Wan: clip length or extension, note by note
6 Wan entries on clip length or extension, 14 May 2025 to 24 August 2026, across Wan 2.1, Wan 2.5, Wan 2.6 and Wan 3.0. The latest: Wan 3.0 and Wan 3.0 Prime arrive on Higgsfield, up to 30 seconds. As of 2026-09-25.
| Line | Entries |
|---|---|
| Adobe Firefly Video | 1 |
| Amazon Nova Reel | 2 |
| Gemini Omni | 3 |
| Google Veo | 4 |
| Kling AI | 3 |
| LTX | 2 |
| Midjourney video | 1 |
| MiniMax Hailuo | 2 |
| PixVerse | 2 |
| Runway | 3 |
| Seedance | 7 |
| Sora | 1 |
| Vidu | 1 |
| Wan | 6 |
Inclusion rule. Lines with at least one entry of this kind. Order. Alphabetical by line.
Of Wan's entries, 6 concern clip length or extension, 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
- wan2.1-vace-plusWan 2.1 VACE combines local editing, repainting, outpainting, extension and image references
23 September 2025, Wan 2.5
newly upgraded model architecture supports synchronized audio generation with visuals, enables 10-second long video generation
Alibaba Cloud Model Studio, newly released models
- wan2.5-t2v-previewWan 2.5 preview generates synchronised audio and 10 second clips
The gap from the previous entry: 132 days.
3 December 2025, Wan 2.6
Intelligent shot scheduling supports multi-shot storytelling, generating multi-shot narrative videos with consistent subjects, scenes, and atmosphere, with a maximum duration of 15 seconds.
Alibaba Cloud Model Studio, newly released models
- wan2.6-t2vWan 2.6 text-to-video plans several shots inside one clip of up to 15 seconds
The gap from the previous entry: 71 days.
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
- wan3.0-videoWan 3.0 folds reference, editing, replication and driving into one model, with clips up to 30 seconds
The gap from the previous entry: 246 days.
24 August 2026, Wan 3.0
Up to 30 seconds per generation, at 480p, 720p, or 1080p.
Higgsfield, changelog
- Wan 3.0 and Wan 3.0 PrimeWan 3.0 and Wan 3.0 Prime arrive on Higgsfield, up to 30 seconds
The gap from the previous entry: 18 days.
Undated tier row, Wan 3.0
Wan 3.0 ยท 480P (default)
SceneMixer, pricing page
- Video tiers tableSceneMixer's tier list carries Wan 3.0 at 480p, its default, and at 720p and 1080p, each up to 30 seconds a clip
2The same kind of change in other lines
- Adobe Firefly Video: 1 entry, October 2024
- Amazon Nova Reel: 2 entries, April 2025
- Gemini Omni: 3 entries, June 2026 to August 2026
- Google Veo: 4 entries, June 2025 to December 2025
- Kling AI: 3 entries, June 2025 to December 2025
- LTX: 2 entries, February 2026 to August 2026
- Midjourney video: 1 entry, June 2025
- MiniMax Hailuo: 2 entries, June 2025
- PixVerse: 2 entries, July 2025 to March 2026
- Runway: 3 entries, September 2024 to November 2024
- Seedance: 7 entries, August 2026
- Sora: 1 entry, March 2026
- Vidu: 1 entry, October 2025
Wan, every entry · Clip length and extension, every line · Wan 2.1 · Wan 2.6 · Wan 3.0
3Notes read
- Alibaba Cloud Model Studio, newly released models, read 2026-09-25
- Higgsfield, changelog, read 2026-09-25
- SceneMixer, pricing page, read 2026-09-25