Runway release notes on motion or performance transfer
3 Runway entries on motion or performance transfer, 1 July 2024 to 17 July 2025, across Gen-3 Alpha, Act-One and Act-Two. The latest: Act-Two tracks head, face, body and hands. From 1 source page, read 2026-09-25; no maker pays to be listed.
| Line | Entries |
|---|---|
| Adobe Firefly Video | 1 |
| HappyHorse | 1 |
| Kling AI | 4 |
| Luma Ray | 1 |
| Midjourney video | 1 |
| MiniMax Hailuo | 1 |
| PixVerse | 1 |
| Runway | 3 |
| Wan | 3 |
Inclusion rule. Lines with at least one entry of this kind. Order. Alphabetical by line.
Of Runway's entries, 3 concern motion or performance transfer, the first from July 2024.
1The entries
1 July 2024, Gen-3 Alpha
It is a major improvement in fidelity, consistency, and motion over Gen-2
Runway, changelog
- Gen-3 Alpha Text to VideoGen-3 Alpha text-to-video, described as a step up in fidelity, consistency and motion
25 October 2024, Act-One
A new way to generate expressive character performances inside Gen-3 Alpha using a single driving video and character image.
Runway, changelog
- Act-One in Gen-3 AlphaAct-One drives a character from one performance video and one image
116 days after the entry before it.
17 July 2025, Act-Two
Next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking.
Runway, changelog
- Act-TwoAct-Two tracks head, face, body and hands
265 days after the entry before it.
2The same kind of change in other lines
- Adobe Firefly Video: 1 entry, July 2025
- HappyHorse: 1 entry, June 2026
- Kling AI: 4 entries, November 2024 to March 2026
- Luma Ray: 1 entry, June 2025
- Midjourney video: 1 entry, June 2025
- MiniMax Hailuo: 1 entry, October 2025
- PixVerse: 1 entry, February 2026
- Wan: 3 entries, January 2025 to November 2025
Runway, every entry · Motion and performance, every line · Gen-3 Alpha
3Notes read
- Runway, changelog, read 2026-09-25
4A pipeline on current models
Release notes such as “Runway” 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)
It is one of the 2K tiers, with SeedDream 5.0 Lite; the Qwen tiers render at lower pixel counts.
SceneMixer, SeedDream 5.0 Pro — “Is this the highest-resolution image tier?” (read 2026-10-13)