Update app.py

app.py

@@ -11,16 +11,19 @@ from huggingface_hub import hf_hub_download
 
 MAX_SEED = np.iinfo(np.int32).max
 
+# Load the base pipeline
 pipe = FluxKontextPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.bfloat16).to("cuda")
 
-# Add the adapter to the app
-pipe.load_lora_weights("prithivMLmods/PhotoCleanser-i2i", weight_name="PhotoCleanser-i2i.safetensors", adapter_name="lora")
-pipe.set_adapters(["lora"], adapter_weights=[1.0])
+# Load the PhotoCleanser adapter
+pipe.load_lora_weights("prithivMLmods/PhotoCleanser-i2i", weight_name="PhotoCleanser-i2i.safetensors", adapter_name="cleanser")
+# Load the Photo-Restore adapter
+pipe.load_lora_weights("prithivMLmods/Photo-Restore-i2i", weight_name="Photo-Restore-i2i.safetensors", adapter_name="restorer")
+
 
 @spaces.GPU
-def infer(input_image, prompt, seed=42, randomize_seed=False, guidance_scale=2.5, steps=28, progress=gr.Progress(track_tqdm=True)):
+def infer(input_image, prompt, lora_selection, seed=42, randomize_seed=False, guidance_scale=2.5, steps=28, progress=gr.Progress(track_tqdm=True)):
     """
-    Perform image editing using the FLUX.1 Kontext pipeline.
+    Perform image editing using the FLUX.1 Kontext pipeline with selectable LoRA adapters.
     
     This function takes an input image and a text prompt to generate a modified version
     of the image based on the provided instructions. It uses the FLUX.1 Kontext model
@@ -30,36 +33,27 @@ def infer(input_image, prompt, seed=42, randomize_seed=False, guidance_scale=2.5
         input_image (PIL.Image.Image): The input image to be edited. Will be converted
             to RGB format if not already in that format.
         prompt (str): Text description of the desired edit to apply to the image.
-            Examples: "Remove glasses", "Add a hat", "Change background to beach".
+        lora_selection (str): The name of the LoRA adapter to use ("PhotoCleanser" or "PhotoRestore").
         seed (int, optional): Random seed for reproducible generation. Defaults to 42.
-            Must be between 0 and MAX_SEED (2^31 - 1).
-        randomize_seed (bool, optional): If True, generates a random seed instead of
-            using the provided seed value. Defaults to False.
-        guidance_scale (float, optional): Controls how closely the model follows the
-            prompt. Higher values mean stronger adherence to the prompt but may reduce
-            image quality. Range: 1.0-10.0. Defaults to 2.5.
-        steps (int, optional): Controls how many steps to run the diffusion model for.
-            Range: 1-30. Defaults to 28.
-        progress (gr.Progress, optional): Gradio progress tracker for monitoring
-            generation progress. Defaults to gr.Progress(track_tqdm=True).
+        randomize_seed (bool, optional): If True, generates a random seed. Defaults to False.
+        guidance_scale (float, optional): Controls how closely the model follows the prompt. Defaults to 2.5.
+        steps (int, optional): Number of diffusion steps. Defaults to 28.
+        progress (gr.Progress, optional): Gradio progress tracker.
     
     Returns:
-        tuple: A 3-tuple containing:
-            - PIL.Image.Image: The generated/edited image
-            - int: The seed value used for generation (useful when randomize_seed=True)
-            - gr.update: Gradio update object to make the reuse button visible
-    
-    Example:
-        >>> edited_image, used_seed, button_update = infer(
-        ...     input_image=my_image,
-        ...     prompt="Add sunglasses",
-        ...     seed=123,
-        ...     randomize_seed=False,
-        ...     guidance_scale=2.5
-        ... )
+        tuple: A 3-tuple containing the generated image, the seed used, and a Gradio update object.
     """
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
+
+    # Set the adapter based on the user's selection
+    if lora_selection == "PhotoCleanser":
+        pipe.set_adapters(["cleanser"], adapter_weights=[1.0])
+    elif lora_selection == "PhotoRestore":
+        pipe.set_adapters(["restorer"], adapter_weights=[1.0])
+    else: # If "None" or any other value, disable LoRA
+        pipe.disable_lora()
+
     
     if input_image:
         input_image = input_image.convert("RGB")
@@ -79,13 +73,30 @@ def infer(input_image, prompt, seed=42, randomize_seed=False, guidance_scale=2.5
             num_inference_steps=steps,
             generator=torch.Generator().manual_seed(seed),
         ).images[0]
+        
     return image, seed, gr.Button(visible=True)
 
+# Wrapper function for PhotoCleanser examples
 @spaces.GPU
-def infer_example(input_image, prompt):
-    image, seed, _ = infer(input_image, prompt)
+def infer_example_cleanser(input_image, prompt):
+    image, seed, _ = infer(input_image, prompt, lora_selection="PhotoCleanser")
     return image, seed
 
+# Wrapper function for PhotoRestore examples
+@spaces.GPU
+def infer_example_restorer(input_image, prompt):
+    image, seed, _ = infer(input_image, prompt, lora_selection="PhotoRestore")
+    return image, seed
+
+# Function to switch visibility of example sets based on dropdown selection
+def switch_examples(lora_choice):
+    if lora_choice == "PhotoCleanser":
+        return gr.update(visible=True), gr.update(visible=False)
+    elif lora_choice == "PhotoRestore":
+        return gr.update(visible=False), gr.update(visible=True)
+    return gr.update(visible=False), gr.update(visible=False)
+
+
 css="""
 #col-container {
     margin: 0 auto;
@@ -98,6 +109,13 @@ with gr.Blocks(css=css, theme="YTheme/Minecraft") as demo:
     with gr.Column(elem_id="col-container"):
         gr.Markdown(f"""# **[Photo-Mate-i2i](https://huggingface.co/collections/prithivMLmods/i2i-kontext-exp-68ce573b5c0623476b636ec7)**
         Image manipulation with Kontext adapters""")
+        
+        lora_dropdown = gr.Dropdown(
+            label="Select Adapter (LoRA)",
+            choices=["PhotoCleanser", "PhotoRestore"],
+            value="PhotoCleanser"
+        )
+
         with gr.Row():
             with gr.Column():
                 input_image = gr.Image(label="Upload the image for editing", type="pil", height="300")
@@ -106,60 +124,69 @@ with gr.Blocks(css=css, theme="YTheme/Minecraft") as demo:
                         label="Prompt",
                         show_label=False,
                         max_lines=1,
-                        placeholder="Enter your prompt for editing (e.g., 'Remove glasses', 'Add a hat')",
+                        placeholder="Enter your prompt for editing (e.g., 'Remove the cat')",
                         container=False,
                     )
                     run_button = gr.Button("Run", scale=0)
                 with gr.Accordion("Advanced Settings", open=False):
                     
                     seed = gr.Slider(
-                        label="Seed",
-                        minimum=0,
-                        maximum=MAX_SEED,
-                        step=1,
-                        value=0,
+                        label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0,
                     )
-                    
                     randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-                    
                     guidance_scale = gr.Slider(
-                        label="Guidance Scale",
-                        minimum=1,
-                        maximum=10,
-                        step=0.1,
-                        value=2.5,
+                        label="Guidance Scale", minimum=1, maximum=10, step=0.1, value=2.5,
                     )       
-                    
                     steps = gr.Slider(
-                        label="Steps",
-                        minimum=1,
-                        maximum=30,
-                        value=28,
-                        step=1
+                        label="Steps", minimum=1, maximum=30, value=28, step=1
                     )
                     
             with gr.Column():
                 result = gr.Image(label="Result", show_label=False, interactive=False, format="png")
                 reuse_button = gr.Button("Reuse this image", visible=False)
         
+        with gr.Group():
+            cleanser_examples = gr.Examples(
+                examples=[
+                    ["photocleanser/1.png", "[photo content], remove the embroidered pattern from the image while preserving the background and remaining elements, maintaining realism and original details."],
+                    ["photocleanser/2.png", "[photo content], remove the cat from the image while preserving the background and remaining elements, maintaining realism and original details."]
+                ],
+                inputs=[input_image, prompt],
+                outputs=[result, seed],
+                fn=infer_example_cleanser,
+                cache_examples=False,
+                label="PhotoCleanser Examples"
+            )
             
-        examples = gr.Examples(
-            examples=[
-                ["photocleanser/1.png", "[photo content], remove the embroidered pattern from the image while preserving the background and remaining elements, maintaining realism and original details."],
-                ["photocleanser/2.png", "[photo content], remove the cat from the image while preserving the background and remaining elements, maintaining realism and original details."]
-            ],
-            inputs=[input_image, prompt],
-            outputs=[result, seed],
-            fn=infer_example,
-            cache_examples=False
-        )
-            
+            restorer_examples = gr.Examples(
+                examples=[
+                    ["photorestore/1.png", "[photo content], restore and enhance the image by repairing any damage, scratches, or fading. Colorize the photo naturally while preserving authentic textures and details, maintaining a realistic and historically accurate look."],
+                    ["photorestore/2.png", "[photo content], restore and enhance the image by repairing any damage, scratches, or fading. Colorize the photo naturally while preserving authentic textures and details, maintaining a realistic and historically accurate look."]
+                ],
+                inputs=[input_image, prompt],
+                outputs=[result, seed],
+                fn=infer_example_restorer,
+                cache_examples=False,
+                visible=False,
+                label="PhotoRestore Examples"
+            )
+
+    # Event listener for the main run button
     gr.on(
         triggers=[run_button.click, prompt.submit],
         fn = infer,
-        inputs = [input_image, prompt, seed, randomize_seed, guidance_scale, steps],
+        inputs = [input_image, prompt, lora_dropdown, seed, randomize_seed, guidance_scale, steps],
         outputs = [result, seed, reuse_button]
     )
+    
+    # Event listener to switch example sets when the dropdown changes
+    lora_dropdown.change(
+        fn=switch_examples,
+        inputs=lora_dropdown,
+        outputs=[cleanser_examples, restorer_examples]
+    )
+
+    # Event listener for the reuse button
     reuse_button.click(
         fn = lambda image: image,
         inputs = [result],