[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [FLUX.2 LoRA Edit](https://spiral.ai/integrations/antigravity/flux-2-lora-edit)

# How to Use FLUX.2 LoRA Edit in Google Antigravity

Use FLUX.2 LoRA Edit for learned image transformations, such as a consistent illustration treatment. Unlike FLUX.2 LoRA, it applies that training to existing images.

|  |  |
| --- | --- |
| Model | FLUX.2 LoRA Edit |
| Available through | fal |
| Category | Image |
| Price | Up to $0.34125 per run at the default inputs. $0.273 per unit of `num_images`. Each item in `image_urls` adds $0.06825. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with FLUX.2 LoRA Edit in Google Antigravity

- Use FLUX.2 LoRA Edit on the product photograph in the project's assets. Place the product on a dark stone counter with soft window light from the right. Preserve its shape, label wording, and camera angle. Return a 1536 × 1024 image.
- Use FLUX.2 LoRA Edit to revise the project's onboarding illustration. Change the setting to a bright home office while preserving the person's pose, clothing, and position. Keep the result at 1024 × 1024.
- Remove the background from the photo I attach with FLUX.2 LoRA Edit and give me a transparent PNG. Save the result in ./assets.
- Use FLUX.2 LoRA Edit to clean up these product shots so they sit on pure white.
- Edit this image with FLUX.2 LoRA Edit: keep the subject, swap the background for a sunlit studio.

## How to set up FLUX.2 LoRA Edit in Google Antigravity

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

### Use Spiral's MCP server

1. **Open the MCP config**: * Antigravity App: click Customizations, then Installed. In the MCP Servers section, click Copy Config File Path and open that file. * Antigravity IDE: click … at the top of the agent side panel, select MCP Servers, then Manage MCP Servers › View raw config. * Antigravity CLI: edit `~/.gemini/config/mcp_config.json`.

2. **Add the server**: Add Spiral under `mcpServers`:

```json
{
  "mcpServers": {
    "spiral": {
      "serverUrl": "https://api.spiral.ai/mcp"
    }
  }
}
```

3. **Sign in**: In the Antigravity App, open Customizations › Installed. Under MCP Servers, click Authenticate next to Spiral. Sign in to Spiral, pick the organization and click Authorize. Copy the authorization code the browser shows, paste it into Enter authorization code and click Submit. No API key.

### Use the Spiral skill

1. **Send Google Antigravity 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.2 LoRA 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": "fal-ai/flux-2/lora/edit",
    "input": {
      "prompt": "Make this donut realistic",
      "image_urls": [
        "<image_urls>"
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds FLUX.2 LoRA Edit on Spiral, shows the price and runs it.

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

## FLUX.2 LoRA Edit tools and prices

- [FLUX 2 Lora Edit · Image Editing LoRA](https://spiral.ai/tools/fal/fal-ai/flux-2/lora/edit) (fal): Up to $0.34125 per run at the default inputs. $0.273 per unit of `num_images`. Each item in `image_urls` adds $0.06825.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| guidance_scale | 0 to 20 | 2.5 | 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. |
| seed |  | — | The seed to use for the generation. If not provided, a random seed will be used. |
| num_inference_steps | 4 to 50 | 28 | The number of inference steps to perform. |
| image_size |  | — | The size of the image to generate. The width and height must be between 512 and 2048 pixels. |
| num_images | 1 to 4 | 1 | The number of images to generate. |
| acceleration | none, regular, high | regular | The acceleration level to use for the image generation. |

## What can you do with FLUX.2 LoRA Edit in Google Antigravity?

Create product imagery and visual design concepts alongside the project you are building. Have the agent turn project requirements into concrete image briefs with explicit composition, colors, and text.

### Product background changes

Start with a product image and request a new setting. Describe the product details to preserve and the lighting needed in the replacement scene.

### Color studies from existing images

Recolor a garment, package, or piece of furniture in a supplied image. Name the object and provide its target hex color while asking to preserve its texture.

### Illustrated treatments of photographs

Transform a supplied photograph into a specified illustration style. State which subjects, poses, and spatial relationships should remain recognizable.

### Reference-based compositions

Combine a subject from one reference with an object or setting from another. Explain what each image contributes and how the elements should fit together.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Google Antigravity guides](https://spiral.ai/integrations/antigravity)

## FLUX.2 LoRA Edit in other agents

- [Amp](https://spiral.ai/integrations/amp/flux-2-lora-edit)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/flux-2-lora-edit)
- [Claude](https://spiral.ai/integrations/claude-desktop/flux-2-lora-edit)
- [Claude Code](https://spiral.ai/integrations/claude-code/flux-2-lora-edit)
- [Cline](https://spiral.ai/integrations/cline/flux-2-lora-edit)
- [Codex](https://spiral.ai/integrations/codex/flux-2-lora-edit)
- [Cursor](https://spiral.ai/integrations/cursor/flux-2-lora-edit)
- [Devin](https://spiral.ai/integrations/devin/flux-2-lora-edit)
- [dots](https://spiral.ai/integrations/dots/flux-2-lora-edit)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/flux-2-lora-edit)
- [Gemini](https://spiral.ai/integrations/gemini/flux-2-lora-edit)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/flux-2-lora-edit)
- [goose](https://spiral.ai/integrations/goose/flux-2-lora-edit)
- [Grok](https://spiral.ai/integrations/grok/flux-2-lora-edit)
- [Grok Build](https://spiral.ai/integrations/grok-build/flux-2-lora-edit)
- [Hermes](https://spiral.ai/integrations/hermes/flux-2-lora-edit)
- [Instinct](https://spiral.ai/integrations/instinct/flux-2-lora-edit)
- [Manus](https://spiral.ai/integrations/manus/flux-2-lora-edit)
- [Muse](https://spiral.ai/integrations/muse/flux-2-lora-edit)
- [Muse Code](https://spiral.ai/integrations/muse-code/flux-2-lora-edit)
- [n8n](https://spiral.ai/integrations/n8n/flux-2-lora-edit)
- [Notion](https://spiral.ai/integrations/notion/flux-2-lora-edit)
- [OpenClaw](https://spiral.ai/integrations/openclaw/flux-2-lora-edit)
- [opencode](https://spiral.ai/integrations/opencode/flux-2-lora-edit)
- [Perplexity](https://spiral.ai/integrations/perplexity/flux-2-lora-edit)
- [Raycast](https://spiral.ai/integrations/raycast/flux-2-lora-edit)
- [VS Code](https://spiral.ai/integrations/vscode/flux-2-lora-edit)
- [Windsurf](https://spiral.ai/integrations/windsurf/flux-2-lora-edit)
- [Zapier](https://spiral.ai/integrations/zapier/flux-2-lora-edit)

## More Google Antigravity guides

- [FLUX.2 LoRA](https://spiral.ai/integrations/antigravity/flux-2-lora)
- [FLUX.2 Max](https://spiral.ai/integrations/antigravity/flux-2-max)
- [FLUX.2 Klein 9B LoRA](https://spiral.ai/integrations/antigravity/flux-2-klein-9b-lora)
- [FLUX.2 Max Edit](https://spiral.ai/integrations/antigravity/flux-2-max-edit)
- [FLUX.2 Klein 9B Base LoRA](https://spiral.ai/integrations/antigravity/flux-2-klein-9b-base-lora)
- [FLUX.2 Realism LoRA](https://spiral.ai/integrations/antigravity/flux-2-realism-lora)

## Questions about FLUX.2 LoRA Edit in Google Antigravity

**Can Google Antigravity use FLUX.2 LoRA Edit?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run FLUX.2 LoRA Edit like any built-in tool.

**How much does FLUX.2 LoRA Edit cost in Google Antigravity?**

Up to $0.34125 per run at the default inputs. $0.273 per unit of `num_images`. Each item in `image_urls` adds $0.06825. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Google Antigravity plan is separate.

**Do I need a fal account to use FLUX.2 LoRA Edit in Google Antigravity?**

No. Spiral runs FLUX.2 LoRA 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.2 LoRA Edit in Google Antigravity?**

About two minutes: open the MCP config, then add the server, then sign in.

**Does Google Antigravity wait while FLUX.2 LoRA Edit runs?**

FLUX.2 LoRA Edit runs in the background. Google Antigravity starts the run, checks on it and gives you the image when it's ready.

**What is FLUX.2 good at?**

FLUX.2 is useful for realistic product imagery, editorial scenes, and designs that include text. Specify the materials, lighting, composition, and exact wording you want.

**How large can FLUX.2 images be?**

These FLUX.2 tools support dimensions from 512 to 2048 pixels per side. A square image can reach 2048 × 2048 pixels, roughly four megapixels.

**How should I write a FLUX.2 prompt?**

Describe the subject, action, visual style, and setting. Use concrete details such as brushed steel, side lighting, or an overhead view.

**Does FLUX.2 support negative prompts?**

No. Describe the desired result positively: ask for an empty street or sharp focus instead of listing things to exclude.

**How do I get readable text in FLUX.2 images?**

Put the exact wording in quotation marks and describe its position and appearance. Black Forest Labs warns that text-bearing objects can produce gibberish when you leave their wording unspecified.

