VideoGenReview

What each AI video model's release notes say changed

Motion and performance transfer, dated

16 entries on motion or performance transfer from 9 of the 17 lines, dated 1 July 2024 to 16 June 2026. The table lists each with its line and version; the chart counts them per line. As of 2026-09-25.

1Reading the notes

Motion notes cover two things: claims that movement looks better, and tools that copy a performance. Claims appear with new models, as with Hailuo 2.3's body movement and physics or Wan 2.2's sweeping movements, and in updates such as the Firefly Video Model's improved motion fidelity in July 2025. Performance transfer is a thread of its own: Runway's Act-One in October 2024 and Act-Two in July 2025, Wan 2.2 Animate, Kling's Motion Control from December 2025 and PixVerse's Mimic in February 2026.

Entries on motion per lineCounted from the table. Lines without an entry of this kind are left out.Entries on motion per lineKling AI44Runway33Wan33Adobe Firefly Video11HappyHorse11Luma Ray11Midjourney video11MiniMax Hailuo11PixVerse11
Fig. 1 Counted from the table. Lines without an entry of this kind are left out.
Entries on motion or performance transfer per line, read 2026-09-25.
LineEntries
Adobe Firefly Video1
HappyHorse1
Kling AI4
Luma Ray1
Midjourney video1
MiniMax Hailuo1
PixVerse1
Runway3
Wan3

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

2Every entry

Every entry on motion or performance transfer, oldest first.
DateLineVersionWhat changed
1 July 2024RunwayGen-3 AlphaGen-3 Alpha text-to-video, described as a step up in fidelity, consistency and motion
25 October 2024RunwayAct-OneAct-One drives a character from one performance video and one image
29 November 2024Kling AIKling 1.0Motion Brush arrives for the 1.0 model at 5 seconds
9 January 2025WanWan 2.1Wan 2.1 text-to-video Plus, with large movements and physical plausibility named
2 June 2025Luma RayNot named in the noteModify Video keeps a performance and changes the world around it
18 June 2025Midjourney videoMidjourney V1 videoThe V1 video model animates images, with low or high motion and extensions of about 4 seconds
17 July 2025Adobe Firefly VideoFirefly Video ModelMotion fidelity is improved, for smoother transitions and more natural movement
17 July 2025RunwayAct-TwoAct-Two tracks head, face, body and hands
28 July 2025WanWan 2.2Wan 2.2 text-to-video Plus names complex movement and cinematic control
28 October 2025MiniMax HailuoHailuo 2.3Hailuo 2.3 and a 2.3 Fast tier, with body movement, faces and physics named as the gains
10 November 2025WanWan 2.2Wan 2.2 Animate moves a character photo with the performance from a reference video
17 December 2025Kling AIKling 2.6Kling 2.6 Motion Control copies an action and expression, up to 30 seconds in one take
22 December 2025Kling AINot named in the noteMotion Control in the API takes a reference image and a reference video together
28 February 2026PixVerseNot named in the noteMimic motion control is released
4 March 2026Kling AIKling 3.0Kling 3.0 Motion Control launches
16 June 2026HappyHorseHappyHorse 1.1HappyHorse 1.1 text-to-video names shot control and motion rendering

Inclusion rule. All entries tagged with this kind of change, including platform arrivals and undated rows. Order. By date, oldest first; undated rows last.

3One line at a time

4Using the models, not reading about them

Release notes such as “Motion and performance” matter once a pipeline runs the models; SceneMixer's guides describe how it does:

Dubbing replaces the audio of a finished clip; the picture was generated for a different line, so mouth shapes, pauses and shot length all belong to the original language. Native-language generation gives the video model the line in the target language before it renders the shot, so the performance, the pacing and the cut points are built for that language.

SceneMixer, Native-Language Dialogue vs. Dubbing in AI Video (2026): Why the Cast Should Speak the Line (read 2026-10-13)

Video is 16:9 landscape by default, with 9:16 vertical available; you set it once per project. Segments are typically 4 to 15 seconds, and some model tiers go to 30.

SceneMixer, AI Short Drama Generator — “What length and aspect ratio does it output?” (read 2026-10-13)

5Other kinds of change