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
- Write a detailed prompt or upload one face.
- Use a clear reference with even light.
- Generate several low-cost variants.
- 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 We do not publish numbers we have not measured.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.
Release History and Sources
February 15, 2025 · API access opened
The model release log records February 15, 2025. A separate news announcement is dated February 28. This event is API availability, not an assertion of a single first-release date.
Explore this event on the image model timeline →
Related Models and Tools
AI Image Generator
Create an image, try a new look or transform a photo. Start with the result you want.
Image to Image
Start from an image. You decide how much of it survives.
Consistent Character
Use a character reference to create new poses, scenes and outfits.
FLUX.2 Max
Black Forest Labs
The highest-fidelity FLUX.2 tier for final-publish generation and demanding prompt adherence.
FLUX.2 Flex
Black Forest Labs
FLUX.2 with explicit guidance and step controls for typography-heavy final renders.
FLUX.2 Flash
Black Forest Labs
A low-cost FLUX.2 route for rapid generation and exact multi-reference edits.
FLUX.2 Turbo
Black Forest Labs
A fast FLUX.2 draft model with prompt expansion and unusually low megapixel cost.