Start creating with the MiniMax H3 Max AI video studio. Get started →

Home Guides MiniMax H3 Max image to video

MiniMax H3 Max guide

MiniMax H3 Max image to video

H3 Max Studio · last updated 3 September 2026

MiniMax H3 Max image to video starts from a still. The first image is the opening frame. An optional last image is the end keyframe. Aspect follows the first frame. Without a first image, fal treats the job as text to video.

First frame and last frame

Upload a first image to lock composition, wardrobe, and product. Add a last image when you need the shot to land on a specific end pose or layout. The model interpolates the move between the two stills while it writes audio from the prompt.

What I2V does not take

Image-to-video does not use the T2V aspect dropdown. The still sets the frame. Reference-to-video is the mode for extra image, video, and audio files (up to 12 total; audio cannot be the only file).

Credits

Duration still costs 5 credits per second. The first four images are included in that reservation. Extra images after four cost 10 credits each.

How to run MiniMax H3 Max image to video

  1. Switch the studio to Image / I2V.
  2. Drop a first-frame still. Optionally add a last-frame still.
  3. Prompt the motion, camera, and sound. Do not fight the still's framing.
  4. Generate, unmute to check audio, then download the MP4.

FAQ

Does MiniMax H3 Max image to video keep my composition?

It follows the first frame. Strong, well-lit stills hold better than busy collages.

Can I set 9:16 on I2V?

Not as a separate field. Export or crop the first image to the ratio you want.

What if I skip the first image?

fal treats the job as text-to-video.

Related MiniMax H3 Max guides