app.py

import gradio as gr
from diffusers import StableDiffusionPipeline
import os
import cv2

# --- Initialize Stable Diffusion pipeline ---
pipe = StableDiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1")

FRAME_FOLDER = "frames"
VIDEO_OUTPUT = "generated_video.mp4"

# --- Function to generate N frames using AI ---
def generate_frames(prompt, num_frames=10):
    os.makedirs(FRAME_FOLDER, exist_ok=True)
    for i in range(num_frames):
        image = pipe(prompt).images[0]
        image.save(f"{FRAME_FOLDER}/frame_{i:03d}.png")

# --- Function to create video from frames ---
def create_video_from_frames(frame_folder, output_path, fps=2):
    images = sorted([img for img in os.listdir(frame_folder) if img.endswith(".png")])
    if not images:
        raise ValueError("No frames generated.")
    frame = cv2.imread(os.path.join(frame_folder, images[0]))
    height, width, _ = frame.shape

    video = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (width, height))
    for img in images:
        video.write(cv2.imread(os.path.join(frame_folder, img)))
    video.release()

# --- Main function called by Gradio ---
def generate_video(prompt):
    generate_frames(prompt, num_frames=10)  # Generate 10 frames
    create_video_from_frames(FRAME_FOLDER, VIDEO_OUTPUT, fps=2)  # 2 fps
    return VIDEO_OUTPUT

# --- Gradio UI ---
iface = gr.Interface(
    fn=generate_video,
    inputs=gr.Textbox(lines=3, placeholder="Describe your scene here..."),
    outputs=gr.Video(),
    title="AI Text-to-Video Generator (No manual assets needed)"
)

if __name__ == "__main__":
    iface.launch()