Wan2.1 Video Generation

Open and Advanced Large-Scale Video Generative Model

Choose one of the following generation modes:

Generate videos from textual descriptions.

Try It

Convert still images into dynamic videos.

Try It

Create videos from first and last frames.

Try It

About Wan2.1

Wan2.1 is a comprehensive and open suite of video foundation models that pushes the boundaries of video generation with the following features:

SOTA Performance: Consistently outperforms existing open-source models and state-of-the-art commercial solutions.
Consumer-grade GPU Support: The T2V-1.3B model requires only 8.19 GB VRAM, compatible with most consumer-grade GPUs.
Multiple Tasks: Excels in Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, and Video-to-Audio.
Visual Text Generation: First video model capable of generating both Chinese and English text.
Powerful Video VAE: Exceptional efficiency and performance, encoding and decoding 1080P videos of any length.