app.py

import torch
import gradio as gr
from diffusers import StableVideoDiffusionPipeline
from diffusers.utils import load_image, export_to_video
import spaces

# Check if GPU is available
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the pipeline
pipeline = StableVideoDiffusionPipeline.from_pretrained(
    "stabilityai/stable-video-diffusion-img2vid-xt", torch_dtype=torch.float16, variant="fp16"
)
pipeline.to(device)

@spaces.GPU(duration=120)
def generate_video(image_path, seed):
    # Load and preprocess the image
    image = load_image(image_path)
    image = image.resize((1024, 576))

    # Set the generator seed
    generator = torch.Generator(device=device).manual_seed(seed)

    # Generate the video frames
    frames = pipeline(image, decode_chunk_size=8, generator=generator).frames[0]

    # Export the frames to a video file
    output_video_path = "generated.mp4"
    export_to_video(frames, output_video_path, fps=25)

    return output_video_path

# Create the Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# Stable Video Diffusion")
    gr.Markdown("Generate a video from an uploaded image using Stable Video Diffusion.")
    
    with gr.Row():
        with gr.Column():
            image_input = gr.Image(type="filepath", label="Upload Image")
            seed_input = gr.Number(label="Seed", value=666666)
            generate_button = gr.Button("Generate Video")
        with gr.Column():
            video_output = gr.Video(label="Generated Video")
        # Display the example image
    example_image = gr.Image("example.jpeg", label="Example Image")
    with gr.Row():
        example_video = gr.Video("generated.mp4", label="Example Video")

    generate_button.click(
        fn=generate_video,
        inputs=[image_input, seed_input],
        outputs=video_output
    )

# Launch the interface
if __name__ == "__main__":
    demo.launch()