[Integrations](https://spiral.ai/integrations) › [Notion](https://spiral.ai/integrations/notion) › [Fal Color Correction](https://spiral.ai/integrations/notion/fal-color-correction)

# How to Use Fal Color Correction in Notion

Fal Color Correction adjusts an existing photo toward balanced tones and natural color. Its focus is photo color grading, with no custom text editing instruction documented.

|  |  |
| --- | --- |
| Model | Fal Color Correction |
| Available through | fal |
| Category | Image |
| Price | $0.052 per image. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Fal Color Correction in Notion

- Every morning, use Fal Color Correction on new product photos in the review collection. Present originals and corrected candidates together for color approval.
- Each Friday, use Fal Color Correction on newly submitted newsletter photos. Assemble a review gallery without replacing the originals.
- Each evening, use Fal Color Correction on new restaurant photos awaiting review. Flag the pairs for a check of natural ingredient colors.
- Every Monday, use Fal Color Correction on new property photos in the review collection. Prepare comparisons for checking walls, floors, and furnishings.
- Once a week, use Fal Color Correction on newly submitted team portraits. Save PNG candidates and arrange them beside the originals for skin tone review.

## How to set up Fal Color Correction in Notion

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

### Use the Spiral skill

1. **Send Notion 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 Spiral's MCP server

1. **Allow custom MCP servers**: A workspace owner opens Settings › Connections, then the Manage tab, and turns on Enable custom MCP servers. Where members may install only approved connections, also add Spiral under Approved connections › Add approved connection › Custom MCP server with the URL below.

2. **Add Spiral to a custom agent**: Open the custom agent (or create one), then Settings › Tools & Access › Add connection › Custom MCP server. Paste this URL, name it Spiral, keep OAuth and click Connect.

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

3. **Sign in to Spiral and approve**: Spiral opens: sign in, pick the organization and click Authorize. No API key. Spiral gives the connection its own key; Notion never sees it, and you can remove it under Settings › Connected apps in the console.

4. **Run Fal Color Correction in a workflow step**: Give the step an instruction like the ones below and run it on your trigger or schedule. Spiral finds Fal Color Correction, prices it and runs it each time the step fires.

### 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 Fal Color Correction**: 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/image-editing/color-correction",
    "input": {
      "image_url": "https://v3.fal.media/files/zebra/hAjCkcyly4gsS9-cptD3Y_image%20(20).png"
    }
  }'
```

Then paste one of the prompts above: Notion finds Fal Color Correction on Spiral, shows the price and runs it.

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

## Fal Color Correction tools and prices

- [Image Editing Color Correction](https://spiral.ai/tools/fal/fal-ai/image-editing/color-correction) (fal): $0.052 per image.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| guidance_scale | 0 to 20 | 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_inference_steps | 1 to 50 | 30 | Number of inference steps for sampling. |
| safety_tolerance | 1, 2, 3, 4, 5, 6 | 2 | The safety tolerance level for the generated image. 1 being the most strict and 6 being the most permissive. |
| output_format | jpeg, png | jpeg | The format of the generated image. |
| aspect_ratio | 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21 | — | The aspect ratio of the generated image. |
| seed |  | — | The same seed and the same prompt given to the same version of the model will output the same image every time. |

## What can you do with Fal Color Correction in Notion?

Prepare color corrected photo candidates as new images arrive for review. A scheduled agent can organize originals and results into a recurring review gallery.

### Product listing photo review

Try a natural color correction pass on a product photo, then compare the result with the original before approving product colors.

### Portrait color review

Create a corrected portrait candidate and inspect skin tones alongside the original before choosing the final image.

### Food photo preparation

Test a color correction pass on a restaurant or recipe photo. Review whether the ingredients still look natural.

### Property photo preparation

Create a corrected candidate for a property listing and review neutral walls, wood, and furnishings against the source photo.

### Travel photo selection

Try color correction on travel photos before assembling a gallery. Compare skies, foliage, and overall tone with the originals.

### Editorial photo review

Prepare a color corrected candidate for an article or newsletter, keeping the source image beside it for editorial review.

## Overview

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

## Fal Color Correction in other agents

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

## More Notion guides

- [Face Enhancement](https://spiral.ai/integrations/notion/face-enhancement)
- [FeyNoBg](https://spiral.ai/integrations/notion/feynobg)
- [FLUX1.1 Pro Ultra Fine-tuned](https://spiral.ai/integrations/notion/flux1-1-pro-ultra-fine-tuned)
- [Fibo 2.0 Edit](https://spiral.ai/integrations/notion/fibo-2-0-edit)
- [FLUX1.1 Pro Redux](https://spiral.ai/integrations/notion/flux1-1-pro-redux)
- [Fibo 2.0 Generate](https://spiral.ai/integrations/notion/fibo-2-0-generate)

## Questions about Fal Color Correction in Notion

**Can Notion use Fal Color Correction?**

Yes. Add Spiral to Notion as an MCP server, and Notion can find and run Fal Color Correction like any built-in tool.

**How much does Fal Color Correction cost in Notion?**

$0.052 per image. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Notion plan is separate.

**Do I need a fal account to use Fal Color Correction in Notion?**

No. Spiral runs Fal Color Correction on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Fal Color Correction in Notion?**

About two minutes: allow custom MCP servers, then add Spiral to a custom agent, then sign in to Spiral and approve.

**Does Notion wait while Fal Color Correction runs?**

Fal Color Correction runs in the background. Notion starts the run, checks on it and gives you the image when it's ready.

**What is Fal Color Correction good for?**

It targets balanced tones and natural color in existing photos. Consider it for a color correction pass before reviewing an image for publication.

**Is Fal Color Correction intended for natural or stylized grading?**

The stated target is vibrant but natural color. For a specific cinematic treatment, do not assume the result will match a named film stock or reference grade.

**How should I prompt Fal Color Correction?**

Give your agent the photo to process and clear review criteria, such as checking skin tones or product colors afterward. The published model schema does not document a custom text editing instruction.

**Can I reproduce a correction?**

The documentation describes repeatable results with the same seed, prompt, and model version. Keep those fixed when revisiting a candidate.

**How should I evaluate a corrected photo?**

Use balanced tones and natural color as the review criteria. Compare against the original, paying particular attention to skin, neutral surfaces, and any color that matters to the subject.

