MiniMax H3 Image to Video

MiniMax H3 Image to Video · MiniMax — Image to video · 4–15 s · Up to 2K · End frame. Call it through one queue API and pay for the options you pick.

modellane/minimax-h3-image-to-video · Image to video · MiniMax

Image to video model: 4–15 s, up to 2K, end frame.

Vendor
MiniMax
Task
Image to video
Output
Video
Price
From $0.43 per run
Longest run
15 seconds

Input parameters

  • Prompt prompt — required Describe what you want produced as concretely as you can.
  • Source image image — optional The frame the generation starts from.
  • End frame image end_image — optional If given, the generation ends on this image; it can be left empty.
  • Resolution resolution — required, options: 768p, 2K The output resolution.
  • Duration duration — required, default: 8, options: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 A longer duration raises the price directly.
  • Aspect ratio ratio — optional, options: Auto Sets whether the output is square, portrait, or landscape; with "Auto" the model picks the ratio.
  • Prompt expansion prompt_expansion — optional, default: No When on, the model enriches the prompt with its own rules.

Output and retention

The generated file and your input are kept for seven days and then deleted.

Queue API

Submit to the queue: POST /v1/queue/modellane/minimax-h3-image-to-video

Status, result, cancellation and error codes work the same for every model; see the API docs.

Playground

Everything on this page is public; you need an account to run the model.