Update app to use SDXL Refiner for image-to-image generation

app.py

@@ -2,49 +2,67 @@ import gradio as gr
 import numpy as np
 import random
 
-import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
+import spaces
+from diffusers import StableDiffusionXLImg2ImgPipeline
+from diffusers.utils import load_image
 import torch
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
+model_repo_id = "stabilityai/stable-diffusion-xl-refiner-1.0"
 
 if torch.cuda.is_available():
     torch_dtype = torch.float16
 else:
     torch_dtype = torch.float32
 
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
+pipe = StableDiffusionXLImg2ImgPipeline.from_pretrained(
+    model_repo_id, 
+    torch_dtype=torch_dtype, 
+    variant="fp16" if torch.cuda.is_available() else None,
+    use_safetensors=True
+)
 pipe = pipe.to(device)
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
-
-@spaces.GPU #[uncomment to use ZeroGPU]
+@spaces.GPU
 def infer(
     prompt,
+    input_image,
     negative_prompt,
     seed,
     randomize_seed,
-    width,
-    height,
+    strength,
     guidance_scale,
     num_inference_steps,
     progress=gr.Progress(track_tqdm=True),
 ):
+    if input_image is None:
+        return None, seed
+    
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
 
     generator = torch.Generator().manual_seed(seed)
+    
+    # Process the image
+    if input_image is not None:
+        width, height = input_image.size
+        
+        # Ensure width and height are valid for the model
+        if width > MAX_IMAGE_SIZE:
+            width = MAX_IMAGE_SIZE
+        if height > MAX_IMAGE_SIZE:
+            height = MAX_IMAGE_SIZE
 
     image = pipe(
         prompt=prompt,
+        image=input_image,
         negative_prompt=negative_prompt,
         guidance_scale=guidance_scale,
         num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
+        strength=strength,
         generator=generator,
     ).images[0]
 
@@ -52,41 +70,52 @@ def infer(
 
 
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    ["Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", "https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/aa_xl/000000009.png"],
+    ["An astronaut riding a green horse", "https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/aa_xl/000000009.png"],
+    ["A delicious ceviche cheesecake slice", "https://huggingface.co/datasets/patrickvonplaten/images/resolve/main/aa_xl/000000009.png"],
 ]
 
 css = """
 #col-container {
     margin: 0 auto;
-    max-width: 640px;
+    max-width: 840px;
 }
 """
 
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
+        gr.Markdown(" # SDXL Refiner - Image-to-Image")
 
         with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
+            with gr.Column(scale=1):
+                input_image = gr.Image(
+                    label="Input Image",
+                    type="pil",
+                    height=400
+                )
+            with gr.Column(scale=1):
+                result = gr.Image(label="Result", height=400)
 
-        result = gr.Image(label="Result", show_label=False)
+        prompt = gr.Text(
+            label="Prompt",
+            placeholder="Enter your prompt",
+        )
+        
+        run_button = gr.Button("Run", variant="primary")
 
         with gr.Accordion("Advanced Settings", open=False):
             negative_prompt = gr.Text(
                 label="Negative prompt",
                 max_lines=1,
                 placeholder="Enter a negative prompt",
-                visible=False,
+            )
+            
+            strength = gr.Slider(
+                label="Strength",
+                minimum=0.0,
+                maximum=1.0,
+                step=0.05,
+                value=0.7,
             )
 
             seed = gr.Slider(
@@ -99,51 +128,41 @@ with gr.Blocks(css=css) as demo:
 
             randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
 
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
             with gr.Row():
                 guidance_scale = gr.Slider(
                     label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
+                    minimum=1.0,
+                    maximum=20.0,
                     step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
+                    value=7.5,
                 )
 
                 num_inference_steps = gr.Slider(
                     label="Number of inference steps",
                     minimum=1,
-                    maximum=50,
+                    maximum=100,
                     step=1,
-                    value=2,  # Replace with defaults that work for your model
+                    value=30,
                 )
 
-        gr.Examples(examples=examples, inputs=[prompt])
+        gr.Examples(
+            examples=examples, 
+            inputs=[prompt, input_image],
+            outputs=[result, seed],
+            fn=infer,
+            cache_examples=True,
+        )
+    
     gr.on(
-        triggers=[run_button.click, prompt.submit],
+        triggers=[run_button.click],
         fn=infer,
         inputs=[
             prompt,
+            input_image,
             negative_prompt,
             seed,
             randomize_seed,
-            width,
-            height,
+            strength,
             guidance_scale,
             num_inference_steps,
         ],