Wan2.2
by Wan-Video
Wan2.2 is a set of open video generation models that create short videos from text, images or audio. It also includes code to animate or replace characters in existing footage.
- Stars
- 18.3k
- Licence
- Apache-2.0
- Runs on
- A gpu machine, with a GPU
- Setup
- Technical
- Language
- Python
- Age
- 461 days
What you can do with it
- Generate short videos from a text prompt or a still image
- Create speech-driven videos from audio using the speech-to-video model
- Animate a character or swap one into existing footage
Make money with it
Offer short AI-generated video clips, such as social adverts or animated product images, as a paid service to small businesses.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Produce short social media and advert clips without paying for stock footage or per-clip video services
- Make product teasers or animated explainer visuals from still images for clients
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Clone the repository, install the Python dependencies and download the model weights from Hugging Face or ModelScope, or use the ComfyUI and Diffusers integrations.
Follow the official instructions in the project README.
Things to check
- Needs a powerful GPU; the smaller 5B model runs on a 4090-class card, the larger models need more
- Large model downloads
- Generated video may raise copyright or likeness concerns, so check the model licence terms for commercial use
Who's talking about it
Checked 01 Nov 2026. Summary drafted by AI from the project's README.
