VideoGenReview

What each AI video model's release notes say changed

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. From 11 source pages, read 2026-09-25 to 2026-10-25; no maker pays to be listed.

The entries by dateOne dot per dated entry.The entries by date2024-09-04Runway, Gen-3 Alpha2024-09-23Runway, Gen-3 Alpha Turbo2024-10-14Adobe Firefly Video, Firefly Video Model2025-05-14Wan, Wan 2.12025-06-18Midjourney video, Midjourney V1 video2025-06-21PixVerse, Not named in the note2025-06-23Google Veo, Veo 22025-10-15Google Veo, Veo 3.12025-10-21Vidu, Vidu Q22025-12-08Google Veo, Veo 3.12026-02-18LTX, Not named in the note2026-03-12Sora, Sora 22026-03-31PixVerse, PixVerse V62026-08-27Gemini Omni, Gemini Omni 1.1 Flash
Fig. 1 One dot per dated entry.
Entries that answer this question, oldest first, read 2026-09-25.
DateLineVersionWhat changed
4 September 2024RunwayGen-3 AlphaGen-3 Alpha clips can be extended to 40 seconds in total
23 September 2024RunwayGen-3 Alpha TurboGen-3 Alpha Turbo clips extend to 34 seconds
14 October 2024Adobe Firefly VideoFirefly Video ModelGenerative Extend in the Premiere Pro beta lengthens clips to cover gaps and hold shots longer
14 May 2025WanWan 2.1Wan 2.1 VACE combines local editing, repainting, outpainting, extension and image references
18 June 2025Midjourney videoMidjourney V1 videoThe V1 video model animates images, with low or high motion and extensions of about 4 seconds
21 June 2025PixVerseNot named in the noteCamera-control parameters, speech (lip sync) and video extend are released
23 June 2025Google VeoVeo 2Veo 2 on Vertex AI takes a last frame as well as a first, or a video to extend
15 October 2025Google VeoVeo 3.1Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame input
21 October 2025ViduVidu Q2Q2 gains reference-to-video, text-to-video and extension
8 December 2025Google VeoVeo 3.1Veo 3.1 video extension reaches Vertex AI in preview
18 February 2026LTXNot named in the noteAn extend endpoint adds frames at the start or the end
12 March 2026SoraSora 2Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobs
31 March 2026PixVersePixVerse V6V6 covers text-to-video, image-to-video, first and last frame and extend
27 August 2026Gemini OmniGemini Omni 1.1 FlashGemini Omni 1.1 Flash goes GA with extension, first-and-last-frame input and 360p to 4K output
Undated version rowSeedanceSeedance 2.0Seedance 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 Alpha
    Gen-3 Alpha clips can be extended to 40 seconds in totalRunway, changelog / since 2024-09-04 / checked 2026-09-25

Runway, 23 September 2024

Extend generations up to 34s in Gen-3 Alpha Turbo.

Runway, changelog
  • Gen-3 Alpha Turbo Extensions
    Gen-3 Alpha Turbo clips extend to 34 secondsRunway, changelog / since 2024-09-23 / checked 2026-09-25

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

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

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 Model
    The V1 video model animates images, with low or high motion and extensions of about 4 secondsMidjourney, V1 video model announcement / since 2025-06-18 / checked 2026-09-25

PixVerse, 21 June 2025

Released camera-control parameters, Speech (Lip Sync), and Video Extend.

PixVerse, API changelog
  • 2025-06-21
    Camera-control parameters, speech (lip sync) and video extend are releasedPixVerse, API changelog / since 2025-06-21 / checked 2026-10-25

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

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 15
    Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame input2025Google, Gemini API changelog / since 2025-10-15 / checked 2026-09-25

Vidu, 21 October 2025

Viduq2 models upgraded new abilities: Reference to video, Text to video and Video extension.

Vidu, API update notice
  • October 21
    Q2 gains reference-to-video, text-to-video and extension2025Vidu, API update notice / since 2025-10-21 / checked 2026-09-25

Google Veo, 8 December 2025

Veo 3.1 supports video extension in Preview.

Google Cloud, Vertex AI release notes

LTX, 18 February 2026

for extending video duration by generating additional frames at the beginning or end.

LTX, API changelog
  • Extend Video Endpoint
    An extend endpoint adds frames at the start or the endLTX, API changelog / since 2026-02-18 / checked 2026-09-25

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 12
    Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobs2026OpenAI, API changelog / since 2026-03-12 / checked 2026-09-25

PixVerse, 31 March 2026

Added V6 support for Text-to-Video, Image-to-Video, First and Last Frame Video, and Video Extend.

PixVerse, API changelog
  • 2026-03-31
    V6 covers text-to-video, image-to-video, first and last frame and extendPixVerse, API changelog / since 2026-03-31 / checked 2026-10-25

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 27
    Gemini Omni 1.1 Flash goes GA with extension, first-and-last-frame input and 360p to 4K output2026Google, Gemini API changelog / since 2026-08-27 / checked 2026-09-25

Seedance, Undated version row

4K (10-bit color depth)

BytePlus ModelArk, model list
  • dreamina-seedance-2-0-260128
    Seedance 2.0: 4 to 15 seconds, up to 4K, multimodal references, editing and extensionBytePlus ModelArk, model list / recorded 2026-09-25

Clip length and extension · How many reference images do AI video models take? · Can AI video models edit part of a clip?

2Notes read

3Where new versions end up

Release notes such as “Which AI video models can extend a clip?” matter once a pipeline runs the models; SceneMixer's guides describe how it does:

The shots add up to more than the selected video tier allows for one segment.

SceneMixer, Shot Seconds: Changing Timing, and the Limits — “What does 'over cap' mean on the segment card?” (read 2026-10-13)

Video is 16:9 landscape by default, with 9:16 vertical available; you set it once per project. Segments are typically 4 to 15 seconds, and some model tiers go to 30.

SceneMixer, AI Short Drama Generator — “What length and aspect ratio does it output?” (read 2026-10-13)