image"):
+              with gr.Group():
+                image = gr.Image(label="Image", height=256, tool="editor", type="pil")
+                strength = gr.Slider(label="Transformation strength", minimum=0, maximum=1, step=0.01, value=0.5)
+
+    if is_colab:
+      model_name.change(lambda x: gr.update(visible = x == models[0].name), inputs=model_name, outputs=custom_model_group)
+      custom_model_path.change(custom_model_changed, inputs=custom_model_path, outputs=None)
+    # n_images.change(lambda n: gr.Gallery().style(grid=[2 if n > 1 else 1], height="auto"), inputs=n_images, outputs=gallery)
+
+    inputs = [model_name, prompt, guidance, steps, width, height, seed, image, strength, neg_prompt]
     prompt.submit(inference, inputs=inputs, outputs=image_out)
     generate.click(inference, inputs=inputs, outputs=image_out)
 
     ex = gr.Examples([
-        [models[0].name, "Neon techno-magic robot with spear pierces an ancient beast, hyperrealism, no blur, 4k resolution, ultra detailed", 7.5, 50],
-        [models[0].name, "halfturn portrait of a big crystal face of a beautiful abstract ancient Egyptian elderly shaman woman, made of iridescent golden crystals, half - turn, bottom view, ominous, intricate, studio, art by anthony macbain and greg rutkowski and alphonse mucha, concept art, 4k, sharp focus", 7.5, 25],
+        [models[1].name, "Neon techno-magic robot with spear pierces an ancient beast, hyperrealism, no blur, 4k resolution, ultra detailed", 7.5, 50],
+        [models[1].name, "halfturn portrait of a big crystal face of a beautiful abstract ancient Egyptian elderly shaman woman, made of iridescent golden crystals, half - turn, bottom view, ominous, intricate, studio, art by anthony macbain and greg rutkowski and alphonse mucha, concept art, 4k, sharp focus", 7.5, 25],
     ], [model_name, prompt, guidance, steps, seed], image_out, inference, cache_examples=False)
 
     gr.HTML("""
-      <p>Models by <a href="https://huggingface.co/riccardogiorato">@riccardogiorato</a><br></p>
+       <p>Models by <a href="https://huggingface.co/riccardogiorato">@riccardogiorato</a><br></p>
     """)
 
 if not is_colab:
-    demo.queue(concurrency_count=1)
-demo.launch(debug=is_colab, share=is_colab)
+  demo.queue(concurrency_count=1)
+demo.launch(debug=is_colab, share=is_colab)