README.md

---
title: Wan2.1 FLF2V - First & Last Frame to Video
emoji: 🎬
colorFrom: blue
colorTo: yellow
sdk: gradio
sdk_version: 6.1.0
app_file: app.py
pinned: true
license: apache-2.0
short_description: Generate videos from first & last frame + text using Wan2.1
---

# Wan2.1 FLF2V - First & Last Frame to Video Generator

Generate high-quality videos from first and last frame images combined with text prompts using the [Wan2.1-FLF2V-14B-720P](https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P) model.

## Features

- 🎬 Generate videos from first and last frame images
- ✍️ Text prompt support with prompt enhancement
- ⚙️ Advanced controls: diffusion steps, guidance scale, shift scale, seed, solver selection
- 🌍 Multi-language prompt enhancement (Chinese/English)
- 📐 Multiple resolution options (720P, 1280x720, 480P, 832x480)
- 🎯 Customizable frame count (17-81 frames, must be 4n+1)
- 🚀 ZeroGPU support for efficient GPU usage

## Usage

1. Wait for the model to load automatically (first time may take a few minutes)
2. Upload first and last frame images
3. Enter a text prompt describing the video
4. (Optional) Click "Enhance Prompt" to improve your prompt
5. Adjust advanced options if needed
6. Click "Generate Video" to create your video

## Model

This space uses the [Wan-AI/Wan2.1-FLF2V-14B-720P](https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P) model from Hugging Face Hub.

## License

Apache 2.0