# Russian Blue Cat - flux-v1.0

> # Russian Blue Cat - Flux Dev LoRA v1.0**Initial Release** - Photorealistic Russian Blue cat generation model## Version Information- **Version**: 1.0- **Release Date**: 2025-10-16- **Status**: Stable- **Model Type**: Flux Dev LoRA## What's New in v1.0 **Initial Release**- First public release of the Russian Blue cat LoRA model- 1000 training images across multiple resolutions- Optimized for photorealistic output- No trigger word required - natural language prompting## Model Specifications### Architecture- **Base Model**: Flux Dev- **Model Type**: LoRA- **Transformer**: float8- **Text Encoder**: float8- **Linear Rank**: 64- **Data Type**: bf16### Training Configuration- **Training Steps**: 7000- **Gradient Accumulation**: 1- **Batch Size**: 1- **Timestep Type**: Sigmoid- **Timestep Bias**: Balanced- **Optimizer**: AdamW8bit### Dataset- **Total Images**: 1000- **Resolutions**: 1024×1024, 768×768, 512×512- **Caption Format**: Individual `.txt` files per image## Usage Guide### Basic Usage**No trigger word required** - Simply describe what you want:```russian blue cat, photorealistic photographyRussian blue cat portrait, professional lighting, detailed furRussian blue cat sitting on windowsill, natural light, shallow depth of field```### Recommended Tags```russian blue, cat, photorealistic, photography, detailed fur, green eyes```### Optimal Settings for v1.0| Parameter | Recommended Value | Range || ------------------ | ----------------- | ------------------------- || **LoRA Weight** | 0.8-0.9 | 0.7-1.0 || **CFG Scale** | 5.0 | 3.5-7.0 || **Sampling Steps** | 25 | 20-30 || **Sampler** | Euler a | Euler a / DPM++ 2M Karras |### Example Prompts**Portrait Style**:```russian blue cat portrait, photorealistic, professional photography,detailed blue-grey fur, bright green eyes, studio lighting, sharp focus```**Environmental Shots**:```russian blue cat sitting on a velvet cushion, natural window light,photorealistic, elegant pose, detailed whiskers```**Close-up Detail**:```russian blue cat face close-up, photorealistic photography,detailed fur texture, green eyes, soft lighting, shallow depth of field```## Version-Specific Notes### Strengths- Excellent photorealistic quality- Accurate breed characteristics (blue-grey coat, green eyes)- Good detail in fur texture- Works well with natural lighting descriptions- Stable across different resolutions### Known Characteristics- Best results at LoRA weight 0.8-0.9- Responds well to photography-style prompts- Optimized for realistic lighting scenarios- Works best with descriptive prompts about pose and environment### Tips for Best Results1. **Lighting**: Include lighting descriptions (natural light, studio lighting, etc.)2. **Detail Level**: Mention specific details (fur texture, eye color, whiskers)3. **Photography Terms**: Use photography vocabulary (shallow depth of field, bokeh, sharp focus)4. **Environment**: Describe the setting or background5. **Weight**: Start at 0.8 and adjust based on your needs## Technical DetailsThis v1.0 release uses float8 precision for both transformer and text encoder to optimize memory usage while maintaining high-quality output. The model was trained over 7000 steps using the AdamW8bit optimizer with a balanced sigmoid timestep bias for efficient convergence and stable results.The diverse dataset spanning three resolution tiers (1024px, 768px, 512px) ensures the model performs well across different output sizes.## Compatibility- **Base Model**: Flux Dev- **Recommended**: Use with Flux Dev base model for best results- **ComfyUI**: Compatible with standard LoRA loader nodes- **A1111/Forge**: Compatible with built-in LoRA support## File Information- **File Size**: ~TBD MB- **Format**: SafeTensors- **Precision**: bf16## Future VersionsThis is the initial release. Future versions may include:- Fine-tuning based on community feedback- Additional training on specific poses or scenarios- Optimization for different art styles- Extended dataset for improved variety## Support & FeedbackFound an issue or have suggestions for v2.0? Please provide feedback to help improve future releases.## LicensePlease specify your license here.## Credits**Model Training**: wangkanai**Release Date**: 2025-10-16**Version**: 1.0---For general model information and specifications, see [readme-model.md](readme-model.md)

## Overview

- **Model ID**: `russian-blue-cat-flux-v1-0`
- **Category**: flux
- **Provider**: modelslab
- **Source Type**: Open Source Model
- **Status**: model_ready
- **Screenshot**: `https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ec175f05-6ef2-4239-9a2d-50913005b042/original=true/106284963.mp4`

## 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): prompt help in image generation
  - Type: textarea
  - Example: Enter prompt

- **`model_id`** (required): Enter model_id that can help in image generation
  - Type: text
  - Example: Enter model_id here

- **`lora_model`** (required): 
  - Type: multiple_models

- **`width`** (required): width of the image 
  - Type: number (range: 512-1024)

- **`height`** (required): height of the image 
  - Type: number (range: 512-1024)

- **`negative_prompt`** (optional): Negative prompt help in avoid things that you do not want in image 
  - Type: textarea
  - Example: Enter negative prompt that you do not want see in image

- **`scheduler`** (optional): 
  - Type: select (options: DPM++ 2M, DPM++ SDE, Euler, Euler a)

- **`guidance_scale`** (optional): 
  - Type: number (range: 1-10)

## 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": "russian-blue-cat-flux-v1-0",
    "prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro",
    "width": "1024",
    "height": "1024",
    "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
    "scheduler": "DPMSolverMultistepScheduler",
    "guidance_scale": "7.5"
  }'
```

### 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": "russian-blue-cat-flux-v1-0",
        "prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro",
        "width": "1024",
        "height": "1024",
        "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
        "scheduler": "DPMSolverMultistepScheduler",
        "guidance_scale": "7.5"
    }
)

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": "russian-blue-cat-flux-v1-0",
    "prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro",
    "width": "1024",
    "height": "1024",
    "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
    "scheduler": "DPMSolverMultistepScheduler",
    "guidance_scale": "7.5"
  })
})
.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 "russian-blue-cat-flux-v1-0"                       # Find this model
modelslab models detail --id russian-blue-cat-flux-v1-0                    # Get model details
modelslab generate image --prompt "..." --model russian-blue-cat-flux-v1-0  # Generate with model
modelslab config set generation.default_model russian-blue-cat-flux-v1-0   # 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/russian-blue-cat-flux-v1-0)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)