Wan: editing existing video, note by note
3 Wan entries on editing existing video, 14 May 2025 to 6 August 2026, across Wan 2.1, Wan 2.7 and Wan 3.0. The latest: Wan 3.0 folds reference, editing, replication and driving into one model, with clips up to 30 seconds. From 1 source page, read 2026-09-25; no maker pays to be listed.
| Line | Entries |
|---|---|
| Adobe Firefly Video | 1 |
| Gemini Omni | 2 |
| HappyHorse | 1 |
| Kling AI | 1 |
| LTX | 2 |
| Luma Ray | 4 |
| PixVerse | 3 |
| Runway | 6 |
| Seedance | 1 |
| Sora | 1 |
| Wan | 3 |
Inclusion rule. Lines with at least one entry of this kind. Order. Alphabetical by line.
The register holds 3 Wan entries on editing existing video; the first is dated 14 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
3 April 2026, Wan 2.7
Wan2.7 video edit, supports both localized and global editing with prompt.
Alibaba Cloud Model Studio, newly released models
- wan2.7-videoeditWan 2.7 video edit makes local or whole-clip edits from a prompt
It came 324 days after the previous one.
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: 125 days.
2The same kind of change in other lines
- Adobe Firefly Video: 1 entry, October 2024
- Gemini Omni: 2 entries, June 2026
- HappyHorse: 1 entry, April 2026
- Kling AI: 1 entry, June 2026
- LTX: 2 entries, November 2025 to July 2026
- Luma Ray: 4 entries, May 2025 to December 2025
- PixVerse: 3 entries, September 2025 to April 2026
- Runway: 6 entries, September 2024 to May 2026
- Sora: 1 entry, March 2026
Wan, every entry · Editing video that exists, every line · Wan 2.1 · Wan 2.7 · Wan 3.0
3Notes read
- Alibaba Cloud Model Studio, newly released models, read 2026-09-25
4A pipeline on current models
Release notes such as “Wan” matter once a pipeline runs the models; SceneMixer's guides describe how it does:
The Seedance 2.0 tiers render segments up to 15 seconds; use a Seedance 2.5 or Wan tier for 30-second takes.
SceneMixer, Seedance 2.0 Fast — “Does Fast render 30-second takes?” (read 2026-10-13)
When you edit a sheet (change the hair, swap the coat, add a scar) or generate a state (the drawn blade, the burnt room), the model starts from the existing image and reads your text as what to change.
SceneMixer, Editing a Sheet or Making a State: Write the Change, Not the Whole Picture (read 2026-10-13)