[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [FLUX 3 Image](https://spiral.ai/integrations/gemini-cli/flux-3-image)

# How to Use FLUX 3 Image in Gemini CLI

FLUX 3 Image turns written descriptions into photographs, illustrations, and posters with text. Native 2K and 4K generation and prompt-based layout control make it useful for detailed compositions.

|  |  |
| --- | --- |
| Model | FLUX 3 Image |
| Available through | fal |
| Category | Image |
| Price | `resolution`: otherwise $0.0624, 1k (default) $0.1248, 1.5k $0.1872, 2k $0.312, 4k $1.0608 per megapixel. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with FLUX 3 Image in Gemini CLI

- Read the homepage copy and layout in this project. Use FLUX 3 Image to create a 16:9 header illustration at 2K, with the main subject on the right and a quiet left third for the HTML headline. Match the subject to the product's actual purpose.
- Read the latest article in this project's content directory. Use FLUX 3 Image to create a square editorial illustration at 1K that explains its central idea through one concrete scene. Specify the medium, palette, lighting, and viewpoint.
- Read the event details in this project. Use FLUX 3 Image to create a 2:3 poster at 2K with the exact event title in quotation marks, a clear illustration, and separately positioned date and venue lines. Check the rendered lettering against the source copy.
- Inspect this project's empty-state copy. Use FLUX 3 Image to create a square 1K illustration of a single character performing the relevant action, with thick linework, a limited palette, and a plain background.
- Read the book description and title in this project. Use FLUX 3 Image to create a 2:3 cover concept at 2K. Write a scene caption and append an element table with generous bounding boxes for the illustration and quoted title.

## How to set up FLUX 3 Image in Gemini CLI

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

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI 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 FLUX 3 Image**: 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": "blackforestlabs/flux-3/text-to-image",
    "input": {
      "prompt": "A red fox leaping over a stream in a pine forest, low-angle wildlife photograph."
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds FLUX 3 Image on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## FLUX 3 Image tools and prices

- [FLUX 3 Text to Image](https://spiral.ai/tools/fal/blackforestlabs/flux-3/text-to-image) (fal): $0.0624 per megapixel of the output image, as fal measures it.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| aspect_ratio | auto, 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2 | auto | Output aspect ratio. Auto uses the first reference image when editing. |
| resolution | 768sq, 1k, 1.5k, 2k, 4k | 1k | Output resolution tier. 4k can take several minutes. |
| enable_prompt_expansion |  | false | Expand the prompt while preserving its intent and reference roles. |
| safety_tolerance | 0 to 4 | 2 | Safety tolerance, from 0 (strictest) to 4. |
| output_format | jpeg, png | jpeg | The format of the generated image. |
| version |  | latest | The model version. |

## What can you do with FLUX 3 Image in Gemini CLI?

Create artwork that fits the page you are building. A coding agent can turn project copy and layout requirements into image briefs with deliberate framing and space for interface text.

### Article illustrations

Turn an article's central idea into an illustration with a named medium, a clear subject, and room for the page's headline.

### Event posters

Compose an illustrated scene with a quoted event title and supporting copy. Give each text block its own position and proofread the result.

### Website header artwork

Create a wide scene whose subject sits beside a quiet area reserved for HTML copy. Describe what fills the full width.

### Photographic scene concepts

Explore a scene through camera angle, lens language, light direction, and materials before planning a shoot.

### Book cover concepts

Develop portrait compositions with a central illustration and a short quoted title. Specify the title's placement, weight, and color.

### Bilingual artwork

Create poster concepts that combine English and Japanese lettering. Supply the exact wording and describe each script's position and reading direction.

### Character design sheets

Explore an illustrated character's appearance through thick linework, a limited palette, and a clearly described pose.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## FLUX 3 Image in other agents

- [Amp](https://spiral.ai/integrations/amp/flux-3-image)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/flux-3-image)
- [Claude](https://spiral.ai/integrations/claude-desktop/flux-3-image)
- [Claude Code](https://spiral.ai/integrations/claude-code/flux-3-image)
- [Cline](https://spiral.ai/integrations/cline/flux-3-image)
- [Codex](https://spiral.ai/integrations/codex/flux-3-image)
- [Cursor](https://spiral.ai/integrations/cursor/flux-3-image)
- [Devin](https://spiral.ai/integrations/devin/flux-3-image)
- [dots](https://spiral.ai/integrations/dots/flux-3-image)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/flux-3-image)
- [Gemini](https://spiral.ai/integrations/gemini/flux-3-image)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/flux-3-image)
- [goose](https://spiral.ai/integrations/goose/flux-3-image)
- [Grok](https://spiral.ai/integrations/grok/flux-3-image)
- [Grok Build](https://spiral.ai/integrations/grok-build/flux-3-image)
- [Hermes](https://spiral.ai/integrations/hermes/flux-3-image)
- [Instinct](https://spiral.ai/integrations/instinct/flux-3-image)
- [Manus](https://spiral.ai/integrations/manus/flux-3-image)
- [Muse](https://spiral.ai/integrations/muse/flux-3-image)
- [Muse Code](https://spiral.ai/integrations/muse-code/flux-3-image)
- [n8n](https://spiral.ai/integrations/n8n/flux-3-image)
- [Notion](https://spiral.ai/integrations/notion/flux-3-image)
- [OpenClaw](https://spiral.ai/integrations/openclaw/flux-3-image)
- [opencode](https://spiral.ai/integrations/opencode/flux-3-image)
- [Perplexity](https://spiral.ai/integrations/perplexity/flux-3-image)
- [Raycast](https://spiral.ai/integrations/raycast/flux-3-image)
- [VS Code](https://spiral.ai/integrations/vscode/flux-3-image)
- [Windsurf](https://spiral.ai/integrations/windsurf/flux-3-image)
- [Zapier](https://spiral.ai/integrations/zapier/flux-3-image)

## More Gemini CLI guides

- [FLUX 1.1 Pro Ultra](https://spiral.ai/integrations/gemini-cli/flux-1-1-pro-ultra)
- [FLUX 3 Image Edit](https://spiral.ai/integrations/gemini-cli/flux-3-image-edit)
- [FLUX 1.1 Pro](https://spiral.ai/integrations/gemini-cli/flux-1-1-pro)
- [FLUX 3 Klein Image Edit](https://spiral.ai/integrations/gemini-cli/flux-3-klein-image-edit)
- [FIBO Edit Restyle](https://spiral.ai/integrations/gemini-cli/fibo-edit-restyle)
- [FLUX 3 Klein Text to Image](https://spiral.ai/integrations/gemini-cli/flux-3-klein-text-to-image)

## Questions about FLUX 3 Image in Gemini CLI

**Can Gemini CLI use FLUX 3 Image?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run FLUX 3 Image like any built-in tool.

**How much does FLUX 3 Image cost in Gemini CLI?**

`resolution`: otherwise $0.0624, 1k (default) $0.1248, 1.5k $0.1872, 2k $0.312, 4k $1.0608 per megapixel. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

**Do I need a fal account to use FLUX 3 Image in Gemini CLI?**

No. Spiral runs FLUX 3 Image on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up FLUX 3 Image in Gemini CLI?**

About two minutes: add the server, then sign in, then check it.

**Does Gemini CLI wait while FLUX 3 Image runs?**

FLUX 3 Image runs in the background. Gemini CLI starts the run, checks on it and gives you the image when it's ready.

**What is FLUX 3 Image useful for?**

Use it for illustrated articles, photographic scenes, posters, and compositions that need deliberate placement. Describe the medium and layout along with the subject.

**Does FLUX 3 Image generate native 4K images?**

Yes. BFL documents native 2K and 4K generation and shows a 5456 × 3072 pixel example; 4K does not mean every image is 3840 × 2160.

**Can FLUX 3 Image put readable text in an image?**

Yes. Quote each exact string, then describe its placement and type treatment. Proofread the result, especially small print and long lines.

**Can FLUX 3 Image render Japanese text?**

Yes. BFL demonstrates Japanese text inside images using English prompts that quote the Japanese characters directly.

**How detailed should a FLUX 3 Image prompt be?**

Start with a sentence describing the finished image. Add detail when you need several subjects, a particular layout, or exact text; specify visible details instead of quality labels.

