How to Use MiniMax Image-01 Subject Reference in ChatGPT
MiniMax Image-01 Subject Reference creates new scenes guided by a supplied human face. Unlike MiniMax Image-01 text-to-image generation, it uses a portrait to help keep character appearance consistent.
Prompts to try with MiniMax Image-01 Subject Reference in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use MiniMax Image-01 Subject Reference with my attached portrait to create a square editorial portrait. Show the person beside a large window, with soft morning light, a relaxed expression, natural skin texture, and a plain background.
Use MiniMax Image-01 Subject Reference with the attached face reference to create a widescreen video thumbnail concept. Place the person on the left with a curious expression, use a simple workshop background, and leave the right side clear for a title I will add later.
Use MiniMax Image-01 Subject Reference with this portrait to create a tall fashion concept. Show the person in a navy wool coat on a rainy city sidewalk, with visible fabric texture and soft reflections on the pavement.
Use MiniMax Image-01 Subject Reference with the attached character portrait to make three separate storyboard stills: entering a library, reading beside a window, and leaving at dusk. Use widescreen framing and describe the same wardrobe in each prompt.
Use MiniMax Image-01 Subject Reference with my attached portrait to compare a warm indoor portrait with a cool outdoor portrait. Make both square, keep the same head-and-shoulders framing, and turn off automatic prompt optimization for this comparison.
How to set up MiniMax Image-01 Subject Reference in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run MiniMax Image-01 Subject Reference
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/minimax/image-01/subject-reference", "input": { "prompt": "A beautiful woman with a crown on her head.", "image_url": "https://v3.fal.media/files/koala/hQwSnkWm8FDjou5SwLNuX_c223cf93-0036-4b18-bbea-bf6d0da7f210.png" } }'
Then paste one of the prompts above: ChatGPT finds MiniMax Image-01 Subject Reference on Spiral, shows the price and runs it.
MiniMax Image-01 Subject Reference providers and prices
Spiral runs MiniMax Image-01 Subject Reference through fal. Open a card for today's price, with every fee included.
Settings you can ask for
MiniMax Image-01 Subject Reference works from your prompt and image URL. Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Aspect ratio | 1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, or 21:9 | 1:1 | Aspect ratio of the generated image |
| Number of images | 1 to 9 | 1 | Number of images to generate (1-9) |
| Prompt optimizer | on or off | off | Whether to enable automatic prompt optimization |
Every API field of Minimax Image Subject Reference is on its tool page: open its card above.
What can you do with MiniMax Image-01 Subject Reference in ChatGPT?
Explore new scenes around a supplied portrait with MiniMax Image-01 Subject Reference. Turn a short creative brief into specific directions for framing, expression, setting, and light.
Portrait concepts
Use a human face reference to explore studio lighting, outdoor settings, and different portrait compositions.
Character storyboard stills
Generate separate scenes guided by one character portrait, then arrange the images into a storyboard for review.
Campaign image drafts
Build campaign concepts around one reference face, changing the setting and mood for each proposed image.
Video thumbnail concepts
Use a presenter portrait to draft expressive widescreen images. Leave room beside the presenter for separately added titles.
Website portrait assets
Create portrait-based images for a website draft, with framing and background space chosen for the page layout.
Wardrobe mood boards
Use one human face reference to explore clothing descriptions, fabric textures, and locations for a proposed shoot.
Training scenario illustrations
Illustrate a recurring fictional presenter in workplace situations, using the same portrait as the reference for each scene.
More on MiniMax Image-01 Subject Reference and ChatGPT
Overview
MiniMax Image-01 Subject Reference in other agents
Questions about MiniMax Image-01 Subject Reference in ChatGPT
Can ChatGPT use MiniMax Image-01 Subject Reference?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run MiniMax Image-01 Subject Reference like any built-in tool.
How much does MiniMax Image-01 Subject Reference cost in ChatGPT?
$0.013 per image. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.
Do I need a fal account to use MiniMax Image-01 Subject Reference in ChatGPT?
No. Spiral runs MiniMax Image-01 Subject Reference on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up MiniMax Image-01 Subject Reference in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while MiniMax Image-01 Subject Reference runs?
MiniMax Image-01 Subject Reference runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.
How does subject reference differ from text-to-image generation?
MiniMax Image-01 Subject Reference uses a supplied human face to guide character appearance. Text-to-image generation starts with a written description alone.
Can I supply two people as separate references?
No. MiniMax Image-01 Subject Reference supports one human face reference, so it is a poor fit when you need separate reference identities for two people in one scene.
How long can the prompt be?
The limit is 1,500 characters. Use that space to describe the scene, action, framing, lighting, and visual style.
What image dimensions should I expect?
Documented outputs include 1024×1024 for square images, 1280×720 for widescreen images, 720×1280 for tall images, and 1344×576 for ultrawide images. Choose the intended composition before generating rather than relying on a later crop.
Is MiniMax Image-01 suited to realistic portraits?
Yes. MiniMax highlights realistic skin textures and natural expressions as strengths, making portrait concepts a sensible use.
Start using MiniMax Image-01 Subject Reference in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


