Refactor app for automatic model loading on startup

- Load model globally at startup (no button needed)
- Move CUDA initialization inside @spaces.GPU decorated function
- Remove model loading UI components
- Add 120s duration to GPU decorator for longer generation
- Simplify app flow for better UX

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

app.py

@@ -9,38 +9,21 @@ from PIL import Image
 
 from cogvideox_interpolation.pipeline import CogVideoXInterpolationPipeline
 
-# Global variable to store the pipeline
-pipe = None
-device = "cuda" if torch.cuda.is_available() else "cpu"
+# Load model globally at startup
+print("Loading CogVideoX-Interpolation model...")
+MODEL_PATH = "feizhengcong/CogvideoX-Interpolation"
+dtype = torch.float16
 
+pipe = CogVideoXInterpolationPipeline.from_pretrained(
+    MODEL_PATH,
+    torch_dtype=dtype
+)
+pipe.vae.enable_tiling()
+pipe.vae.enable_slicing()
+print("Model loaded successfully!")
 
-@spaces.GPU
-def load_model(model_path):
-    """Load the CogVideoX-Interpolation model"""
-    global pipe
 
-    print(f"Loading model from {model_path}...")
-    print(f"Using device: {device}")
-
-    # Determine dtype based on model variant
-    dtype = torch.bfloat16 if "5b" in model_path.lower() else torch.float16
-
-    pipe = CogVideoXInterpolationPipeline.from_pretrained(model_path, torch_dtype=dtype)
-
-    # Memory optimization
-    if device == "cuda":
-        pipe.enable_sequential_cpu_offload()
-    else:
-        pipe = pipe.to(device)
-
-    pipe.vae.enable_tiling()
-    pipe.vae.enable_slicing()
-
-    print("Model loaded successfully!")
-    return "✓ Model loaded successfully!"
-
-
-@spaces.GPU
+@spaces.GPU(duration=120)
 def generate_interpolation(
     first_image,
     last_image,
@@ -53,9 +36,6 @@ def generate_interpolation(
 ):
     """Generate interpolated video between two keyframes"""
 
-    if pipe is None:
-        return None, "⚠️ Please load the model first!"
-
     if first_image is None or last_image is None:
         return None, "⚠️ Please upload both start and end frame images!"
 
@@ -63,6 +43,11 @@ def generate_interpolation(
         return None, "⚠️ Please provide a text prompt describing the motion!"
 
     try:
+        # Move model to CUDA inside the decorated function
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+        pipe.to(device)
+        pipe.enable_sequential_cpu_offload()
+
         # Convert numpy arrays to PIL Images if needed
         if not isinstance(first_image, Image.Image):
             first_image = Image.fromarray(first_image)
@@ -115,26 +100,12 @@ with gr.Blocks(title="CogVideoX Keyframe Interpolation") as demo:
     Generate smooth video transitions between two keyframe images using AI.
 
     **Instructions:**
-    1. First, load the model by providing the path to your checkpoint
-    2. Upload start and end frame images
-    3. Describe the motion/transition in the text prompt
-    4. Adjust parameters and generate!
+    1. Upload start and end frame images
+    2. Describe the motion/transition in the text prompt
+    3. Adjust parameters and generate!
     """
     )
 
-    with gr.Row():
-        with gr.Column():
-            gr.Markdown("### 🔧 Model Setup")
-            model_path_input = gr.Textbox(
-                label="Model Path",
-                placeholder="e.g., /path/to/CogVideoX-5b-I2V-inter or feizhengcong/CogvideoX-Interpolation",
-                value="feizhengcong/CogvideoX-Interpolation",
-            )
-            load_btn = gr.Button("Load Model", variant="primary")
-            model_status = gr.Textbox(label="Status", interactive=False)
-
-    gr.Markdown("---")
-
     with gr.Row():
         with gr.Column():
             gr.Markdown("### 🖼️ Input Keyframes")
@@ -210,8 +181,6 @@ with gr.Blocks(title="CogVideoX Keyframe Interpolation") as demo:
     )
 
     # Event handlers
-    load_btn.click(fn=load_model, inputs=[model_path_input], outputs=[model_status])
-
     generate_btn.click(
         fn=generate_interpolation,
         inputs=[
@@ -228,16 +197,4 @@ with gr.Blocks(title="CogVideoX Keyframe Interpolation") as demo:
     )
 
 if __name__ == "__main__":
-    print("=" * 50)
-    print("CogVideoX Keyframe Interpolation Gradio App")
-    print("=" * 50)
-    print(f"Device: {device}")
-    print(f"CUDA available: {torch.cuda.is_available()}")
-    if torch.cuda.is_available():
-        print(f"GPU: {torch.cuda.get_device_name(0)}")
-        print(
-            f"GPU Memory: {torch.cuda.get_device_properties(0).total_memory / 1024**3:.2f} GB"
-        )
-    print("=" * 50)
-
     demo.launch()