Upload folder using huggingface_hub

gradio_sketch2imagehd.py

@@ -112,42 +112,6 @@ def normalize_image(image, range_from=(-1, 1)):
     
     return image_t
 
-
-def run(image, prompt, prompt_template, style_name, seed, val_r):
-    print(f"prompt: {prompt}")
-    print("sketch updated")
-    print(image)
-    if image is None:
-        ones = Image.new("L", (1024, 1024), 255)
-        temp_uri = pil_image_to_data_uri(ones)
-        return ones, gr.update(link=temp_uri), gr.update(link=temp_uri)
-    print(f"Input Image Size: {image.size}")
-    prompt = prompt_template.replace("{prompt}", prompt)
-    image = image.convert("RGB")
-    #image_t = normalize_image(image, range_from=(-1, 1))
-    
-    print(f"r_val={val_r}, seed={seed}")
-    image_t = F.to_tensor(image) < 0.5
-    with torch.no_grad():
-      
-        c_t = image_t.unsqueeze(0).cuda().float()
-        torch.manual_seed(seed)
-        B, C, H, W = c_t.shape
-        noise = torch.randn((1, 4, H // 8, W // 8), device=c_t.device)
-
-        print("Calling Pix2Pix model... ct: {}, prompt: {}, deterministic: False, r: {}, noise_map: {}".format(c_t.shape, prompt, val_r, noise.shape))  
-        output_image = pix2pix_model(c_t, prompt, deterministic=False, r=val_r, noise_map=noise)
-    output_pil = F.to_pil_image(output_image[0].cpu() * 0.5 + 0.5)
-    input_sketch_uri = pil_image_to_data_uri(Image.fromarray(255 - np.array(image)))
-    output_image_uri = pil_image_to_data_uri(output_pil)
-    
-    print(f"Output Image Size: {output_pil.size}")
-    return (
-        output_pil,
-        gr.update(link=input_sketch_uri),
-        gr.update(link=output_image_uri),
-    )
-
 def run(image, prompt, prompt_template, style_name, seed, val_r):
     """Runs the main image processing pipeline."""
     logging.debug("Running model inference...")
@@ -207,6 +171,12 @@ def run(image, prompt, prompt_template, style_name, seed, val_r):
 
 def gradio_interface(image, prompt, style_name, seed, val_r):
     """Gradio interface function to handle inputs and generate outputs."""
+    # Endpoint: `image` - Input image from user (Sketch Image)
+    # Endpoint: `prompt` - Text prompt (optional)
+    # Endpoint: `style_name` - Selected style from dropdown
+    # Endpoint: `seed` - Seed for reproducibility
+    # Endpoint: `val_r` - Sketch guidance value
+
     prompt_template = STYLES.get(style_name, STYLES[DEFAULT_STYLE_NAME])
     result_image = run(image, prompt, prompt_template, style_name, seed, val_r)
     return result_image
@@ -215,13 +185,13 @@ def gradio_interface(image, prompt, style_name, seed, val_r):
 interface = gr.Interface(
     fn=gradio_interface,
     inputs=[
-        gr.Image(source="upload", type="pil", label="Sketch Image"),
-        gr.Textbox(lines=2, placeholder="Enter a text prompt (optional)", label="Prompt"),
-        gr.Dropdown(choices=list(STYLES.keys()), value=DEFAULT_STYLE_NAME, label="Style"),
-        gr.Slider(minimum=0, maximum=MAX_SEED, step=1, default=DEFAULT_SEED, label="Seed"),
-        gr.Slider(minimum=0.0, maximum=1.0, step=0.01, default=VAL_R_DEFAULT, label="Sketch Guidance")
+        gr.Image(source="upload", type="pil", label="Sketch Image"),  # Endpoint: `image`
+        gr.Textbox(lines=2, placeholder="Enter a text prompt (optional)", label="Prompt"),  # Endpoint: `prompt`
+        gr.Dropdown(choices=list(STYLES.keys()), value=DEFAULT_STYLE_NAME, label="Style"),  # Endpoint: `style_name`
+        gr.Slider(minimum=0, maximum=MAX_SEED, step=1, default=DEFAULT_SEED, label="Seed"),  # Endpoint: `seed`
+        gr.Slider(minimum=0.0, maximum=1.0, step=0.01, default=VAL_R_DEFAULT, label="Sketch Guidance")  # Endpoint: `val_r`
     ],
-    outputs=gr.Image(label="Generated Image"),
+    outputs=gr.Image(label="Generated Image"),  # Output endpoint: `result_image`
     title="Sketch to Image Generation",
     description="Upload a sketch and generate an image based on a prompt and style."
 )