Which AI video release notes claim better motion?
Motion claims come with new models and updates: Runway's Gen-3 Alpha in July 2024, Wan 2.1 in January 2025 and Wan 2.2 in July, the Firefly Video Model's improved motion fidelity in July 2025, Hailuo 2.3 in October and HappyHorse 1.1 in June 2026. None of the notes gives a measure. As of 2026-09-25.
| Date | Line | Version | What changed |
|---|---|---|---|
| 1 July 2024 | Runway | Gen-3 Alpha | Gen-3 Alpha text-to-video, described as a step up in fidelity, consistency and motion |
| 9 January 2025 | Wan | Wan 2.1 | Wan 2.1 text-to-video Plus, with large movements and physical plausibility named |
| 17 July 2025 | Adobe Firefly Video | Firefly Video Model | Motion fidelity is improved, for smoother transitions and more natural movement |
| 28 July 2025 | Wan | Wan 2.2 | Wan 2.2 text-to-video Plus names complex movement and cinematic control |
| 28 October 2025 | MiniMax Hailuo | Hailuo 2.3 | Hailuo 2.3 and a 2.3 Fast tier, with body movement, faces and physics named as the gains |
| 16 June 2026 | HappyHorse | HappyHorse 1.1 | HappyHorse 1.1 text-to-video names shot control and motion rendering |
Inclusion rule. Entries whose note bears directly on the question. Order. By date, oldest first; undated rows last.
A motion claim describes how the output is said to look: smoother transitions, larger movements, physics that hold together, bodies and faces that move naturally. It cannot be checked from the note itself, only by trying the model on the same prompt before and after.
Controls over motion are a different kind of entry and have their own question: how much moves, and where.
1In the makers' words
Runway, 1 July 2024
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
Wan, 9 January 2025
Wan2.1 text to video Plus version, one sentence generated video. Support for large and complex movements, adherence to physical laws, artistic styles, and visual quality of movies.
Alibaba Cloud Model Studio, newly released models
- wan2.1-t2v-plusWan 2.1 text-to-video Plus, with large movements and physical plausibility named
Adobe Firefly Video, 17 July 2025
The Video Model’s newly improved motion fidelity means your video generations will now move more naturally, with smoother transitions and lifelike accuracy.
Adobe Blog, new Firefly video capabilities
- July 17Motion fidelity is improved, for smoother transitions and more natural movement2025
Wan, 28 July 2025
The upgraded Wan 2.2 Plus text to video model, delivers higher quality results with stable sweeping complex movements, cinematic vision control, more powerful prompt following, and realistic world recreation.
Alibaba Cloud Model Studio, newly released models
- wan2.2-t2v-plusWan 2.2 text-to-video Plus names complex movement and cinematic control
MiniMax Hailuo, 28 October 2025
Released MiniMax-Hailuo-2.3 & 2.3-Fast, featuring breakthroughs in body movement, facial expressions, physical realism, and prompt adherence.
MiniMax, model release notes
- MiniMax-Hailuo-2.3 & 2.3-FastHailuo 2.3 and a 2.3 Fast tier, with body movement, faces and physics named as the gains
HappyHorse, 16 June 2026
HappyHorse-1.1-T2V supports Text-to-Video generation with improved semantic understanding, cinematic shot control, and dynamic motion rendering.
Alibaba Cloud Model Studio, newly released models
- happyhorse-1.1-t2vHappyHorse 1.1 text-to-video names shot control and motion rendering
Motion and performance · Which AI video models take a reference video? · Which AI video models let you set how much moves?
2Notes read
- Runway, changelog, read 2026-09-25
- Alibaba Cloud Model Studio, newly released models, read 2026-09-25
- Adobe Blog, new Firefly video capabilities, read 2026-09-25
- MiniMax, model release notes, read 2026-09-25