---
title: MiniMax-H3 Multi-Shot Video Generator
emoji: 🎬
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 5.20.0
app_file: app.py
pinned: false
license: apache-2.0
tags:
- text-to-video
- comfyui
- minimax-h3
- agents-md
---

# MiniMax-H3 Multi-Shot Seamless Video Chain

Interactive demo and agent API for [joeygambino/MiniMax-H3-Multishot-Workflow](https://huggingface.co/joeygambino/MiniMax-H3-Multishot-Workflow).

Generates multi-shot video sequences with seamless shot-boundary transitions, consistent audio, and character identity continuity using the **MiniMax-H3** model.

## Agent API (`agents.md`)

This Space automatically serves an `/agents.md` endpoint. AI Agents can call this Space programmatically via `gradio_client`:

```python
from gradio_client import Client

client = Client("your-username/minimax-h3-multishot-demo")
result = client.predict(
    prompts="A cyberpunk detective walks down a rainy alleyway.\n---\nHe stops under a neon sign and lights a cigarette.",
    resolution="1280x736",
    continuity_mode="first_frame",
    take_seconds=15,
    api_name="/generate_multishot_video"
)
print(result)