AllImageAI

MiniMax Image-01 AI Image Generator

Low-cost photoreal generation with a dedicated one-face consistency operation.

Developed by MiniMaxActiveVerified August 25, 2026

Model Version

Mode

Reference Images0/1

Preview mode: placeholder output, no credits charged

Output

MiniMax Image-01

Low-cost photoreal generation with a dedicated one-face consistency operation.

FastUp to 1KRefs ×11:116:99:164:3

Try one of these prompts

Developer
MiniMax
Model
MiniMax Image-01
Status
Active
Max Output
1K
Input
Text + Images
Released
February 28, 2025
Last Verified
August 25, 2026

What Is MiniMax Image-01?

MiniMax Image-01 is a low-cost model for photoreal people, cinematic environments and fast batches. Its separate subject-reference operation accepts one human face and carries that identity into a new scene.

What Is MiniMax Image-01 Best For?

  • Inexpensive photo batches
  • Single-person consistency
  • Cinematic scenes
  • Wide and vertical social formats

How to Use MiniMax Image-01

  1. Write a detailed prompt or upload one face.
  2. Use a clear reference with even light.
  3. Generate several low-cost variants.
  4. Check identity and small details before export.

MiniMax Image-01 Settings Explained

Prompt Expansion

The documented prompt optimiser enriches short descriptions; disable it for literal directions.

Reference Image

Use one clear, front-facing human face for the subject-reference operation.

The panel above shows only the parameters MiniMax Image-01 actually supports. Switch versions and unsupported controls disappear rather than sitting there doing nothing.

MiniMax Image-01 Prompt Examples

Subject reference

Preserve this person’s facial identity; photograph them walking through a rainy neon street, natural expression, cinematic night light

Environment

Remote coastal observatory at blue hour, powerful ocean wind, warm interior lights, cinematic landscape photography

MiniMax Image-01 Test Results

Testing in progress

Every model runs the same eight-category prompt set — portrait, product, poster text, anime character, interior, multi-reference, image editing and character consistency — recording generation time, success rate, text accuracy and identity retention. That run has not finished for MiniMax Image-01, so this page shows no scores. We do not publish numbers we have not measured.

MiniMax Image-01 Limitations

  • The reference route supports one human face only
  • 1K output
  • Prompt length is capped upstream

MiniMax Image-01 Pricing and Credits

Credits scale with resolution and image count. The Generate button always shows what this run costs.

1K

1 credits / image

Failed generations cost 0 credits.

Commercial Use and Image Rights

Commercial use is governed by MiniMax terms and the selected service terms.

  • Model used: MiniMax Image-01
  • Model developer: MiniMax
  • The inference route is managed internally and may change without changing the selected model
  • Uploads are sent only to the configured inference service needed to complete the generation
  • You can delete any generation from your history at any time

Frequently Asked Questions

Can the reference be a product or animal?+

The documented subject-reference route currently supports one human face.

How many images can I generate?+

The upstream operation supports more, but this interface caps each run at four for predictable billing.

Model Updates and Changelog

  • 2026-08-25 —— Added exact text-to-image and subject-reference routes.