[Integrations](https://spiral.ai/integrations) › [Devin](https://spiral.ai/integrations/devin) › [MiniMax Image-01 Subject Reference](https://spiral.ai/integrations/devin/minimax-image-01-subject-reference)

# How to Use MiniMax Image-01 Subject Reference in Devin

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.

|  |  |
| --- | --- |
| Model | MiniMax Image-01 Subject Reference |
| Available through | fal |
| Category | Image |
| Price | $0.013 per image. Billed on `num_images`, default 1. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with MiniMax Image-01 Subject Reference in Devin

- Use MiniMax Image-01 Subject Reference with the portrait in assets to create a widescreen homepage image. Read the homepage copy first, place the person on the right in a bright workshop, and leave uncluttered space on the left for the existing heading.
- Use MiniMax Image-01 Subject Reference with the project's character portrait to create a square onboarding illustration. Show the person seated at a tidy desk, smiling naturally, with soft window light and a simple background that fits our existing palette.
- Read the tutorial in this project and use MiniMax Image-01 Subject Reference with the supplied presenter portrait to create three separate widescreen scene images. Give each scene one clear action, keep the lighting description consistent, and keep each generation prompt under 1,500 characters.
- Use MiniMax Image-01 Subject Reference with assets/presenter.png to create a tall portrait concept for our mobile welcome screen. Frame the person from the waist up against a quiet outdoor background, with clear space above the head for the interface copy.
- Use MiniMax Image-01 Subject Reference with the project's portrait to compare two square profile-image concepts: soft daylight and warm studio light. Disable prompt optimization, keep the pose and background description fixed, and show the results side by side for review.

## How to set up MiniMax Image-01 Subject Reference in Devin

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add a custom MCP**: Open Customize › MCPs. Click + and choose New MCP. Fill in:

2. **Sign in to Spiral and approve**: In Customize › MCPs, open Spiral and choose Connect. Spiral opens: sign in, pick the organization and click Authorize. No API key.

3. **Check it**: On Spiral's configuration page, click Test tools. Devin lists Spiral's tools.

### Use the Spiral skill

1. **Send Devin this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run MiniMax Image-01 Subject Reference**: One request; the result comes back by polling or a webhook.

```bash
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: Devin finds MiniMax Image-01 Subject Reference on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/devin

## MiniMax Image-01 Subject Reference tools and prices

- [Minimax Image Subject Reference](https://spiral.ai/tools/fal/fal-ai/minimax/image-01/subject-reference) (fal): $0.013 per image. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| aspect_ratio | 1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, 21:9 | 1:1 | Aspect ratio of the generated image |
| num_images | 1 to 9 | 1 | Number of images to generate (1-9) |
| prompt_optimizer |  | false | Whether to enable automatic prompt optimization |

## What can you do with MiniMax Image-01 Subject Reference in Devin?

Create portrait-based assets that fit the project's actual layouts with MiniMax Image-01 Subject Reference. Use project copy and image slots to write scene briefs, then review the generated images in context.

### 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.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Devin guides](https://spiral.ai/integrations/devin)

## MiniMax Image-01 Subject Reference in other agents

- [Amp](https://spiral.ai/integrations/amp/minimax-image-01-subject-reference)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/minimax-image-01-subject-reference)
- [Claude](https://spiral.ai/integrations/claude-desktop/minimax-image-01-subject-reference)
- [Claude Code](https://spiral.ai/integrations/claude-code/minimax-image-01-subject-reference)
- [Cline](https://spiral.ai/integrations/cline/minimax-image-01-subject-reference)
- [Codex](https://spiral.ai/integrations/codex/minimax-image-01-subject-reference)
- [Cursor](https://spiral.ai/integrations/cursor/minimax-image-01-subject-reference)
- [dots](https://spiral.ai/integrations/dots/minimax-image-01-subject-reference)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/minimax-image-01-subject-reference)
- [Gemini](https://spiral.ai/integrations/gemini/minimax-image-01-subject-reference)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/minimax-image-01-subject-reference)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/minimax-image-01-subject-reference)
- [goose](https://spiral.ai/integrations/goose/minimax-image-01-subject-reference)
- [Grok](https://spiral.ai/integrations/grok/minimax-image-01-subject-reference)
- [Grok Build](https://spiral.ai/integrations/grok-build/minimax-image-01-subject-reference)
- [Hermes](https://spiral.ai/integrations/hermes/minimax-image-01-subject-reference)
- [Instinct](https://spiral.ai/integrations/instinct/minimax-image-01-subject-reference)
- [Manus](https://spiral.ai/integrations/manus/minimax-image-01-subject-reference)
- [Muse](https://spiral.ai/integrations/muse/minimax-image-01-subject-reference)
- [Muse Code](https://spiral.ai/integrations/muse-code/minimax-image-01-subject-reference)
- [n8n](https://spiral.ai/integrations/n8n/minimax-image-01-subject-reference)
- [Notion](https://spiral.ai/integrations/notion/minimax-image-01-subject-reference)
- [OpenClaw](https://spiral.ai/integrations/openclaw/minimax-image-01-subject-reference)
- [opencode](https://spiral.ai/integrations/opencode/minimax-image-01-subject-reference)
- [Perplexity](https://spiral.ai/integrations/perplexity/minimax-image-01-subject-reference)
- [Raycast](https://spiral.ai/integrations/raycast/minimax-image-01-subject-reference)
- [VS Code](https://spiral.ai/integrations/vscode/minimax-image-01-subject-reference)
- [Windsurf](https://spiral.ai/integrations/windsurf/minimax-image-01-subject-reference)
- [Zapier](https://spiral.ai/integrations/zapier/minimax-image-01-subject-reference)

## More Devin guides

- [MiniMax Image-01](https://spiral.ai/integrations/devin/minimax-image-01)
- [Muse Image Edit](https://spiral.ai/integrations/devin/muse-image-edit)
- [MiniMax H3 Image Text to Image](https://spiral.ai/integrations/devin/minimax-h3-image-text-to-image)
- [Muse Image Text to Image](https://spiral.ai/integrations/devin/muse-image-text-to-image)
- [MiniMax H3 Image Highspeed Text to Image](https://spiral.ai/integrations/devin/minimax-h3-image-highspeed-text-to-image)
- [NAFNet Deblur](https://spiral.ai/integrations/devin/nafnet-deblur)

## Questions about MiniMax Image-01 Subject Reference in Devin

**Can Devin use MiniMax Image-01 Subject Reference?**

Yes. Add Spiral to Devin as an MCP server, and Devin can find and run MiniMax Image-01 Subject Reference like any built-in tool.

**How much does MiniMax Image-01 Subject Reference cost in Devin?**

$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 Devin plan is separate.

**Do I need a fal account to use MiniMax Image-01 Subject Reference in Devin?**

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 Devin?**

About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.

**Does Devin wait while MiniMax Image-01 Subject Reference runs?**

MiniMax Image-01 Subject Reference runs in the background. Devin 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.

