[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [FLUX 3 Image Edit](https://spiral.ai/integrations/chatgpt/flux-3-image-edit)

# How to Use FLUX 3 Image Edit in ChatGPT

FLUX 3 Image Edit is for targeted photo changes and compositions built from up to ten references. Unlike FLUX 3 Text to Image, it starts from supplied images, so you can describe what to change and what to keep.

|  |  |
| --- | --- |
| Model | FLUX 3 Image Edit |
| 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 Edit in ChatGPT

- Use FLUX 3 Image Edit on this product photo. Change only the red lid to forest green, keeping the bottle shape, label, and background.
- Use FLUX 3 Image Edit with these two images. Image 1 supplies the kitchen; place the vase from image 2 on the counter beside the window.
- Use FLUX 3 Image Edit to preview the jacket from image 2 on the person in image 1. Preserve the person's pose and the surrounding scene.
- Use FLUX 3 Image Edit on this poster. Replace the top headline with "Saturday market", keeping its position and the illustration below.
- Use FLUX 3 Image Edit to turn this landscape photo into a watercolor illustration. Preserve the mountain shapes, river path, and framing.

## How to set up FLUX 3 Image Edit 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 3 Image Edit**: 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/edit-image",
    "input": {
      "prompt": "A red fox leaping over a stream in a pine forest, low-angle wildlife photograph.",
      "image_urls": [
        "<image_urls>"
      ]
    }
  }'
```

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

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

## FLUX 3 Image Edit tools and prices

- [FLUX 3 Image Edit](https://spiral.ai/tools/fal/blackforestlabs/flux-3/edit-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 Edit in ChatGPT?

Explore visual revisions from supplied photos and artwork with FLUX 3 Image Edit. Describe the change in ordinary language and identify the details you want preserved.

### Product color previews

Recolor a product in an existing photo while asking to preserve its shape, label, and setting. Specify the target color with a hex code and check the match.

### Product scene mockups

Combine a product reference with a setting reference to preview a new placement. Describe the product's position and how its lighting should fit the scene.

### Outfit previews

Use a person photo and a garment reference to preview a clothing change. Name the pose and surrounding details you want to preserve.

### Room furnishing concepts

Combine a room photo with furniture references to explore placement. State which object belongs where and which existing furnishings should stay.

### Poster copy revisions

Revise words inside an existing poster. Quote the new copy and identify its location so the instruction targets the right text.

### Object cleanup

Remove an unwanted object from an existing scene. Include its shadow or reflection in the removal request and inspect the surrounding area afterward.

### Illustration restyling

Explore a different visual treatment for existing artwork. Describe the new medium and identify the shapes and composition to retain.

### Packaging design previews

Combine a package photo with an artwork reference to preview a new surface design. Specify where the artwork belongs and which package details to preserve.

## Overview

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

## FLUX 3 Image Edit in other agents

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

## More ChatGPT guides

- [FLUX 3 Image](https://spiral.ai/integrations/chatgpt/flux-3-image)
- [FLUX 3 Klein Image Edit](https://spiral.ai/integrations/chatgpt/flux-3-klein-image-edit)
- [FLUX 1.1 Pro Ultra](https://spiral.ai/integrations/chatgpt/flux-1-1-pro-ultra)
- [FLUX 3 Klein Text to Image](https://spiral.ai/integrations/chatgpt/flux-3-klein-text-to-image)
- [FLUX 1.1 Pro](https://spiral.ai/integrations/chatgpt/flux-1-1-pro)
- [FLUX Kontext LoRA Text to Image](https://spiral.ai/integrations/chatgpt/flux-kontext-lora-text-to-image)

## Questions about FLUX 3 Image Edit in ChatGPT

**Can ChatGPT use FLUX 3 Image Edit?**

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

**How much does FLUX 3 Image Edit cost in ChatGPT?**

`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 ChatGPT plan is separate.

**Do I need a fal account to use FLUX 3 Image Edit in ChatGPT?**

No. Spiral runs FLUX 3 Image Edit 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 Edit 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 3 Image Edit runs?**

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

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

Use it to change a specific detail, restyle an existing image, or combine references into a new composition. Start with an image that already contains the parts you want to keep.

**How many reference images can I combine?**

You can combine up to ten references. Give each one a clear job, such as the scene, product, garment, or visual style.

**Will everything outside an edit stay unchanged?**

Treat preservation as something to check. Even with targeted edits, nearby shadows, reflections, or lighting may change.

**How large must reference images be?**

Each reference must be at least 256 pixels on both sides. Oversized references are downscaled to at most four megapixels, so inspect small details in the result.

**How do I change just one object?**

Identify it by its appearance and location, then describe the replacement and the details to preserve. Bounding boxes can guide placement, but they do not create a hard clipping boundary.

