[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [Qwen Image Edit 2509 LoRA](https://spiral.ai/integrations/claude-code/qwen-image-edit-2509-lora)

# How to Use Qwen Image Edit 2509 LoRA in Claude Code

Use Qwen Image Edit 2509 LoRA to revise product photos, portraits, and text inside images. Unlike Qwen Image Edit 2509, it supports loading custom LoRA adapters for specialized edits.

|  |  |
| --- | --- |
| Model | Qwen Image Edit 2509 LoRA |
| Available through | fal |
| Category | Image |
| Price | Up to $0.0455 per run at the default inputs. $0.0455 per unit of `num_images`. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen Image Edit 2509 LoRA in Claude Code

- Use Qwen Image Edit 2509 LoRA on the product photo in public/images. Place the product on a sunlit kitchen counter, preserving its shape and label. Save the result separately for review.
- Use Qwen Image Edit 2509 LoRA to replace 'Coming soon' with 'Now available' in the project's launch poster. Preserve the illustration and text placement, then check the spelling.
- Use Qwen Image Edit 2509 LoRA to turn the project's founder portrait into a watercolor illustration. Preserve recognizable facial features and save a comparison with the original.
- Use Qwen Image Edit 2509 LoRA with the portrait and pose keypoint image in the assets directory. Apply the reference pose while preserving the person's face and clothing.
- Use Qwen Image Edit 2509 LoRA to revise the project's promotional image at 1280 by 720 pixels. Change the headline lettering to brushed copper while keeping its wording and the product recognizable.

## How to set up Qwen Image Edit 2509 LoRA in Claude Code

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

### Use Spiral's MCP server

1. **Add the hosted server**: This adds Spiral to the current project. Add `--scope user` to use it in every project.

```bash
claude mcp add --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `claude`, type `/mcp`, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

### Use the Spiral skill

1. **Send Claude Code 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 Qwen Image Edit 2509 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/qwen-image-edit-2509-lora",
    "input": {
      "prompt": "Close shot of a woman standing in next to this car on this highway",
      "image_urls": [
        "<image_urls>"
      ]
    }
  }'
```

Then paste one of the prompts above: Claude Code finds Qwen Image Edit 2509 LoRA on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-code

## Qwen Image Edit 2509 LoRA tools and prices

- [Qwen Image Edit 2509 Lora](https://spiral.ai/tools/fal/fal-ai/qwen-image-edit-2509-lora) (fal): Up to $0.0455 per run at the default inputs. $0.0455 per unit of `num_images`.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| image_size |  | — | The size of the generated image. If not provided, the size of the final input image will be used to calculate the size of the output image. |
| num_inference_steps | 2 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 | 0 to 20 | 4 | 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 | png | The format of the generated image. |

## What can you do with Qwen Image Edit 2509 LoRA in Claude Code?

Turn existing project artwork into revised product scenes, portraits, and promotional images with Qwen Image Edit 2509 LoRA. A coding agent can use the project's assets and copy to prepare edits and check the results against the originals.

### Product campaign images

Use Qwen Image Edit 2509 LoRA to place a photographed product in a new setting. Check its shape, label, and identifying details against the reference.

### Portrait style studies

Use Qwen Image Edit 2509 LoRA to explore painted or illustrated treatments of an existing portrait while retaining the person's recognizable features.

### Poster copy revisions

Use Qwen Image Edit 2509 LoRA to replace Chinese or English wording in an existing poster, then proofread the rendered text.

### Lettering treatments

Use Qwen Image Edit 2509 LoRA to explore a different font, color, or material for lettering already present in an image.

### Pose studies from references

Use Qwen Image Edit 2509 LoRA with a portrait and a keypoint map to explore a new pose. Review facial identity and body proportions.

### Composite portraits

Use Qwen Image Edit 2509 LoRA to bring people from separate reference images into one scene. Compare each face with its source image.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Claude Code guides](https://spiral.ai/integrations/claude-code)

## Qwen Image Edit 2509 LoRA in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen-image-edit-2509-lora)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen-image-edit-2509-lora)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen-image-edit-2509-lora)
- [Cline](https://spiral.ai/integrations/cline/qwen-image-edit-2509-lora)
- [Codex](https://spiral.ai/integrations/codex/qwen-image-edit-2509-lora)
- [Cursor](https://spiral.ai/integrations/cursor/qwen-image-edit-2509-lora)
- [Devin](https://spiral.ai/integrations/devin/qwen-image-edit-2509-lora)
- [dots](https://spiral.ai/integrations/dots/qwen-image-edit-2509-lora)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen-image-edit-2509-lora)
- [Gemini](https://spiral.ai/integrations/gemini/qwen-image-edit-2509-lora)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen-image-edit-2509-lora)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen-image-edit-2509-lora)
- [goose](https://spiral.ai/integrations/goose/qwen-image-edit-2509-lora)
- [Grok](https://spiral.ai/integrations/grok/qwen-image-edit-2509-lora)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen-image-edit-2509-lora)
- [Hermes](https://spiral.ai/integrations/hermes/qwen-image-edit-2509-lora)
- [Instinct](https://spiral.ai/integrations/instinct/qwen-image-edit-2509-lora)
- [Manus](https://spiral.ai/integrations/manus/qwen-image-edit-2509-lora)
- [Muse](https://spiral.ai/integrations/muse/qwen-image-edit-2509-lora)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen-image-edit-2509-lora)
- [n8n](https://spiral.ai/integrations/n8n/qwen-image-edit-2509-lora)
- [Notion](https://spiral.ai/integrations/notion/qwen-image-edit-2509-lora)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen-image-edit-2509-lora)
- [opencode](https://spiral.ai/integrations/opencode/qwen-image-edit-2509-lora)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen-image-edit-2509-lora)
- [Raycast](https://spiral.ai/integrations/raycast/qwen-image-edit-2509-lora)
- [VS Code](https://spiral.ai/integrations/vscode/qwen-image-edit-2509-lora)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen-image-edit-2509-lora)
- [Zapier](https://spiral.ai/integrations/zapier/qwen-image-edit-2509-lora)

## More Claude Code guides

- [Qwen Image Edit 2509 Lighting Restoration](https://spiral.ai/integrations/claude-code/qwen-image-edit-2509-lighting-restoration)
- [Qwen Image Edit 2509 Multiple Angles](https://spiral.ai/integrations/claude-code/qwen-image-edit-2509-multiple-angles)
- [Qwen Image Edit 2509 Integrate Product](https://spiral.ai/integrations/claude-code/qwen-image-edit-2509-integrate-product)
- [Qwen Image Edit 2509 Next Scene](https://spiral.ai/integrations/claude-code/qwen-image-edit-2509-next-scene)
- [Qwen Image Edit 2509 Group Photo](https://spiral.ai/integrations/claude-code/qwen-image-edit-2509-group-photo)
- [Qwen Image Edit 2509 Remove Element](https://spiral.ai/integrations/claude-code/qwen-image-edit-2509-remove-element)

## Questions about Qwen Image Edit 2509 LoRA in Claude Code

**Can Claude Code use Qwen Image Edit 2509 LoRA?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Qwen Image Edit 2509 LoRA like any built-in tool.

**How much does Qwen Image Edit 2509 LoRA cost in Claude Code?**

Up to $0.0455 per run at the default inputs. $0.0455 per unit of `num_images`. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

**Do I need a fal account to use Qwen Image Edit 2509 LoRA in Claude Code?**

No. Spiral runs Qwen Image Edit 2509 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 Qwen Image Edit 2509 LoRA in Claude Code?**

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

**Does Claude Code wait while Qwen Image Edit 2509 LoRA runs?**

Qwen Image Edit 2509 LoRA runs in the background. Claude Code starts the run, checks on it and gives you the image when it's ready.

**What is Qwen Image Edit 2509 LoRA good at?**

It suits edits where recognizable faces, products, or existing lettering matter. Use it for product scenes, portrait treatments, and revisions to text inside an image.

**How many reference images should I use?**

Qwen recommends one to three for the best results. Give each reference a clear job, such as the person, the product, or the setting.

**Can it edit Chinese and English lettering?**

Yes, Qwen Image Edit supports adding, removing, and replacing text in both languages. Specify the exact replacement wording and proofread the result.

**Will faces and products stay exactly the same?**

Treat preservation as something to check. Qwen describes further reductions in image drift and improvements in character consistency in 2511, so compare 2509 results with the original references.

**Can I request a specific output size?**

Yes, custom width and height are supported. The documentation gives 1280 by 720 pixels as an example.

