Available now

MiniMax Image-01: text to image

By MiniMax

MiniMax Image-01 creates up to nine images per run from a text prompt, and keeps one character's look across new scenes from a single reference photo.

Model ID
Maker
MiniMax

Input

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

Text prompt for image generation (max 1500 characters)

Example prompt. Edit it or write your own.

Number of images to generate (1-9)

Additional settings

Whether to enable automatic prompt optimization

Estimated total$0.02

You sign up first. Your settings are kept.

About this model

Overview

MiniMax Image-01 takes a prompt of up to 1500 characters and renders in eight shapes from 21:9 to 9:16. A prompt optimizer can rework your wording before it renders.

The subject reference mode takes one photo of a person or character and places them in the scene you describe, so the same face and look carry over from image to image.

What you can build

  • A character shown in many settings for a story or campaign
  • Large sets of options from one prompt
  • Wide 21:9 scenes for headers and covers
  • Consistent mascot or avatar images

Prompting tips

  • For the reference mode, use a clear, well-lit photo where the face is fully visible.
  • Describe only the new scene and outfit in the prompt; the face comes from the photo.
  • Turn the prompt optimizer on for short ideas and off when the wording must stay exact.

What to check

Compare facial features and clothing against the reference; inspect hands and lettering.

Inputs

  • Prompt (required): Text prompt for image generation (max 1500 characters).
  • Aspect Ratio (optional): Aspect ratio of the generated image. Options: 1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, 21:9.
  • Number of Images (optional): Number of images to generate (1-9).
  • Prompt Optimizer (optional): Whether to enable automatic prompt optimization.

Output and limits

  • Aspect ratios: 1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, 21:9.
  • Up to 9 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1 image: $0.02 / image