# Krea-2-turbo Text to Image

> AI model for generating image content

## Overview

- **Model ID**: `krea-2-turbo`
- **Category**: image
- **Provider**: modelslab
- **Source Type**: Open Source Model
- **Status**: model_ready
- **Screenshot**: `https://assets.modelslab.ai/generations/c7144b17-55ef-4a8c-93a7-7555d9f45874.png`

## API Information

This model can be used via our HTTP API. See the API documentation and usage examples below.

### Endpoint

- **URL**: `https://modelslab.com/api/v6/images/text2img`
- **Method**: POST

### Parameters

- **`prompt`** (required): Describe the image you want to generate
  - Type: textarea
  - Example: Enter prompt

- **`negative_prompt`** (optional): Things to avoid in the generated image
  - Type: textarea
  - Example: Enter negative prompt

- **`height`** (required): The height of the image in pixels. Must be between 1024-1488 and divisible by 8. When set to 1488, width must be 1200 (1488x1488 is not supported).
  - Type: number (range: 1024-1488)

- **`width`** (required): The width of the image in pixels. Must be between 1024-1488 and divisible by 8. When set to 1488, height must be 1200 (1488x1488 is not supported).
  - Type: number (range: 1024-1488)

## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://modelslab.com/api/v6/images/text2img \
  --header "Content-Type: application/json" \
  --data '{
    "key": "YOUR_API_KEY",
    "model_id": "krea-2-turbo",
    "prompt": "create an ultra-realistic Korean street-fashion editorial portrait of the same young woman, preserving her facial identity. She stands beside a bold orange wall under bright natural sunlight, wearing an oversized pastel mint green structured blazer with matching high-waisted wide-leg trousers and a fitted dark brown cropped tube top. Style her with luxury silver statement earrings, layered necklaces, rings, and a decorative blazer chain. She has long sleek straight dark brown hair, flawless porcelain skin, soft glam makeup with nude matte lips, sharp brows, and a confident elegant expression. Relaxed pose with one hand against the wall. Clear blue sky, soft urban background, cinematic sunlight, vibrant orange and mint color contrast. Vogue Korea-inspired luxury street-style editorial, photorealistic, ultra-detailed fabric and skin texture, sharp focus, soft depth of field, premium color grading, 85mm lens, 8K.",
    "negative_prompt": "Low quality, blurry, bad anatomy, distorted face, bad hands, extra fingers, duplicate limbs, messy hair, duplicate accessories, oversaturated colors, cartoon, anime, CGI, watermark, logo, text, noise, unrealistic skin, low resolution",
    "height": "1488",
    "width": "1200"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://modelslab.com/api/v6/images/text2img",
    headers={
        "Content-Type": "application/json"
    },
    json={
        "key": "YOUR_API_KEY",
        "model_id": "krea-2-turbo",
        "prompt": "create an ultra-realistic Korean street-fashion editorial portrait of the same young woman, preserving her facial identity. She stands beside a bold orange wall under bright natural sunlight, wearing an oversized pastel mint green structured blazer with matching high-waisted wide-leg trousers and a fitted dark brown cropped tube top. Style her with luxury silver statement earrings, layered necklaces, rings, and a decorative blazer chain. She has long sleek straight dark brown hair, flawless porcelain skin, soft glam makeup with nude matte lips, sharp brows, and a confident elegant expression. Relaxed pose with one hand against the wall. Clear blue sky, soft urban background, cinematic sunlight, vibrant orange and mint color contrast. Vogue Korea-inspired luxury street-style editorial, photorealistic, ultra-detailed fabric and skin texture, sharp focus, soft depth of field, premium color grading, 85mm lens, 8K.",
        "negative_prompt": "Low quality, blurry, bad anatomy, distorted face, bad hands, extra fingers, duplicate limbs, messy hair, duplicate accessories, oversaturated colors, cartoon, anime, CGI, watermark, logo, text, noise, unrealistic skin, low resolution",
        "height": "1488",
        "width": "1200"
    }
)

print(response.json())
```

### JavaScript

```javascript
fetch("https://modelslab.com/api/v6/images/text2img", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "key": "YOUR_API_KEY",
    "model_id": "krea-2-turbo",
    "prompt": "create an ultra-realistic Korean street-fashion editorial portrait of the same young woman, preserving her facial identity. She stands beside a bold orange wall under bright natural sunlight, wearing an oversized pastel mint green structured blazer with matching high-waisted wide-leg trousers and a fitted dark brown cropped tube top. Style her with luxury silver statement earrings, layered necklaces, rings, and a decorative blazer chain. She has long sleek straight dark brown hair, flawless porcelain skin, soft glam makeup with nude matte lips, sharp brows, and a confident elegant expression. Relaxed pose with one hand against the wall. Clear blue sky, soft urban background, cinematic sunlight, vibrant orange and mint color contrast. Vogue Korea-inspired luxury street-style editorial, photorealistic, ultra-detailed fabric and skin texture, sharp focus, soft depth of field, premium color grading, 85mm lens, 8K.",
    "negative_prompt": "Low quality, blurry, bad anatomy, distorted face, bad hands, extra fingers, duplicate limbs, messy hair, duplicate accessories, oversaturated colors, cartoon, anime, CGI, watermark, logo, text, noise, unrealistic skin, low resolution",
    "height": "1488",
    "width": "1200"
  })
})
.then(response => response.json())
.then(data => console.log(data));
```

## Integration Options

### CLI

Install: `curl -fsSL https://modelslab.sh/install.sh | sh` or `brew install modelslab/tap/modelslab`

```bash
modelslab auth login                                    # Authenticate
modelslab models search "krea-2-turbo"                       # Find this model
modelslab models detail --id krea-2-turbo                    # Get model details
modelslab generate image --prompt "..." --model krea-2-turbo  # Generate with model
modelslab config set generation.default_model krea-2-turbo   # Set as default
```

- Website: https://modelslab.sh
- GitHub: https://github.com/ModelsLab/modelslab-cli

### MCP Servers (Model Context Protocol)

For Claude Code, Cursor, VS Code, Windsurf, and any MCP-compatible agent.

- Generation: `https://modelslab.com/mcp/v7` (API key auth, 23 tools)
- Agent Control Plane: `https://modelslab.com/mcp/agents` (Bearer token auth, 10 tools)

Claude Code config (`~/.claude/settings.json`):

```json
{
  "mcpServers": {
    "modelslab-v7": {
      "url": "https://modelslab.com/mcp/v7",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
```

- Documentation: https://docs.modelslab.com/mcp-web-api/overview

### Agent Skills

Install skill files directly into AI coding agents:

```bash
npx skills add modelslab/skills --all                          # All skills
npx skills add modelslab/skills --skill image-generation       # Specific skill
npx skills add modelslab/skills --all -a claude-code -a cursor # Target agents
```

- GitHub: https://github.com/ModelsLab/skills
- Documentation: https://docs.modelslab.com/agent-skills

### SDKs

- Python: `pip install modelslab`
- TypeScript: `npm install modelslab`
- PHP: `composer require modelslab/modelslab`
- Go: `go get github.com/modelslab/modelslab-go`
- Dart: `dart pub add modelslab`

## Links

- [Model Playground](https://modelslab.com/models/krea-2-turbo-text-to-image/krea-2-turbo)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)