What Wan 2.1 changed, by its release notes
Wan 2.1, in the Wan line: 5 entries, 9 January 2025 to 14 May 2025, covering new model, motion, frames, tiers, editing, length and references. From 1 source page, read 2026-09-25; no maker pays to be listed.
| Date | What changed | Kinds | Source |
|---|---|---|---|
| 9 January 2025 | Wan 2.1 text-to-video Plus, with large movements and physical plausibility named | new model, motion | Maker's note |
| 20 January 2025 | Wan 2.1 image-to-video Plus turns a still into a clip | frames | Maker's note |
| 27 February 2025 | A Turbo tier of Wan 2.1 image-to-video for faster generation | tiers | Maker's note |
| 7 April 2025 | Wan 2.1 start-and-end-frame model makes a transition between two images | frames | Maker's note |
| 14 May 2025 | Wan 2.1 VACE combines local editing, repainting, outpainting, extension and image references | editing, length, references | Maker's note |
Inclusion rule. All entries filed under this version: the maker's notes, platform arrivals and undated rows. Order. By date, oldest first; undated rows last.
Most of what the notes record for Wan 2.1 concerns a new model or snapshot, motion or performance transfer and start, end or middle frames.
1Each entry
9 January 2025, from Alibaba Cloud Model Studio, newly released models
Wan2.1 text to video Plus version, one sentence generated video. Support for large and complex movements, adherence to physical laws, artistic styles, and visual quality of movies.
Alibaba Cloud Model Studio, newly released models
- wan2.1-t2v-plusWan 2.1 text-to-video Plus, with large movements and physical plausibility named
20 January 2025, from Alibaba Cloud Model Studio, newly released models
Wan2.1 image to video Plus version, make the static image generated video.
Alibaba Cloud Model Studio, newly released models
- wan2.1-i2v-plusWan 2.1 image-to-video Plus turns a still into a clip
27 February 2025, from Alibaba Cloud Model Studio, newly released models
The ability to follow instructions is further improved, and generation more fast.
Alibaba Cloud Model Studio, newly released models
- wan2.1-i2v-turboA Turbo tier of Wan 2.1 image-to-video for faster generation
7 April 2025, from Alibaba Cloud Model Studio, newly released models
Wan2.1 start and end frames to video Plus version, generate a smooth transition video for two images.
Alibaba Cloud Model Studio, newly released models
- wan2.1-kf2v-plusWan 2.1 start-and-end-frame model makes a transition between two images
14 May 2025, from Alibaba Cloud Model Studio, newly released models
It supports local editing, video repainting, background outpainting, duration extension, image reference, and other video editing and generation tasks
Alibaba Cloud Model Studio, newly released models
- wan2.1-vace-plusWan 2.1 VACE combines local editing, repainting, outpainting, extension and image references
2Versions either side in this line
- Dated before it: none in the register.
- Dated after it: Wan 2.2, 4 entries, first dated 28 July 2025.
3Same kinds of change elsewhere, within six weeks
- 29 November 2024, Kling AI: Kling 1.0
- 6 December 2024, Runway: Act-One
- 9 December 2024, Kling AI: Kling 1.5
- 19 December 2024, Runway: Gen-3 Alpha Turbo
- 12 February 2025, Adobe Firefly Video: Firefly Video Model
The whole line: Wan. Quarter: Q1 2025.
4Notes read
- Alibaba Cloud Model Studio, newly released models, read 2026-09-25
5A pipeline on current models
Release notes such as “Wan 2.1” matter once a pipeline runs the models; SceneMixer's guides describe how it does:
Wan 3.0 · 480P is the tier every new project starts on.
SceneMixer, Wan 3.0 · 480P: the default video tier (read 2026-10-13)
Wan 3.0 is Alibaba Cloud's video generation model on the Model Studio platform, called through an asynchronous submit-then-poll API, in two tiers: the standard wan3.0-video and the faster wan3.0-video-prime.
SceneMixer, Wan 3.0 for AI Short Drama (2026): Parameters, Reference Limits, Moderation Rules and the 30-Second Take (read 2026-10-13)