[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [FLUX.1 SRPO](https://spiral.ai/integrations/gemini-cli/flux-1-srpo)

# How to Use FLUX.1 SRPO in Gemini CLI

FLUX.1 SRPO creates images from text, with a focus on photographic realism, lighting, and fine detail. Compared with FLUX.1 Dev, Tencent's fine-tuning targets more realistic textures and stronger visual composition.

|  |  |
| --- | --- |
| Model | FLUX.1 SRPO |
| Available through | fal |
| Category | Image |
| Price | $0.0325 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with FLUX.1 SRPO in Gemini CLI

- Read the outdoor journal page in this project and use FLUX.1 SRPO to create a square editorial portrait of a fictional mountain guide, with worn clothing, visible fabric texture, and crisp side lighting. Save it with the page assets.
- Use FLUX.1 SRPO to create a 1024 × 1024 image for the nature article in this project: a butterfly on a white flower, soft morning light, and a blurred green background. Use 50 steps and guidance 3.5.
- Inspect the film club page's visual brief and use FLUX.1 SRPO to create a black-and-white scene of a lone traveler at a station, with deep shadows and fine film grain. Keep signs outside the composition.
- Read the book description in this project and use FLUX.1 SRPO to create a square painted cover concept with a river, wildflowers, and a solitary figure. Leave the title to the page's existing typography.
- Use FLUX.1 SRPO to create a square nature image for this project's newsletter preview: a fox resting beside a weathered log in soft daylight. Save the image and draft descriptive alt text after inspecting it.

## How to set up FLUX.1 SRPO 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.1 SRPO**: 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/flux-1/srpo",
    "input": {
      "prompt": "Mountain guide, sturdy build, wilderness wisdom, alert gaze, technical outdoor gear with rope coils, snow-capped peaks background, crisp mountain lighting,…"
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds FLUX.1 SRPO on Spiral, shows the price and runs it.

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

## FLUX.1 SRPO tools and prices

- [FLUX.1 SRPO \[dev\] · Text to Image](https://spiral.ai/tools/fal/fal-ai/flux-1/srpo) (fal): $0.0325 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size |  | landscape_4_3 | The size of the generated image. |
| num_inference_steps | 1 to 50 | 28 | The number of inference steps to perform. |
| seed |  | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| guidance_scale | 1 to 20 | 4.5 | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. |
| num_images | 1 to 4 | 1 | The number of images to generate. |
| output_format | jpeg, png | jpeg | The format of the generated image. |

## What can you do with FLUX.1 SRPO in Gemini CLI?

Create photographic and painted assets from the visual brief in your project. A coding agent can inspect the page layout, describe an appropriate composition, and save reviewed images beside the site's other assets.

### Editorial portrait concepts

Explore a fictional subject's clothing, surroundings, and lighting before planning a portrait session. Describe visible details such as weathered fabric and light across the face.

### Nature article illustrations

Create illustrative flower, insect, or animal scenes for articles. Use a close viewpoint and a clearly described background to plan the composition.

### Film lighting studies

Explore a scene's mood with black-and-white imagery, deep shadows, and film grain. Use the results as visual references for a shot discussion.

### Painted cover concepts

Develop painting concepts for a book or music cover. Describe the medium, subject placement, natural details, and mood, then add the final typography separately.

### Website image concepts

Generate photographic scene ideas for an outdoor, arts, or nature website. Plan open space around the subject for the page's actual text.

### Newsletter illustrations

Turn an editorial brief into a proposed portrait, nature scene, or painted illustration. Review the result against the brief before placing it in the newsletter.

## Overview

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

## FLUX.1 SRPO in other agents

- [Amp](https://spiral.ai/integrations/amp/flux-1-srpo)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/flux-1-srpo)
- [Claude](https://spiral.ai/integrations/claude-desktop/flux-1-srpo)
- [Claude Code](https://spiral.ai/integrations/claude-code/flux-1-srpo)
- [Cline](https://spiral.ai/integrations/cline/flux-1-srpo)
- [Codex](https://spiral.ai/integrations/codex/flux-1-srpo)
- [Cursor](https://spiral.ai/integrations/cursor/flux-1-srpo)
- [Devin](https://spiral.ai/integrations/devin/flux-1-srpo)
- [dots](https://spiral.ai/integrations/dots/flux-1-srpo)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/flux-1-srpo)
- [Gemini](https://spiral.ai/integrations/gemini/flux-1-srpo)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/flux-1-srpo)
- [goose](https://spiral.ai/integrations/goose/flux-1-srpo)
- [Grok](https://spiral.ai/integrations/grok/flux-1-srpo)
- [Grok Build](https://spiral.ai/integrations/grok-build/flux-1-srpo)
- [Hermes](https://spiral.ai/integrations/hermes/flux-1-srpo)
- [Instinct](https://spiral.ai/integrations/instinct/flux-1-srpo)
- [Manus](https://spiral.ai/integrations/manus/flux-1-srpo)
- [Muse](https://spiral.ai/integrations/muse/flux-1-srpo)
- [Muse Code](https://spiral.ai/integrations/muse-code/flux-1-srpo)
- [n8n](https://spiral.ai/integrations/n8n/flux-1-srpo)
- [Notion](https://spiral.ai/integrations/notion/flux-1-srpo)
- [OpenClaw](https://spiral.ai/integrations/openclaw/flux-1-srpo)
- [opencode](https://spiral.ai/integrations/opencode/flux-1-srpo)
- [Perplexity](https://spiral.ai/integrations/perplexity/flux-1-srpo)
- [Raycast](https://spiral.ai/integrations/raycast/flux-1-srpo)
- [VS Code](https://spiral.ai/integrations/vscode/flux-1-srpo)
- [Windsurf](https://spiral.ai/integrations/windsurf/flux-1-srpo)
- [Zapier](https://spiral.ai/integrations/zapier/flux-1-srpo)

## More Gemini CLI guides

- [FLUX.1 Redux \[dev\]](https://spiral.ai/integrations/gemini-cli/flux-1-redux-dev)
- [FLUX.1 SRPO Dev](https://spiral.ai/integrations/gemini-cli/flux-1-srpo-dev)
- [FLUX.1 Krea Redux](https://spiral.ai/integrations/gemini-cli/flux-1-krea-redux)
- [FLUX.1 Schnell](https://spiral.ai/integrations/gemini-cli/flux-1-schnell)
- [FLUX.1 Krea LoRA](https://spiral.ai/integrations/gemini-cli/flux-1-krea-lora)
- [FLUX.1 Schnell Redux](https://spiral.ai/integrations/gemini-cli/flux-1-schnell-redux)

## Questions about FLUX.1 SRPO in Gemini CLI

**Can Gemini CLI use FLUX.1 SRPO?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run FLUX.1 SRPO like any built-in tool.

**How much does FLUX.1 SRPO cost in Gemini CLI?**

$0.0325 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. 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 Gemini CLI plan is separate.

**Do I need a fal account to use FLUX.1 SRPO in Gemini CLI?**

No. Spiral runs FLUX.1 SRPO 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.1 SRPO in Gemini CLI?**

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

**Does Gemini CLI wait while FLUX.1 SRPO runs?**

FLUX.1 SRPO runs in the background. Gemini CLI starts the run, checks on it and gives you the image when it's ready.

**How does FLUX.1 SRPO differ from FLUX.1 Dev?**

Tencent fine-tuned FLUX.1 Dev to improve photographic realism, detail, and aesthetics. Its paper reports stronger realism and detail complexity in the illustrated comparisons.

**What should I use FLUX.1 SRPO for?**

Consider it for photographic concepts where texture and lighting matter: outdoor portraits, nature close-ups, and editorial imagery. These recommendations follow the subjects and visual treatments in the published examples.

**Can FLUX.1 SRPO make paintings?**

Yes. Tencent's example prompt requests a Pre-Raphaelite painting with flowers, natural detail, and a river scene.

**What resolution and settings should I try first?**

For a documented comparison point, try 1024 × 1024 pixels, 50 steps, and guidance 3.5. Those are Tencent's reference settings, not a claim about the maximum output size.

**What weaknesses should I watch for?**

High guidance can introduce overly smooth surfaces and artifacts, according to the researchers. Also inspect whether the scene matches your instructions: imperfect prompt matching is a documented limitation of the FLUX.1 Dev base model.

