# FLUX.2 Klein 9B LoRA Trainer

> FLUX.2 Klein 9B LoRA Trainer
Efficiently fine-tune custom FLUX.2 Klein 9B LoRA models using optimised training pipelines, flexible image format support, and a minimum of 16 GB of of VRAM for fast, high-quality LoRA training.

## Overview

- **Model ID**: `flux2-klein-9b-lora-trainer`
- **Category**: training
- **Provider**: modelslab
- **Source Type**: Open Source Model
- **Status**: active
- **Screenshot**: `https://assets.modelslab.ai/generations/54dfe855-cd75-4798-b78f-aaad0ef3b912.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/trainer/train`
- **Method**: POST

### Parameters

- **`images`** (required): Add miimum 15 images for good quality lora trained
  - Type: array

- **`trigger_word`** (required): Trigger word for the LoRA model
  - Type: text

- **`hf_username`** (optional): username for huggingface
  - Type: text

- **`hf_token`** (optional): hf token for the user
  - Type: text

- **`training_steps`** (optional): Recommended training steps are based on your dataset size. Training Steps = 100 to 150 × number of images. Example 10 images × 150 = 1500 steps. General Rule of Thumb: Fewer images = more steps per image. More images = fewer steps per image
  - Type: number (range: 500-3000)

- **`training_id`** (optional): Please enter the training ID
  - Type: text

## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://modelslab.com/api/v6/trainer/train \
  --header "Content-Type: application/json" \
  --data '{
    "key": "YOUR_API_KEY",
    "model_id": "flux2-klein-9b-lora-trainer",
    "trigger_word": "Pink",
    "training_steps": "2000"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://modelslab.com/api/v6/trainer/train",
    headers={
        "Content-Type": "application/json"
    },
    json={
        "key": "YOUR_API_KEY",
        "model_id": "flux2-klein-9b-lora-trainer",
        "trigger_word": "Pink",
        "training_steps": "2000"
    }
)

print(response.json())
```

### JavaScript

```javascript
fetch("https://modelslab.com/api/v6/trainer/train", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "key": "YOUR_API_KEY",
    "model_id": "flux2-klein-9b-lora-trainer",
    "trigger_word": "Pink",
    "training_steps": "2000"
  })
})
.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 "flux2-klein-9b-lora-trainer"                       # Find this model
modelslab models detail --id flux2-klein-9b-lora-trainer                    # Get model details
modelslab generate image --prompt "..." --model flux2-klein-9b-lora-trainer  # Generate with model
modelslab config set generation.default_model flux2-klein-9b-lora-trainer   # 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/modelslab/flux2-klein-9b-lora-trainer)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)