App.py

import gradio as gr
from huggingface_hub import InferenceClient

"""
For more information on `huggingface_hub` Inference API support, please check the docs:
https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("damo-vilab/modelscope-text-to-video-synthesis")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]
    
    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})
    
    messages.append({"role": "user", "content": message})

    # NOTE: Video models don't usually use "streaming" generation, so we'll just call once
    payload = {
        "inputs": message,
        "parameters": {
            "max_new_tokens": max_tokens,
            "temperature": temperature,
            "top_p": top_p,
        }
    }

    # Post directly to the model
    response = client.post(json=payload)

    video_url = response.get("video", None)

    if video_url:
        yield video_url
    else:
        yield "Failed to generate video."

"""
For information on how to customize the ChatInterface, peruse the gradio docs:
https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are generating a creative video.", label="System message"),
        gr.Slider(minimum=1, maximum=1000, value=250, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=2.0, value=1.0, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.9,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)

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