About Wan
Wan is an AI creative platform from Alibaba Cloud for making images and videos from text, still pictures or reference material. It brings text-to-video, image-to-video and image editing into one place.
What it does
Wan turns a written prompt or a still image into a short video clip. It also covers text-to-image, image-to-image and editing tools that change an existing video or picture. The team publishes open model code on GitHub alongside the hosted service, so developers can look at the underlying work as well as use the app.
Key features
- Text to video and image to video
- Up to 20 reference assets in one request
- Video editing with written instructions
- Text to image and image editing
- Web app, mobile apps and an API
Who it's for
Creators, marketers and product teams who want short AI video without a camera or a crew. Developers can use the API to add video generation to their own apps.
Pricing and good to know
Plan details are on the pricing page, so check there before you commit to a paid tier. The mobile apps are on the App Store and Google Play, and a mobile web version is offered for regions without the app. The open model code on GitHub is released under the Apache-2.0 license.
Highlights
- Turn a text prompt into a short video clip
- Animate a still image into a video
- Combine several reference images or files
- Edit an existing video with written instructions
- Use the web app, phone apps or the API
