Create app.py

app.py

@@ -0,0 +1,54 @@
+import gradio as gr
+import torch
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+from diffusers.utils import load_image
+from controlnet_aux import OpenposeDetector
+import numpy as np
+from PIL import Image
+
+# Load models
+controlnet = ControlNetModel.from_pretrained(
+    "lllyasviel/control_v11p_sd15_openpose",
+    torch_dtype=torch.float16
+)
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    controlnet=controlnet,
+    torch_dtype=torch.float16
+).to("cuda")
+
+pose_detector = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
+
+def transfer_pose(pose_image, appearance_image, prompt="person"):
+    # Extract pose from first image
+    pose_img = pose_detector(pose_image)
+    
+    # Use appearance image as reference for style/identity
+    # Generate new image with pose + appearance guidance
+    result = pipe(
+        prompt=f"photo of {prompt}, high quality",
+        image=pose_img,
+        controlnet_conditioning_scale=1.0,
+        num_inference_steps=20,
+        guidance_scale=7.0
+    ).images[0]
+    
+    return pose_img, result
+
+# Gradio interface
+demo = gr.Interface(
+    fn=transfer_pose,
+    inputs=[
+        gr.Image(label="Source Pose Image", type="pil"),
+        gr.Image(label="Target Appearance Image", type="pil"),
+        gr.Textbox(label="Prompt (optional)", value="person")
+    ],
+    outputs=[
+        gr.Image(label="Detected Pose"),
+        gr.Image(label="Result")
+    ],
+    title="Pose Transfer Tool",
+    description="Transfer pose from first image to generate a new image"
+)
+
+demo.launch()