VideoGenReview

What each AI video model's release notes say changed

Wan 2.2: every dated change

Wan 2.2, in the Wan line: 4 entries, 28 July 2025 to 10 November 2025, covering new model, camera, motion, tiers, frames and references. Dated before it in this line: Wan 2.1. From 1 source page, read 2026-09-25; no maker pays to be listed.

Wan 2.2 entries by dateOne dot per dated entry.Wan 2.2 entries by date2025-07-28Wan 2.2 text-to-video Plus names complex…2025-08-15Wan 2.2 image-to-video Flash: faster…2025-09-12A Wan 2.2 first-and-last-frame model…2025-11-10Wan 2.2 Animate moves a character photo…
Fig. 1 One dot per dated entry.
Every Wan 2.2 entry, oldest first, read 2026-09-25.
DateWhat changedKindsSource
28 July 2025Wan 2.2 text-to-video Plus names complex movement and cinematic controlnew model, camera, motionMaker's note
15 August 2025Wan 2.2 image-to-video Flash: faster, with shot controltiers, cameraMaker's note
12 September 2025A Wan 2.2 first-and-last-frame model for transitions between two imagesframesMaker's note
10 November 2025Wan 2.2 Animate moves a character photo with the performance from a reference videomotion, referencesMaker'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.

The entries for Wan 2.2 cluster around a new model or snapshot, camera control or several shots and motion or performance transfer.

1Each entry

28 July 2025, from Alibaba Cloud Model Studio, newly released models

The upgraded Wan 2.2 Plus text to video model, delivers higher quality results with stable sweeping complex movements, cinematic vision control, more powerful prompt following, and realistic world recreation.

Alibaba Cloud Model Studio, newly released models

15 August 2025, from Alibaba Cloud Model Studio, newly released models

The upgraded Wan 2.2 image to video Flash model, delivers faster speed with optimized stability, more powerful prompt following, improved consistency for text, portraits, and products, and precise shot control.

Alibaba Cloud Model Studio, newly released models

12 September 2025, from Alibaba Cloud Model Studio, newly released models

The all-new Wan2.2 First and Last Frame to video model is here.

Alibaba Cloud Model Studio, newly released models

10 November 2025, from Alibaba Cloud Model Studio, newly released models

Users simply upload a character photo and a reference performance video, and the model transfers the expressions and actions from the video onto the character in the image

Alibaba Cloud Model Studio, newly released models

2Versions either side in this line

  • Dated before it: Wan 2.1, 5 entries, first dated 9 January 2025.
  • Dated after it: Wan 2.5, 1 entry, first dated 23 September 2025.

3Same kinds of change elsewhere, within six weeks

5 more such entries are on the quarter pages.

The whole line: Wan. Quarter: Q3 2025.

4Notes read

5Where new versions end up

Release notes such as “Wan 2.2” 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)