Wan
by Alibaba
At a glance
Alibaba's Tongyi Wanxiang video generation model family, with open-weight releases.
video-generation open-weights text-to-video
- Licence
- Apache-2.0
- Category
- Video Generation
- Business model
- Open (open weights/source)
- Availability
- Global
- Launched
- 2024
Overview
Wan is Alibaba's Tongyi Wanxiang family of video generation models, covering text-to-video and image-to-video. Alibaba has released open-weight versions under Apache-2.0, letting developers download and run the models themselves, while hosted access is available through Alibaba's Tongyi services. The open releases have made Wan one of the more widely used open video model families.
Compare this tool Suggest a correction
Key features
- Text-to-video and image-to-video generation
- Open-weight releases under Apache-2.0
- Multiple model sizes for different hardware budgets
- Hosted access through Alibaba's Tongyi platform
Use cases
- Generating short video clips from text prompts
- Animating still images into motion
- Self-hosted video generation research and products
Pricing
Open-weight Wan models are free to download and run under Apache-2.0; Alibaba's hosted Tongyi Wanxiang service is metered separately.
Record details
Provenance, dates and links are kept here so the main sections stay about the product itself.
Links, dates and provenance
- Record updated
- 2026-09-10
- Founded
- 1999
- Headquarters
- CN
- Canonical URL
- https://globalaiproductindex.com/products/wan/
Selection profile
Every field says where its value comes from. "Unknown" means we have not confirmed it — it does not mean the product lacks the feature.
Selection profile11 fields3 unknown
- Tasks it fits
- Video generation
Derived from the record: category "video-generation".
Suggest a correction - How you use it
- Model weights
Derived from record tag matching /^open-weights$/.
Suggest a correction - Runs on
- Not recorded
No platform support is stated in the record.
Suggest a correction - Where it runs
- Local machine
Open-weight models are run by the user, not served by the vendor.
Suggest a correction - Works offline
- Partly
Local execution implies the model can run without a network once downloaded, but the vendor does not state this in the record.
Suggest a correction - Official service region
- Global
Mirrors the availability field already on the record ("global").
Suggest a correction - Public API
- Not recorded
The record does not state whether a public API exists.
Suggest a correction - Licence
- Apache-2.0
Mirrors the licence already recorded on the product record; not re-verified against the licence text by this migration.
Suggest a correction - Commercial use
- Permitted
Recorded licence allows commercial use (copyleft obligations may still apply).
Suggest a correction - Interface languages
- Not recorded
No vendor page read in this pass states the product's own interface languages; the key exists so the field can be answered later rather than left absent.
Suggest a correction - Billing
- Open source Free Free allowance: Yes Subscription required: No
Prices are the vendor’s advertised entry price and exclude taxes; always confirm on the vendor’s own page.
Suggest a correction
Where each value comes from
- Tasks it fits
- Our inference
- How you use it
- Our inference
- Runs on
- Our inference
- Where it runs
- Our inference
- Works offline
- Our inference
- Official service region
- Our inference
- Public API
- Our inference
- Licence
- Our inference
- Commercial use
- Our inference
- Interface languages
- Unknown
Frequently asked questions
Is Wan open source?
Alibaba releases open-weight Wan models under the Apache-2.0 license, free to download and use commercially.
What can Wan generate?
Wan generates video from text prompts and animates still images into video clips.
Who develops Wan?
Wan (Tongyi Wanxiang) is developed by Alibaba as part of its Tongyi model family.
What does Wan not record?
Its record includes no public documentation page and no vendor pricing page, because those pages were not in the fetch scope.
Similar products
- Hailuo AI — Text-to-video and image-to-video model from MiniMax for generating short cinematic clips.
- Kling AI — Text-to-video and image-to-video generation model from Kuaishou, producing high-resolution cinematic clips.
- Veo — Google DeepMind's text-to-video model that generates high-definition clips with native audio, available via Gemini and Vertex AI.
- Vidu — Text-to-video and image-to-video generation model from Shengshu Technology.
- Higgsfield — AI video generation platform focused on cinematic camera controls and effects for social and marketing content.
- Moonvalley — AI video company whose Marey model is trained only on licensed footage and aimed at professional film production.
Related guides
Sources
This record was last reviewed on 2026-09-10.
Machine-readable record: /api/products/wan.json · Spot an error? Suggest a correction