MiniMaxFastHigh

MiniMax Image-01

MiniMax's first image generation model with character reference support: provide a single face photo via subject_reference and generate consistent images of that person across prompts, styles, and aspect ratios — up to 9 images per request.

23 credits

per image — 23 credits × number_of_images (1-9)

Character consistency from a single face photo via subject_reference

Batch generation of 1-9 images per request

8 aspect ratios from square 1:1 to cinematic 21:9

Built-in prompt optimizer (enabled by default)

Low, predictable per-image pricing

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/image-01",
  "input": {
    "prompt": "A close-up portrait of a leopard with distinctive spotted pattern and intense eyes",
    "aspect_ratio": "3:4",
    "number_of_images": 1,
    "prompt_optimizer": true
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	-	Text prompt for generation
`subject_reference`	string	No	-	An optional character reference image (human face) to use as the subject in the generated image(s)
`aspect_ratio`	string	No	1:1	Image aspect ratio 1:116:94:33:22:33:49:1621:9
`number_of_images`	integer	No	1	Number of images to generate (1-9). Each image is billed separately
`prompt_optimizer`	boolean	No	true	Use prompt optimizer

How to Provide File Input

There are 3 ways to provide files for the subject_reference parameter:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=minimax/image-01" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:subject_reference=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "minimax/image-01",
  "input": {
    "prompt": "your prompt here",
    "subject_reference": "https://example.com/image.jpg"
  }
}

See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Detailed Portrait

Text-to-image portrait with the default prompt optimizer

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/image-01",
  "input": {
    "prompt": "A close-up portrait of a leopard with distinctive spotted pattern and intense eyes",
    "aspect_ratio": "3:4",
    "number_of_images": 1,
    "prompt_optimizer": true
  }
}'

Consistent Character from a Face Photo

subject_reference keeps the same person across generated variations

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/image-01",
  "input": {
    "prompt": "A professional studio portrait, soft lighting, navy suit, confident smile",
    "subject_reference": "https://example.com/face.jpg",
    "aspect_ratio": "3:4",
    "number_of_images": 4
  }
}'

Tips & Best Practices

1Total cost is 30 credits × number_of_images — a 9-image batch costs 270 credits, so size batches deliberately

2For best character consistency, use a clear, front-facing face photo as subject_reference

3Keep prompt_optimizer on unless you need literal prompt adherence — it improves variety and quality

4Generate several images in one request and pick the best; per-image cost is low

5Only use photos of real people as subject_reference with the person's explicit consent

Use Cases

Consistent character portraits across different scenes and outfits

Personalized avatar and profile image generation

Storyboard or webtoon frames featuring the same character

Batch exploration of prompt variations at low cost

General text-to-image generation without a reference

Model Info

ProviderMiniMax

Version-

CategoryImage Generation

Price23 credits

API Endpoint

POST /v1/predictions

Try in Console

Related Models

Salesforce • 1 credits

Change Haircut

Black Forest Labs • 93 credits

Back to Docs