VideoGenReview

What each AI video model's release notes say changed

Wan release notes on references or consistency

6 Wan entries on references or consistency, 14 May 2025 to 6 August 2026, across Wan 2.1, Wan 2.2, Wan 2.6 and Wan 2.7 and more. The latest: Wan 3.0 folds reference, editing, replication and driving into one model, with clips up to 30 seconds. As of 2026-09-25.

Entries on references per line, this one markedA count of entries, which follows how often a maker writes notes.Entries on references per line, this one markedWan66Kling AI55PixVerse55HappyHorse33Runway33Vidu33Adobe Firefly Video22Google Veo22MiniMax Hailuo22Grok Imagine11Luma Ray11Seedance11Sora11
Fig. 1 A count of entries, which follows how often a maker writes notes.
Entries on references or consistency per line, read 2026-09-25.
LineEntries
Adobe Firefly Video2
Google Veo2
Grok Imagine1
HappyHorse3
Kling AI5
Luma Ray1
MiniMax Hailuo2
PixVerse5
Runway3
Seedance1
Sora1
Vidu3
Wan6

Inclusion rule. Lines with at least one entry of this kind. Order. Alphabetical by line.

Of Wan's entries, 6 concern references or consistency, the first from May 2025.

1The entries

14 May 2025, Wan 2.1

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

10 November 2025, Wan 2.2

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

180 days after the entry before it.

16 December 2025, Wan 2.6

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

It came 36 days after the previous one.

29 January 2026, Wan 2.6

Wan2.6 reference to video flash, faster and more cost-effective generation.

Alibaba Cloud Model Studio, newly released models

The gap from the previous entry: 44 days.

3 April 2026, Wan 2.7

Supports hybrid referencing of up to 5 mixed image/video inputs and audio timbre cloning.

Alibaba Cloud Model Studio, newly released models

64 days after the entry before it.

6 August 2026, Wan 3.0

It supports four-modal all-reference input, up to 30 seconds of video generation, and can parse files, web pages, and complex images.

Alibaba Cloud Model Studio, newly released models

The gap from the previous entry: 125 days.

2The same kind of change in other lines

  • Adobe Firefly Video: 2 entries, July 2025 to December 2025
  • Google Veo: 2 entries, October 2025 to January 2026
  • Grok Imagine: 1 entry, July 2026
  • HappyHorse: 3 entries, April 2026 to June 2026
  • Kling AI: 5 entries, December 2025 to March 2026
  • Luma Ray: 1 entry, December 2025
  • MiniMax Hailuo: 2 entries, July 2026 to August 2026
  • PixVerse: 5 entries, August 2025 to July 2026
  • Runway: 3 entries, December 2024 to June 2025
  • Sora: 1 entry, March 2026
  • Vidu: 3 entries, August 2025 to September 2026

Wan, every entry · References and consistency, every line · Wan 2.1 · Wan 2.2 · Wan 2.6 · Wan 2.7 · Wan 3.0

3Notes read