Make a Video from a First and Last Frame with AI

What the start & end frame tool does

Add a start image and an end image and describe how things move. You get a video that moves from the first picture to the last. The end image is optional; without it, the start image is animated as you describe (image to video).

Because both ends are fixed as pictures, it suits connecting two manga panels, making the moment an expression or pose changes, and planning the first and last shot of a scene before generating the motion between them.

• Input: a start image (required), an end image (optional) and how it moves (required)
• Length: choose 3, 5, 7 or 10 seconds (some models use their nearest supported length)
• Models: Kling 3.0 Pro / Standard, Kling 2.6 Pro, Veo 3.1 Fast, Seedance 2.0, Wan 3.0

What to prepare (two images and a description)

• Start image: PNG, JPEG or WebP; short side at least 300 px; aspect ratio between 1:2.5 and 2.5:1
• End image: same aspect ratio as the start image. If the person or background changes too much, the middle tends to look unnatural
• How it moves: describe the action, direction and camera, e.g. "turns around, waves and walks toward the window"
• For two pictures of the same character, keeping the look consistent with the studio's character settings makes the transition smoother

How to make a video from start and end frames

1. 1Open the video tools

   In the studio, open Video tools and choose Start & end frame.

2. 2Add the start image

   Upload the start image. Add an end image if you want to fix the last frame.

3. 3Describe the motion and choose the length

   Write how it moves and choose 3, 5, 7 or 10 seconds.

4. 4Pick a model and estimate

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

5. 5Generate and download

   Tick the rights box, generate and download the result.

See also: Start & end frame tool overview

Models you can choose, and approximate credits for 5 seconds

Kling 3.0 Pro outputs 1080p and Standard 720p, both without sound. Kling 2.6 Pro only makes 5 or 10 seconds and uses fewer credits. Veo 3.1 Fast adds sound and makes 4, 6 or 8 seconds. Seedance 2.0 and Wan 3.0 output 720p.

Fixing common problems

• Shapes fall apart in the middle: the start and end pictures are too different. Make one picture in between and connect them in two steps
• It does not move the way you want: add who moves, which direction and what the camera does
• The length differs from what you chose: Veo 3.1 Fast makes 4, 6 or 8 s and Kling 2.6 Pro 5 or 10 s, so they use the nearest length at or above your choice
• You want sound: Veo 3.1 Fast generates sound. For other models, add music or voice in your editor

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