[Integrations](https://spiral.ai/integrations) › [goose](https://spiral.ai/integrations/goose) › [DDColor](https://spiral.ai/integrations/goose/ddcolor)

# How to Use DDColor in goose

DDColor adds plausible color to black-and-white photographs, including archival portraits and street scenes. It estimates colors from the image, so treat the result as an interpretation rather than a record of the original colors.

|  |  |
| --- | --- |
| Model | DDColor |
| Available through | fal |
| Category | Image |
| Price | $0.0013 per 1,048,576 megapixels. Minimum 1,048,576 pixels. |
| Returns | image |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with DDColor in goose

- Use DDColor to colorize the black-and-white portraits in this project's assets directory. Save separate results and create a contact sheet pairing each result with its original.
- Use DDColor on the archival street photographs in this project. Build a review page that shows each original beside its colorized result and labels the colors as estimates.
- Use DDColor to colorize one sample photograph from each archive subfolder. Create a review gallery before processing the remaining photographs.
- Use DDColor on the project's monochrome photographs containing glassware. Put the originals and results side by side so I can inspect transparent objects for color artifacts.
- Use DDColor to prepare color interpretations of the historical portraits in this repository. Add a review checklist for clothing colors that need independent historical verification.

## How to set up DDColor in goose

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

### Use Spiral's MCP server

1. **Add the extension**: In goose Desktop, open the sidebar, click Extensions, then Add custom extension. Enter:

2. **Sign in**: When goose first connects to Spiral, your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key. If the browser does not open, goose prints the link to open yourself.

### Use the Spiral skill

1. **Send goose 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 DDColor**: 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/ddcolor",
    "input": {
      "image_url": "https://storage.googleapis.com/falserverless/gallery/Screenshot%202025-02-26%20154226.png"
    }
  }'
```

Then paste one of the prompts above: goose finds DDColor on Spiral, shows the price and runs it.

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

## DDColor tools and prices

- [DDColor](https://spiral.ai/tools/fal/fal-ai/ddcolor) (fal): $0.0013 per 1,048,576 megapixels. Minimum 1,048,576 pixels.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — | seed to be used for generation |

## What can you do with DDColor in goose?

Turn a project's black-and-white photo collection into colorized review images. Have the coding agent preserve originals, pair each result with its source, and build a comparison view.

### Personal photo albums

Create color interpretations of scanned black-and-white portraits for an album. Keep the original beside each result.

### Local history articles

Colorize archival street photographs for an article, and label the results as AI colorizations.

### Exhibition comparisons

Prepare original-and-colorized pairs for an exhibit about photographic interpretation. Let visitors compare the estimated colors with the source.

### Classroom discussion materials

Colorize historical photographs for a lesson about visual evidence. Ask students which colors would require independent verification.

### Documentary stills

Prepare colorized archival stills for editorial review. Check important clothing and object colors against historical references before publication.

### Modern monochrome photo experiments

Try color interpretations of modern black-and-white photographs. Compare the results with the monochrome versions before choosing an editorial treatment.

## Overview

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

## DDColor in other agents

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

## More goose guides

- [Crystal Upscaler](https://spiral.ai/integrations/goose/crystal-upscaler)
- [Dissolve](https://spiral.ai/integrations/goose/dissolve)
- [Color Tint](https://spiral.ai/integrations/goose/color-tint)
- [Dodge Burn](https://spiral.ai/integrations/goose/dodge-burn)
- [CodeFormer](https://spiral.ai/integrations/goose/codeformer)
- [EVF-SAM2](https://spiral.ai/integrations/goose/evf-sam2)

## Questions about DDColor in goose

**Can goose use DDColor?**

Yes. Add Spiral to goose as an MCP server, and goose can find and run DDColor like any built-in tool.

**How much does DDColor cost in goose?**

$0.0013 per 1,048,576 megapixels. Minimum 1,048,576 pixels. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your goose plan is separate.

**Do I need a fal account to use DDColor in goose?**

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

**How long does it take to set up DDColor in goose?**

About two minutes: add the extension, then sign in.

**Does goose wait while DDColor runs?**

DDColor runs in the background. goose starts the run, checks on it and gives you the image when it's ready.

**What is DDColor useful for?**

DDColor adds color to black-and-white photographs. Consider it for archival portraits, historical street scenes, or modern monochrome photos when you want a color interpretation.

**Does DDColor recover historically accurate colors?**

The result is a plausible estimate. A grayscale object can have several possible colors, so verify clothing, uniforms, and other historically important details against separate references.

**Which images need extra review?**

Check photographs containing transparent or translucent objects, such as glassware. The authors identify these objects as a source of color artifacts.

**Is DDColor limited to 512 × 512 output?**

The official implementation defaults to processing a 512 × 512 copy, then resizes the predicted color channels to the source dimensions. That does not establish a maximum output size for the hosted model.

**How should I prompt an agent using DDColor?**

Specify the photograph to colorize and what to inspect afterward, such as glass artifacts or colors that need historical verification. The official demo uses an image-driven workflow, so detailed prose about a desired palette is not established color control.

