How to Extend a Video with AI: Add 5–7 Seconds from the Last Frame

What the extend tool does

Upload the video and describe what happens next. The model continues from the last frame and the new part is joined to the end of your video. The length added per run depends on the model: 7 seconds with Veo 3.1 Fast and Veo 3.1, 5 seconds with LTX-2.3.

Because the continuation starts from the last frame, it tends to keep the people, background and colours of your video. To go longer, extend the result again.

• Input: the video to extend (up to 60 s) and what happens next (required)
• Output: an MP4 of your video with the continuation joined on
• Models: Veo 3.1 Fast, Veo 3.1, LTX-2.3

What to prepare (video and continuation)

• Video: up to 60 seconds; landscape 16:9 or vertical 9:16 works best. LTX-2.3 needs at least 3 seconds
• Last frame: videos that end on a clear, sharp frame connect more smoothly
• Continuation: describe what happens and how the camera moves, e.g. "the camera pulls back to show the city at night"
• Rights: videos made with other services are fine as long as you own the rights

How to extend a video with AI

1. 1Open the video tools

   In the studio, open Video tools and choose Extend a video.

2. 2Add the video

   Upload the video to continue (up to 60 seconds).

3. 3Describe what happens next

   Write the continuation.

4. 4Pick a model and estimate

   Choose a model, press Estimate and check the added length and credits.

5. 5Generate and download

   Tick the rights box, generate and download the extended video.

See also: Extend video tool overview

Models you can choose, and approximate credits for 5 seconds

Veo 3.1 Fast and Veo 3.1 add 7 seconds with sound; Veo 3.1 has higher quality and uses more credits. LTX-2.3 adds 5 seconds with fewer credits. LTX-2.3 uses the last 3 seconds of your video as context, so those 3 seconds are also counted.

Fixing common problems

• The picture changes at the join: blurry or dark last frames connect poorly. Trim the video so it ends on a clear frame
• The continuation is not what you wanted: write who does what and how the camera moves in one or two concrete sentences
• You want it much longer: extend the result again. Source videos are limited to 60 seconds, so for long videos extend only the last part and join it in your editor
• You want sound: Veo 3.1 Fast and Veo 3.1 generate sound

Rights and AI disclosure

Only use images, audio and video that you own or have permission to use. Real people's faces and voices may only be used with that person's permission. Before generating, you tick a box confirming you have the rights.

You may not make videos that show someone saying something they did not say in a misleading way, or that impersonate someone. When you publish, label the video as AI-generated or AI-edited according to the platform's rules (for example, YouTube's altered or synthetic content setting).

Model names in this guide and in the product are listed because you can choose them in BunCho. Listing them does not imply any partnership with or endorsement by their makers.

Plans and credits

The video tools are available on paid plans (Watering, Seed, Feast, Full Course, Team & Business) with an active subscription. They are not available on the free plan or during a paid plan's free trial.

They use your studio's monthly AI credits, the same balance as novels, manga and video. You see an estimate before generating and nothing is made until you agree. No credits are used if a job fails or if you cancel it before it starts.

See also: Plans and pricing / All five video tools