Available now

MiniMax Video-01 Subject Reference: video from a subject

By MiniMax

MiniMax Video-01 Subject Reference makes a video from a prompt and one photo of a person, keeping that person's face throughout.

Model ID
Maker
MiniMax

Input

Fields marked * are required. Review the price before generating.

Example prompt. Edit it or write your own.

The subject reference image to use for consistent subject appearance

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

Whether to use the model's prompt optimizer

Price$0.80 / run

You sign up first. Your settings are kept.

About this model

Overview

Upload a photo of the subject and describe the scene. The video shows the same face and identity in a new setting and action that you write. The prompt optimizer rewrites your prompt before rendering; turn it off to keep your exact wording.

What you can build

  • A person from one photo placed in new scenes and actions
  • A series of clips with the same lead character
  • Short story scenes starring a recurring face

Prompting tips

  • Use a clear, well-lit photo where the face is large and not turned away.
  • Describe the scene and the action; the photo already sets how the person looks.

What to check

Watch the entire clip and compare motion, identity, transitions and audio with your inputs.

Inputs

  • Prompt (required)
  • Subject Reference Image (required): URL of the subject reference image to use for consistent subject appearance.
  • Prompt Optimizer (optional): Whether to use the model's prompt optimizer.

Output and limits

  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to, default options: $0.80 / run