hair-color-changer

Original source / Raw SKILL.md

---
name: hair-color-changer
description: Change hair color in photos using each::sense AI. Transform hair to any color including natural shades, fantasy colors, ombre effects, highlights, and more.
metadata:
  author: eachlabs
  version: "1.0"
---

# Hair Color Changer

Transform hair color in photos using each::sense. This skill enables realistic hair color changes from subtle natural variations to bold fantasy colors, with support for complex effects like ombre, highlights, and multi-tone styling.

## Features

- **Natural Colors**: Blonde, brunette, black, red, auburn
- **Fantasy Colors**: Purple, blue, pink, green, and more
- **Ombre & Gradient**: Smooth color transitions from roots to tips
- **Highlights & Lowlights**: Multi-dimensional color effects
- **Gray & Silver**: Elegant silver, platinum, and gray tones
- **Color Correction**: Fix or enhance existing hair color
- **Multi-Turn Sessions**: Iterate on results and try different colors

## Quick Start

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Change the hair color to platinum blonde, keep it looking natural and shiny",
    "image_urls": ["https://example.com/portrait.jpg"],
    "mode": "max"
  }'
```

## Use Case Examples

### 1. Change Hair to Blonde

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Change the hair to a warm honey blonde color. Keep the hair texture and shine natural, maintain realistic highlights throughout.",
    "image_urls": ["https://example.com/original-photo.jpg"],
    "mode": "max"
  }'
```

### 2. Change Hair to Brunette

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Transform the hair to a rich chocolate brown color. Add subtle warm undertones and natural-looking dimension to the brunette shade.",
    "image_urls": ["https://example.com/portrait.jpg"],
    "mode": "max"
  }'
```

### 3. Change Hair to Red/Auburn

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Change the hair color to a vibrant auburn red. Make it look like natural ginger hair with copper highlights that catch the light.",
    "image_urls": ["https://example.com/model-photo.jpg"],
    "mode": "max"
  }'
```

### 4. Fantasy Colors (Purple, Blue, Pink)

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Transform the hair to a vivid galaxy purple color. Make it look like professionally dyed hair with deep violet tones and subtle blue undertones. Keep the hair healthy and shiny looking.",
    "image_urls": ["https://example.com/portrait.jpg"],
    "mode": "max"
  }'
```

```bash
# Electric blue hair
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Change the hair to electric blue color, like a bold fashion statement. Mix of deep blue and bright cyan tones throughout.",
    "image_urls": ["https://example.com/photo.jpg"],
    "mode": "max"
  }'
```

```bash
# Pastel pink hair
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Transform the hair to a soft pastel pink color. Think rose gold meets cotton candy - delicate, feminine, and Instagram-worthy.",
    "image_urls": ["https://example.com/headshot.jpg"],
    "mode": "max"
  }'
```

### 5. Ombre/Gradient Effect

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Create an ombre hair effect - dark brown roots transitioning smoothly to caramel blonde at the ends. Make the gradient look natural and well-blended like salon balayage.",
    "image_urls": ["https://example.com/full-portrait.jpg"],
    "mode": "max"
  }'
```

```bash
# Fantasy ombre
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Create a fantasy ombre effect with dark purple roots fading into bright pink, then to peachy coral at the tips. Smooth gradient transitions like a sunset.",
    "image_urls": ["https://example.com/model.jpg"],
    "mode": "max"
  }'
```

### 6. Highlights and Lowlights

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Add dimensional highlights and lowlights to the hair. Keep the base color but add face-framing blonde highlights and subtle caramel lowlights throughout for depth and dimension.",
    "image_urls": ["https://example.com/brunette-photo.jpg"],
    "mode": "max"
  }'
```

```bash
# Babylights effect
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Add subtle babylights throughout the hair - very fine, delicate highlights like sun-kissed natural lightening. Keep it soft and natural looking.",
    "image_urls": ["https://example.com/portrait.jpg"],
    "mode": "max"
  }'
```

### 7. Gray/Silver Hair

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Transform the hair to an elegant silver gray color. Make it look like intentional fashion-forward silver hair, not aging gray - metallic, shiny, and well-maintained.",
    "image_urls": ["https://example.com/fashion-photo.jpg"],
    "mode": "max"
  }'
```

```bash
# Platinum silver
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Change hair to platinum silver with icy undertones. Think high fashion editorial silver - cool-toned, luminous, and striking.",
    "image_urls": ["https://example.com/model-headshot.jpg"],
    "mode": "max"
  }'
```

### 8. Natural Color Variations

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Adjust the hair color to be 2 shades darker, turning it from medium brown to a deep espresso brown. Keep all the natural texture and shine.",
    "image_urls": ["https://example.com/natural-photo.jpg"],
    "mode": "max"
  }'
```

```bash
# Warm up cool tones
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Add warm golden undertones to the existing hair color. Keep the same overall shade but remove any ashy tones and make it warmer and more vibrant.",
    "image_urls": ["https://example.com/portrait.jpg"],
    "mode": "eco"
  }'
```

### 9. Multiple Color Options from Same Photo

Use `session_id` to try different colors on the same photo:

```bash
# First option - Blonde
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Change my hair to platinum blonde. I want to see how I would look with this color.",
    "image_urls": ["https://example.com/my-photo.jpg"],
    "session_id": "hair-color-tryout-001",
    "mode": "eco"
  }'

# Second option - Red (same session)
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Now show me the same photo but with fiery red hair instead.",
    "session_id": "hair-color-tryout-001",
    "mode": "eco"
  }'

# Third option - Black (same session)
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "And one more variation with jet black hair please.",
    "session_id": "hair-color-tryout-001",
    "mode": "eco"
  }'
```

### 10. Before/After Comparison

```bash
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Change the hair to rose gold color, then create a side-by-side before and after comparison showing the original on the left and the new color on the right.",
    "image_urls": ["https://example.com/original-portrait.jpg"],
    "mode": "max"
  }'
```

```bash
# Iterative refinement for comparison
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Transform the hair to strawberry blonde.",
    "image_urls": ["https://example.com/client-photo.jpg"],
    "session_id": "client-consultation-001",
    "mode": "max"
  }'

# Follow-up to adjust
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Make the strawberry blonde a bit more pink and less orange. Also make it slightly lighter overall.",
    "session_id": "client-consultation-001",
    "mode": "max"
  }'
```

## Best Practices

### Getting Realistic Results

- **Good Lighting**: Use photos with clear, even lighting on the hair
- **Hair Visibility**: Ensure the hair is clearly visible and not obscured
- **Face Forward**: Front-facing or 3/4 angle photos work best
- **High Resolution**: Higher quality source images yield better results

### Prompt Tips

1. **Be Specific**: Describe the exact shade you want (e.g., "warm honey blonde" vs just "blonde")
2. **Reference Tones**: Mention undertones (warm, cool, neutral, ashy, golden)
3. **Texture Preservation**: Request to maintain natural texture and shine
4. **Realistic Expectations**: Fantasy colors may look more vibrant on lighter base colors

### Example Prompt Structure

```
"Change the hair to [specific color with undertones].
[Additional details about dimension, highlights, or effects].
Keep the hair looking [natural/healthy/shiny/textured]."
```

## Mode Selection

**"Do you want fast results or highest quality?"**

| Mode | Best For | Speed | Quality |
|------|----------|-------|---------|
| `max` | Final results, client presentations, portfolio work | Slower | Highest |
| `eco` | Quick previews, trying multiple colors, concept exploration | Faster | Good |

## Multi-Turn Color Exploration

Use `session_id` to iterate and explore colors:

```bash
# Start with a base change
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Change my hair to copper red",
    "image_urls": ["https://example.com/selfie.jpg"],
    "session_id": "hair-exploration"
  }'

# Request adjustment
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Make it more auburn and less orange, add some brown lowlights",
    "session_id": "hair-exploration"
  }'

# Try a completely different direction
curl -X POST https://sense.eachlabs.run/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "message": "Actually, let me see the original photo with silver gray hair instead",
    "session_id": "hair-exploration"
  }'
```

## Error Handling

| Error | Cause | Solution |
|-------|-------|----------|
| `Failed to create prediction: HTTP 422` | Insufficient balance | Top up at eachlabs.ai |
| No hair detected | Hair not visible in image | Use a clearer photo with visible hair |
| Unnatural results | Low quality source image | Use higher resolution photo with good lighting |
| Timeout | Complex generation | Set client timeout to minimum 10 minutes |

## Related Skills

- `each-sense` - Core API documentation
- `face-swap` - Face swapping capabilities
- `image-edit` - General image editing
- `product-photo-generation` - E-commerce product shots


---

## Skill Companion Files

> Additional files collected from the skill directory layout.

### _meta.json

```json
{
  "owner": "eftalyurtseven",
  "slug": "hair-color-changer",
  "displayName": "Hair Color Changer",
  "latest": {
    "version": "1.0.0",
    "publishedAt": 1772561228831,
    "commit": "https://github.com/openclaw/skills/commit/88cbdca98eae10c0dafac5d8dd287ae0bbfd44d4"
  },
  "history": []
}

```

### references/SSE-EVENTS.md

```markdown
# SSE Event Reference

Detailed documentation for all Server-Sent Events (SSE) returned by the each::sense `/chat` endpoint.

## Event Format

Each event follows this format:
```
data: {"type": "event_type", ...fields}\n\n
```

Stream ends with:
```
data: [DONE]\n\n
```

---

## Event Types

### thinking_delta

Claude's reasoning as it streams in real-time. Use this to show users what the AI is thinking.

```json
{
  "type": "thinking_delta",
  "content": "Let me find the best model for portrait generation..."
}
```

| Field | Type | Description |
|-------|------|-------------|
| `content` | string | Incremental thinking text |

---

### status

Current operation being executed. Shows tool usage and parameters.

```json
{
  "type": "status",
  "message": "Searching for image generation models...",
  "tool_name": "search_models",
  "parameters": {"use_case": "text to image portrait"}
}
```

| Field | Type | Description |
|-------|------|-------------|
| `message` | string | Human-readable status message |
| `tool_name` | string | Internal tool being used |
| `parameters` | object | Tool parameters (optional) |

---

### text_response

Text content from the AI (explanations, answers, plans).

```json
{
  "type": "text_response",
  "content": "I'll create a stunning portrait for you with cinematic lighting and a warm mood."
}
```

| Field | Type | Description |
|-------|------|-------------|
| `content` | string | Text response content |

---

### generation_response

Generated media URL (image or video). This is the primary output event.

```json
{
  "type": "generation_response",
  "url": "https://storage.eachlabs.ai/outputs/abc123.png",
  "generations": ["https://storage.eachlabs.ai/outputs/abc123.png"],
  "total": 1,
  "tool_name": "execute_model",
  "model": "nano-banana-pro"
}
```

| Field | Type | Description |
|-------|------|-------------|
| `url` | string | Primary output URL |
| `generations` | array | All generated URLs |
| `total` | number | Total number of generations |
| `tool_name` | string | Tool that generated output |
| `model` | string | Model used for generation |

---

### clarification_needed

AI needs more information to proceed. Present options to the user.

```json
{
  "type": "clarification_needed",
  "question": "What type of edit would you like to make to this image?",
  "options": [
    "Remove the background",
    "Apply a style transfer",
    "Upscale to higher resolution",
    "Add or modify elements"
  ],
  "context": "I can see you've uploaded an image, but I need to understand what changes you'd like."
}
```

| Field | Type | Description |
|-------|------|-------------|
| `question` | string | The question to ask the user |
| `options` | array | Suggested options (can be displayed as buttons) |
| `context` | string | Additional context about the clarification |

**Handling:** Display the question and options to the user. Send their response in a follow-up request with the same `session_id`.

---

### web_search_query

Web search being executed.

```json
{
  "type": "web_search_query",
  "query": "best AI video generation models 2024",
  "recency": "month"
}
```

| Field | Type | Description |
|-------|------|-------------|
| `query` | string | Search query |
| `recency` | string | Time filter (day, week, month, year) |

---

### web_search_citations

Citations from web search results.

```json
{
  "type": "web_search_citations",
  "citations": [
    "https://example.com/ai-video-comparison",
    "https://techblog.com/veo3-review"
  ],
  "count": 2
}
```

| Field | Type | Description |
|-------|------|-------------|
| `citations` | array | URLs of sources cited |
| `count` | number | Number of citations |

---

### workflow_created

New workflow was created for complex multi-step generation.

```json
{
  "type": "workflow_created",
  "workflow_id": "wf_abc123",
  "version_id": "v1",
  "input_schema": {
    "properties": {
      "character_description": {
        "type": "text",
        "required": true,
        "default_value": ""
      }
    }
  },
  "steps_count": 5
}
```

| Field | Type | Description |
|-------|------|-------------|
| `workflow_id` | string | Unique workflow identifier |
| `version_id` | string | Workflow version |
| `input_schema` | object | Schema for workflow inputs |
| `steps_count` | number | Number of steps in workflow |

---

### workflow_fetched

Existing workflow was loaded (when `workflow_id` is provided in request).

```json
{
  "type": "workflow_fetched",
  "workflow_name": "Product Video Generator",
  "existing_steps": 3,
  "existing_definition": {...}
}
```

| Field | Type | Description |
|-------|------|-------------|
| `workflow_name` | string | Name of the workflow |
| `existing_steps` | number | Number of existing steps |
| `existing_definition` | object | Current workflow definition |

---

### workflow_built

Workflow definition was constructed.

```json
{
  "type": "workflow_built",
  "steps_count": 4,
  "definition": {
    "version": "v1",
    "input_schema": {...},
    "steps": [...]
  }
}
```

| Field | Type | Description |
|-------|------|-------------|
| `steps_count` | number | Number of steps |
| `definition` | object | Full workflow definition |

---

### workflow_updated

Workflow was pushed to the EachLabs API.

```json
{
  "type": "workflow_updated",
  "success": true,
  "workflow_id": "wf_abc123",
  "version_id": "v1",
  "definition": {...}
}
```

| Field | Type | Description |
|-------|------|-------------|
| `success` | boolean | Whether update succeeded |
| `workflow_id` | string | Workflow identifier |
| `version_id` | string | Version identifier |
| `definition` | object | Updated definition |

---

### execution_started

Workflow execution has begun.

```json
{
  "type": "execution_started",
  "execution_id": "exec_xyz789",
  "workflow_id": "wf_abc123"
}
```

| Field | Type | Description |
|-------|------|-------------|
| `execution_id` | string | Unique execution identifier |
| `workflow_id` | string | Workflow being executed |

---

### execution_progress

Progress update during workflow execution. Sent approximately every 5 seconds.

```json
{
  "type": "execution_progress",
  "step_id": "step2",
  "step_status": "completed",
  "output": "https://storage.eachlabs.ai/outputs/step2.png",
  "model": "nano-banana-pro",
  "completed_steps": 2,
  "total_steps": 5
}
```

| Field | Type | Description |
|-------|------|-------------|
| `step_id` | string | Current step identifier |
| `step_status` | string | Step status (running, completed, failed) |
| `output` | string | Step output URL (if available) |
| `model` | string | Model used for this step |
| `completed_steps` | number | Steps completed so far |
| `total_steps` | number | Total steps in workflow |

---

### execution_completed

Workflow execution finished successfully.

```json
{
  "type": "execution_completed",
  "execution_id": "exec_xyz789",
  "status": "completed",
  "output": "https://storage.eachlabs.ai/outputs/final.mp4",
  "all_outputs": {
    "step1": "https://storage.eachlabs.ai/outputs/step1.png",
    "step2": "https://storage.eachlabs.ai/outputs/step2.png",
    "step3": "https://storage.eachlabs.ai/outputs/final.mp4"
  }
}
```

| Field | Type | Description |
|-------|------|-------------|
| `execution_id` | string | Execution identifier |
| `status` | string | Final status (completed, failed) |
| `output` | string | Final output URL |
| `all_outputs` | object | All step outputs keyed by step_id |

---

### tool_call

Details of a tool being called. Useful for debugging and transparency.

```json
{
  "type": "tool_call",
  "name": "execute_model",
  "input": {
    "model_name": "nano-banana-pro",
    "inputs": {
      "prompt": "A beautiful woman portrait...",
      "aspect_ratio": "1:1"
    }
  }
}
```

| Field | Type | Description |
|-------|------|-------------|
| `name` | string | Tool name |
| `input` | object | Tool input parameters |

---

### message

Informational message from the agent.

```json
{
  "type": "message",
  "content": "Your video is being processed. This typically takes 2-3 minutes."
}
```

| Field | Type | Description |
|-------|------|-------------|
| `content` | string | Message content |

---

### complete

Final event with summary. Always sent when stream completes successfully.

```json
{
  "type": "complete",
  "task_id": "chat_1708345678901",
  "status": "ok",
  "tool_calls": [
    {"name": "search_models", "result": "success"},
    {"name": "get_model_details", "result": "success"},
    {"name": "execute_model", "result": "success", "model": "nano-banana-pro"}
  ],
  "generations": ["https://storage.eachlabs.ai/outputs/abc123.png"],
  "model": "nano-banana-pro"
}
```

| Field | Type | Description |
|-------|------|-------------|
| `task_id` | string | Unique task identifier |
| `status` | string | Final status (ok, awaiting_input, error) |
| `tool_calls` | array | Summary of all tool calls |
| `generations` | array | All generated output URLs |
| `model` | string | Primary model used |

**Status values:**
- `ok` - Completed successfully
- `awaiting_input` - Waiting for user clarification
- `error` - An error occurred

---

### error

An error occurred during processing.

```json
{
  "type": "error",
  "message": "Failed to generate image: Invalid aspect ratio"
}
```

| Field | Type | Description |
|-------|------|-------------|
| `message` | string | Error message |

---

## Event Flow Examples

### Simple Image Generation

```
thinking_delta → "I'll create a beautiful portrait..."
status → "Searching for models..."
status → "Getting model details..."
status → "Generating with nano-banana-pro..."
generation_response → {url: "https://..."}
complete → {status: "ok", generations: [...]}
[DONE]
```

### Clarification Flow

```
thinking_delta → "I see an image, but need to know what edit..."
clarification_needed → {question: "What edit?", options: [...]}
complete → {status: "awaiting_input"}
[DONE]
```

### Workflow Execution

```
thinking_delta → "Creating a multi-step workflow..."
status → "Searching for models..."
workflow_created → {workflow_id: "wf_123", steps_count: 5}
execution_started → {execution_id: "exec_456"}
execution_progress → {completed_steps: 1, total_steps: 5}
execution_progress → {completed_steps: 2, total_steps: 5}
execution_progress → {completed_steps: 3, total_steps: 5}
execution_progress → {completed_steps: 4, total_steps: 5}
execution_completed → {output: "https://...", all_outputs: {...}}
complete → {status: "ok"}
[DONE]
```

### Web Search

```
thinking_delta → "Let me search for current information..."
web_search_query → {query: "best AI models 2024"}
status → "Searching the web..."
web_search_citations → {citations: [...], count: 3}
text_response → "Based on current information..."
complete → {status: "ok"}
[DONE]
```

```