VideoGenReview

What each AI video model's release notes say changed

Kling AI and references or consistency: the dated notes

5 Kling AI entries on references or consistency, 15 December 2025 to 23 March 2026, across Kling Omni and Kling 3.0. The latest: elements made from several images can be tied to a voice. 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.

The register holds 5 Kling AI entries on references or consistency; the first is dated 15 December 2025.

1The entries

15 December 2025, Kling Omni

Omni-Video model launched New API, multiple feature can be achieved through prompt words alone.

Kling AI, API updates
  • 12/15/2025
    The Omni video model launches on a new API driven by prompt wordsKling AI, API updates / since 2025-12-15 / checked 2026-09-25

22 December 2025, Not named in the note

both reference images and reference videos need to be uploaded simultaneously

Kling AI, API updates
  • 12/22/2025
    Motion Control in the API takes a reference image and a reference video togetherKling AI, API updates / since 2025-12-22 / checked 2026-09-25

It came 7 days after the previous one.

23 January 2026, Not named in the note

Supports intelligent completion of images from different angles of the element

Kling AI, API updates
  • 01/23/2026
    Other angles of an element can be filled in from its front viewKling AI, API updates / since 2026-01-23 / checked 2026-09-25

It came 32 days after the previous one.

25 February 2026, Kling 3.0

Supports the creation of elements through video

Kling AI, API updates
  • 02/25/2026
    Kling 3.0 and 3.0 Omni reach the API; elements can be built from videoKling AI, API updates / since 2026-02-25 / checked 2026-09-25

33 days after the entry before it.

23 March 2026, Not named in the note

Multi-image elements also support binding timbres

Kling AI, API updates
  • 03/23/2026
    Elements made from several images can be tied to a voiceKling AI, API updates / since 2026-03-23 / checked 2026-09-25

26 days after the entry before it.

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
  • 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: 6 entries, May 2025 to August 2026

Kling AI, every entry · References and consistency, every line · Kling 3.0

3Notes read