[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Qwen Image Edit Lighting Restoration](https://spiral.ai/integrations/opencode/qwen-image-edit-lighting-restoration)

# How to Use Qwen Image Edit Lighting Restoration in opencode

Qwen Image Edit Lighting Restoration softens harsh shadows and bright light spots in existing photos. It targets even illumination, making it useful for lighting cleanup and preparing images for later relighting.

|  |  |
| --- | --- |
| Model | Qwen Image Edit Lighting Restoration |
| 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 Lighting Restoration in opencode

- Use Qwen Image Edit Lighting Restoration on the portrait in this project's assets, then show an original-and-result comparison.
- Use Qwen Image Edit Lighting Restoration on the product photo with harsh shadows, and add the candidate to our image review page.
- Use Qwen Image Edit Lighting Restoration on our hero photo, keep its dimensions, and preview the result in the existing layout.
- Use Qwen Image Edit Lighting Restoration to prepare a softly lit copy of the project portrait for a later relighting pass.
- Use Qwen Image Edit Lighting Restoration on the selected training portraits and organize each result beside its original for review.

## How to set up Qwen Image Edit Lighting Restoration in opencode

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

### Use Spiral's MCP server

1. **Add the server**: Leave out `--global` to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **Sign in**: Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, `/mcps` starts the same sign-in.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode 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 Lighting Restoration**: 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-plus-lora-gallery/lighting-restoration",
    "input": {
      "image_urls": [
        "<image_urls>"
      ]
    }
  }'
```

Then paste one of the prompts above: opencode finds Qwen Image Edit Lighting Restoration on Spiral, shows the price and runs it.

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

## Qwen Image Edit Lighting Restoration tools and prices

- [Qwen Image Edit Plus Lora Gallery · Lighting Restoration](https://spiral.ai/tools/fal/fal-ai/qwen-image-edit-plus-lora-gallery/lighting-restoration) (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. |
| guidance_scale | 0 to 20 | 1 | The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt. |
| num_inference_steps | 2 to 50 | 6 | The number of inference steps to perform. |
| acceleration | none, regular | regular | Acceleration level for image generation. 'regular' balances speed and quality. |
| negative_prompt |  |  | The negative prompt for the generation |
| seed |  | — | Random seed for reproducibility. Same seed with same prompt will produce same result. |

## What can you do with Qwen Image Edit Lighting Restoration in opencode?

Prepare softly lit photo candidates for a website or app using images already in the project. Your coding agent can place the results beside the originals for visual review.

### Portrait shadow cleanup

Soften harsh facial shadows in a portrait, then compare facial details with the original before selecting the edit.

### Product photo lighting cleanup

Try even illumination on a product photo with distracting light spots. Check labels, surface texture, and color before using the result.

### Preparation for creative relighting

Create a softly lit starting image before a separate editing pass adds the desired lighting.

### Lighting training pairs

Pair an original lit portrait with a lighting-removed result for review as training data.

### Website photo review

Prepare corrected candidates for website photos whose harsh shadows compete with the subject. Review them in the intended layout.

### Lighting correction comparisons

Build before-and-after comparisons to decide which photos benefit from softer illumination and which should keep their original contrast.

## Overview

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

## Qwen Image Edit Lighting Restoration in other agents

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

## More opencode guides

- [Qwen Image Edit Inpaint](https://spiral.ai/integrations/opencode/qwen-image-edit-inpaint)
- [Qwen Image Edit Multiple Angles](https://spiral.ai/integrations/opencode/qwen-image-edit-multiple-angles)
- [Qwen Image Edit Image to Image](https://spiral.ai/integrations/opencode/qwen-image-edit-image-to-image)
- [Qwen Image Edit Next Scene](https://spiral.ai/integrations/opencode/qwen-image-edit-next-scene)
- [Qwen Image Edit Face to Full Portrait](https://spiral.ai/integrations/opencode/qwen-image-edit-face-to-full-portrait)
- [Qwen Image Edit Plus](https://spiral.ai/integrations/opencode/qwen-image-edit-plus)

## Questions about Qwen Image Edit Lighting Restoration in opencode

**Can opencode use Qwen Image Edit Lighting Restoration?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Qwen Image Edit Lighting Restoration like any built-in tool.

**How much does Qwen Image Edit Lighting Restoration cost in opencode?**

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 opencode plan is separate.

**Do I need a fal account to use Qwen Image Edit Lighting Restoration in opencode?**

No. Spiral runs Qwen Image Edit Lighting Restoration 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 Lighting Restoration in opencode?**

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

**Does opencode wait while Qwen Image Edit Lighting Restoration runs?**

Qwen Image Edit Lighting Restoration runs in the background. opencode starts the run, checks on it and gives you the image when it's ready.

**What does Qwen Image Edit Lighting Restoration change?**

It targets harsh shadows and bright light spots in an existing image, replacing them with softer, more even illumination.

**Is it a good choice for dramatic portrait lighting?**

Choose it when you want to soften the existing lighting. Since shadow removal is its purpose, keep the original if strong contrast is part of the portrait's appeal.

**Can it prepare photos for a lighting training dataset?**

Yes. The creator describes removing illumination from a lit photo to help build training pairs with and without that lighting; review each pair before including it.

**How should I describe the lighting correction?**

Keep the request focused on removing light and shadow and producing soft, even illumination. The creator supplies a fixed Chinese instruction for that operation, so elaborate scene descriptions are unnecessary.

**What size will the restored image be?**

Without a requested output size, it uses the dimensions of the final input image. Compare the original and result at the same display size when checking the correction.

