[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [FLUX.1 Dev LoRA](https://spiral.ai/integrations/chatgpt/flux-1-dev-lora)

# How to Use FLUX.1 Dev LoRA in ChatGPT

FLUX.1 Dev LoRA generates product concepts, portraits, and illustrations with trained styles or subjects. It adds custom LoRA adaptations to FLUX.1 Dev, making it useful when a written style description alone is too broad.

|  |  |
| --- | --- |
| Model | FLUX.1 Dev LoRA |
| Available through | fal |
| Category | Image |
| Price | $0.0455 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 Dev LoRA in ChatGPT

- Use FLUX.1 Dev LoRA to make a 1280 by 720 pixel editorial illustration of a small bookstore at dusk. Apply my selected illustration LoRA with its documented trigger phrase, warm window light, and a cyclist in the foreground.
- Use FLUX.1 Dev LoRA with my selected product LoRA to show the trained item on a stone countertop beside a window. Use soft morning light, an eye-level view, and a quiet background.
- Use FLUX.1 Dev LoRA with my selected portrait LoRA to create an environmental portrait in a greenhouse. Frame the subject from the waist up, with soft side lighting and plants behind them.
- Use FLUX.1 Dev LoRA to compare my selected style LoRA at strengths 0.5, 1.0, and 1.5. Keep the scene, random seed, and other settings fixed: a red fishing boat in a misty harbor.
- Use FLUX.1 Dev LoRA with my selected character LoRA to illustrate the trained character reading a map beside a campfire. Include the documented trigger phrase and describe a low camera angle, warm firelight, and distant mountains.

## How to set up FLUX.1 Dev LoRA in ChatGPT

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

### Use the ChatGPT connector

1. **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.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **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

1. **Send ChatGPT 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 Dev LoRA**: 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-lora",
    "input": {
      "prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture…"
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds FLUX.1 Dev LoRA on Spiral, shows the price and runs it.

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

## FLUX.1 Dev LoRA tools and prices

- [FLUX.1 \[dev\] with LoRAs · Text to Image](https://spiral.ai/tools/fal/fal-ai/flux-lora) (fal): $0.0455 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. |
| loras |  | [] | The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image. |
| guidance_scale | 0 to 35 | 3.5 | 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. This is always set to 1 for streaming output. |

## What can you do with FLUX.1 Dev LoRA in ChatGPT?

Turn a written idea into portraits, product concepts, or illustrated scenes with a chosen trained style. A chat app can help you refine the composition and compare how strongly the LoRA affects the result.

### Editorial illustration series

Generate illustrations for related articles with the same trained style. Give each image a distinct subject and composition while retaining the visual treatment.

### Product campaign concepts

Use a product LoRA to explore a trained item in seasonal settings or different lighting. Review the generated product details before selecting images.

### Brand campaign imagery

Apply a brand style LoRA to campaign scenes, social images, and editorial artwork. Specify the palette, medium, and composition in each brief.

### Character scene exploration

Use a character LoRA to explore poses, costumes, and settings for a story. Check each result against the intended character design.

### Personalized portrait concepts

Generate portrait concepts with a trained person LoRA. Compare studio lighting, environmental settings, and framing before choosing a direction.

### Game environment concepts

Explore locations such as workshops, harbors, and forest settlements with a chosen style LoRA. Use the results as visual references during preproduction.

### Storyboard illustrations

Generate individual scene illustrations for a storyboard using a trained visual treatment. Specify the camera position and action separately for each shot.

## Overview

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

## FLUX.1 Dev LoRA in other agents

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

## More ChatGPT guides

- [FLUX.1 Dev](https://spiral.ai/integrations/chatgpt/flux-1-dev)
- [FLUX.1 Kontext Max](https://spiral.ai/integrations/chatgpt/flux-1-kontext-max)
- [FLUX Kontext LoRA Text to Image](https://spiral.ai/integrations/chatgpt/flux-kontext-lora-text-to-image)
- [FLUX.1 Kontext Max Multi](https://spiral.ai/integrations/chatgpt/flux-1-kontext-max-multi)
- [FLUX 3 Klein Text to Image](https://spiral.ai/integrations/chatgpt/flux-3-klein-text-to-image)
- [FLUX.1 Kontext Max Text to Image](https://spiral.ai/integrations/chatgpt/flux-1-kontext-max-text-to-image)

## Questions about FLUX.1 Dev LoRA in ChatGPT

**Can ChatGPT use FLUX.1 Dev LoRA?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run FLUX.1 Dev LoRA like any built-in tool.

**How much does FLUX.1 Dev LoRA cost in ChatGPT?**

$0.0455 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 ChatGPT plan is separate.

**Do I need a fal account to use FLUX.1 Dev LoRA in ChatGPT?**

No. Spiral runs FLUX.1 Dev LoRA 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 Dev LoRA in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while FLUX.1 Dev LoRA runs?**

FLUX.1 Dev LoRA runs in the background. ChatGPT starts the run, checks on it and gives you the image when it's ready.

**What is FLUX.1 Dev LoRA useful for?**

Use it for illustrations, product concepts, portraits, and campaign imagery that need a trained subject or visual treatment. A suitable LoRA gives you a more specific starting point than a style description alone.

**How should I write a FLUX.1 Dev LoRA prompt?**

Describe the subject, setting, composition, lighting, and medium. If your LoRA specifies a trigger phrase, include that phrase alongside the scene description.

**How strong should the LoRA effect be?**

The endpoint documentation suggests strengths typically between 0.5 and 1.5. Start at 1.0 and compare nearby values while keeping the scene and other settings fixed.

**Can FLUX.1 Dev LoRA make widescreen images?**

Yes. The documentation includes custom dimensions of 1280 by 720 pixels, a 16:9 image. Describe the composition for that shape, including where the subject and any open space should sit.

**What should I check before using an image?**

Check whether the image actually follows the brief. Black Forest Labs warns that FLUX.1 Dev can miss prompt requirements and is not intended to provide factual information, so review any image meant to explain a real object or process.

