Wan 2.6 release notes, entry by entry
Wan 2.6, in the Wan line: 5 entries, 3 December 2025 to 29 January 2026, covering new model, camera, length, sound, references and tiers. Dated before it in this line: Wan 2.5. As of 2026-09-25.
| Date | What changed | Kinds | Source |
|---|---|---|---|
| 3 December 2025 | Wan 2.6 text-to-video plans several shots inside one clip of up to 15 seconds | new model, camera, length | Maker's note |
| 3 December 2025 | Wan 2.6 image-to-video handles dialogue between several speakers | sound | Maker's note |
| 16 December 2025 | Wan 2.6 reference-to-video keeps a person's look and voice, with several characters at once | references, sound | Maker's note |
| 15 January 2026 | A Flash tier of Wan 2.6 image-to-video: faster and lower cost | tiers | Maker's note |
| 29 January 2026 | A Flash tier of Wan 2.6 reference-to-video | tiers, 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.
The entries for Wan 2.6 cluster around a new model or snapshot, camera control or several shots and clip length or extension.
1Each entry
3 December 2025, from Alibaba Cloud Model Studio, newly released models
Intelligent shot scheduling supports multi-shot storytelling, generating multi-shot narrative videos with consistent subjects, scenes, and atmosphere, with a maximum duration of 15 seconds.
Alibaba Cloud Model Studio, newly released models
- wan2.6-t2vWan 2.6 text-to-video plans several shots inside one clip of up to 15 seconds
3 December 2025, from Alibaba Cloud Model Studio, newly released models
supports stable multi‑speaker dialogue with more natural and realistic vocal timbres
Alibaba Cloud Model Studio, newly released models
- wan2.6-i2v-usWan 2.6 image-to-video handles dialogue between several speakers
16 December 2025, from Alibaba Cloud Model Studio, newly released models
supports using a specified person or any object as a reference, precisely maintaining consistency of appearance and voice, and allows multi‑character reference for joint performances.
Alibaba Cloud Model Studio, newly released models
- wan2.6-r2vWan 2.6 reference-to-video keeps a person's look and voice, with several characters at once
15 January 2026, from Alibaba Cloud Model Studio, newly released models
Wan2.6 image to video flash, faster and more cost-effective generation.
Alibaba Cloud Model Studio, newly released models
- wan2.6-i2v-flashA Flash tier of Wan 2.6 image-to-video: faster and lower cost
29 January 2026, from Alibaba Cloud Model Studio, newly released models
Wan2.6 reference to video flash, faster and more cost-effective generation.
Alibaba Cloud Model Studio, newly released models
- wan2.6-r2v-flashA Flash tier of Wan 2.6 reference-to-video
2Versions either side in this line
- Dated before it: Wan 2.5, 1 entry, first dated 23 September 2025.
- Dated after it: Wan 2.7, 5 entries, first dated 3 April 2026.
3Same kinds of change elsewhere, within six weeks
- 20 October 2025, Kling AI: Kling 2.5 Turbo
- 21 October 2025, Vidu: Vidu Q2
- 28 October 2025, MiniMax Hailuo: Hailuo 2.3
- 11 November 2025, Kling AI: Kling 2.5 Turbo
- 13 November 2025, Vidu: Not named in the note
- 4 December 2025, Kling AI: Kling Avatar
- 8 December 2025, Google Veo: Veo 3.1
- 9 December 2025, LTX: Not named in the note
- 15 December 2025, Kling AI: Kling 2.6
- 15 December 2025, Kling AI: Kling Omni
- 16 December 2025, Adobe Firefly Video: Firefly Video Model
- 16 December 2025, Kling AI: Kling 2.6
5 more such entries are on the quarter pages.
The whole line: Wan. Quarter: Q4 2025.
4Notes read
- Alibaba Cloud Model Studio, newly released models, read 2026-09-25