Which AI video models can extend a clip?
Extension appears early: Gen-3 Alpha to 40 seconds in total in September 2024, Gen-3 Alpha Turbo to 34, and Firefly's Generative Extend in October. During 2025 Wan 2.1 VACE, Midjourney, Veo 2 and 3.1, PixVerse and Vidu Q2 add it; in 2026 LTX, Sora, PixVerse V6 and Gemini Omni 1.1 Flash. Seedance 2.0 lists it among its capabilities. As of 2026-09-25.
| Date | Line | Version | What changed |
|---|---|---|---|
| 4 September 2024 | Runway | Gen-3 Alpha | Gen-3 Alpha clips can be extended to 40 seconds in total |
| 23 September 2024 | Runway | Gen-3 Alpha Turbo | Gen-3 Alpha Turbo clips extend to 34 seconds |
| 14 October 2024 | Adobe Firefly Video | Firefly Video Model | Generative Extend in the Premiere Pro beta lengthens clips to cover gaps and hold shots longer |
| 14 May 2025 | Wan | Wan 2.1 | Wan 2.1 VACE combines local editing, repainting, outpainting, extension and image references |
| 18 June 2025 | Midjourney video | Midjourney V1 video | The V1 video model animates images, with low or high motion and extensions of about 4 seconds |
| 23 June 2025 | Google Veo | Veo 2 | Veo 2 on Vertex AI takes a last frame as well as a first, or a video to extend |
| 14 July 2025 | PixVerse | Not named in the note | Lip-sync and extend arrive |
| 15 October 2025 | Google Veo | Veo 3.1 | Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame input |
| 21 October 2025 | Vidu | Vidu Q2 | Q2 gains reference-to-video, text-to-video and extension |
| 8 December 2025 | Google Veo | Veo 3.1 | Veo 3.1 video extension reaches Vertex AI in preview |
| 18 February 2026 | LTX | Not named in the note | An extend endpoint adds frames at the start or the end |
| 12 March 2026 | Sora | Sora 2 | Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobs |
| 29 March 2026 | PixVerse | PixVerse V6 | V6 covers text-to-video, image-to-video, transition and extend |
| 27 August 2026 | Gemini Omni | Gemini Omni 1.1 Flash | Gemini Omni 1.1 Flash goes GA with extension, first-and-last-frame input and 360p to 4K output |
| Undated version row | Seedance | Seedance 2.0 | Seedance 2.0: 4 to 15 seconds, up to 4K, multimodal references, editing and extension |
Inclusion rule. Entries whose note bears directly on the question. Order. By date, oldest first; undated rows last.
Extension continues a finished clip with another generation that picks up where it ended. It is how clips got long before single generations did: Midjourney's first video model extended in steps of roughly four seconds, up to four times.
The notes differ on where the new footage goes. LTX's extend endpoint adds frames at the beginning or the end; Google's Gemini Omni note describes continuations at the end of a clip. Most notes do not say.
1In the makers' words
Runway, 4 September 2024
Gen-3 Alpha videos can be extended an additional 5 or 10 seconds to create up to 40s of generated video.
Runway, changelog
- Extensions in Gen-3 AlphaGen-3 Alpha clips can be extended to 40 seconds in total
Runway, 23 September 2024
Extend generations up to 34s in Gen-3 Alpha Turbo.
Runway, changelog
- Gen-3 Alpha Turbo ExtensionsGen-3 Alpha Turbo clips extend to 34 seconds
Adobe Firefly Video, 14 October 2024
Generative Extend allows you to extend clips to cover gaps in footage, smooth out transitions, or hold on shots longer for perfectly timed edits.
Adobe, news release: Firefly Video Model launch
- October 14Generative Extend in the Premiere Pro beta lengthens clips to cover gaps and hold shots longer2024
Wan, 14 May 2025
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
Midjourney video, 18 June 2025
Once you have a video you like you can “extend” them - roughly 4 seconds at a time - four times total.
Midjourney, V1 video model announcement
- Introducing Our V1 Video ModelThe V1 video model animates images, with low or high motion and extensions of about 4 seconds
Google Veo, 23 June 2025
In addition to a providing a first frame of a video, you can specify the last frame of a video or a video to extend in length.
Google Cloud, Vertex AI release notes
- June 23Veo 2 on Vertex AI takes a last frame as well as a first, or a video to extend2025
PixVerse, 14 July 2025
Lip-sync, Extend feature release
PixVerse, API changelogs
- 2025/07/14Lip-sync and extend arrive
Google Veo, 15 October 2025
Released Veo 3.1 and 3.1 Fast models in public preview, with new features including: Extending Veo-created videos. Referencing up to three images to generate a video. Providing first and last frame images to generate videos from.
Google, Gemini API changelog
- October 15Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame input2025
Vidu, 21 October 2025
Viduq2 models upgraded new abilities: Reference to video, Text to video and Video extension.
Vidu, API update notice
- October 21Q2 gains reference-to-video, text-to-video and extension2025
Google Veo, 8 December 2025
Veo 3.1 supports video extension in Preview.
Google Cloud, Vertex AI release notes
- December 8Veo 3.1 video extension reaches Vertex AI in preview2025
LTX, 18 February 2026
for extending video duration by generating additional frames at the beginning or end.
LTX, API changelog
- Extend Video EndpointAn extend endpoint adds frames at the start or the end
Sora, 12 March 2026
Expanded the Sora API with reusable character references, longer generations up to 20 seconds, 1080p output for sora-2-pro , video extensions, and Batch API support for POST /v1/videos .
OpenAI, API changelog
- March 12Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobs2026
PixVerse, 29 March 2026
v6 model released!
PixVerse, API changelogs
- 2026/03/29V6 covers text-to-video, image-to-video, transition and extend
Gemini Omni, 27 August 2026
Resolution control : New resolution parameter in video_config supports 360p , 720p (default), 1080p , and 4k outputs.
Google, Gemini API changelog
- August 27Gemini Omni 1.1 Flash goes GA with extension, first-and-last-frame input and 360p to 4K output2026
Seedance, Undated version row
4K (10-bit color depth)
BytePlus ModelArk, model list
- dreamina-seedance-2-0-260128Seedance 2.0: 4 to 15 seconds, up to 4K, multimodal references, editing and extension
Clip length and extension · How many reference images do AI video models take? · Can AI video models edit part of a clip?
2Notes read
- Runway, changelog, read 2026-09-25
- Adobe, news release: Firefly Video Model launch, read 2026-09-25
- Alibaba Cloud Model Studio, newly released models, read 2026-09-25
- Midjourney, V1 video model announcement, read 2026-09-25
- Google Cloud, Vertex AI release notes, read 2026-09-25
- PixVerse, API changelogs, read 2026-09-25
- Google, Gemini API changelog, read 2026-09-25
- Vidu, API update notice, read 2026-09-25
- LTX, API changelog, read 2026-09-25
- OpenAI, API changelog, read 2026-09-25
- BytePlus ModelArk, model list, read 2026-09-25