---
license: openrail++
language:
- en
tags:
- stable-diffusion-xl
- text-to-image
- art
- fine-art
inference: true
---

<style>
  .artisan-title {
    font-family: Arial, sans-serif;
    font-size: 3em;
    text-align: center;
    color: #000;
    text-transform: uppercase;
    letter-spacing: 0.1em;
    padding: 0.5em 0;
    margin: 0;
  }
  
  .image-grid {
    display: flex;
    flex-wrap: wrap;
    margin-bottom: 20px;
  }

  .image-grid img {
    width: 50%;
    height: auto;
    display: block;
    margin: 0 !important; /* Override any default margins */
    padding: 0;
  }

  .image-grid .wide-image {
    width: 100%;
  }

  /* Override Hugging Face's default styling */
  .prose :where(img):not(:where([class~=not-prose],[class~=not-prose] *)) {
    margin-top: 0 !important;
    margin-bottom: 0 !important;
  }
</style>

<h1 class="artisan-title">Artisan XL</h1>

<div class="image-grid">
  <img src="images/Picasso.webp" alt="Square image 1">
  <img src="images/Repin.webp" alt="Square image 2">
  <img src="images/Van Gogh.webp" alt="Square image 3">
  <img src="images/Vermeer.webp" alt="Square image 4">
  <img src="images/long_van_gogh.webp" alt="Wide image" class="wide-image">
</div>


# Artisan XL: Unparalleled Fine Art Generation

Artisan XL is a state-of-the-art text-to-image model that pushes the boundaries of AI-generated fine art. Trained on an extensive dataset of 200,000 high-resolution oil paintings, this model offers unparalleled style fidelity for a wide range of artistic styles throughout human history.

## Key Features

- Trained for 1200 A100 hours on 8 A100 GPUs
- Captioned with Claude Sonnet 3.5 for precise style understanding
- Exceptional style fidelity for artists like Picasso, Van Gogh, Rembrandt, Klimt, Repin, Serov, Kandinsky, and many more
- Supports all basic SDXL tools and community techniques

## Usage Tips

1. **Prompt Engineering**: We recommend using long, detailed prompts with weighting. Ideally, generate prompts using Claude Sonnet or Haiku for best results.
2. **Negative Prompts**: Use empty or very short negative prompts. Common negative keywords include: `simplified, rough, blurred, crude, imperfections, sketch`
3. **Settings**: 
   - Works well with guidance limiter
   - Recommended CFG scale: 3.0-5.5

## Model Variants

1. **Full Model**: Complete SDXL fine-tuned model
2. **LoRA Variant**: 
   - Linear and Conv modules
   - Rank 128
   - Provides 95% of full model capabilities

### Multi Aspect Resolution

This model supports generating images at the following dimensions:

| Dimensions        | Aspect Ratio    |
|-------------------|-----------------|
| `1024 x 1024`     | 1:1 Square      |
| `1152 x 896`      | 9:7             |
| `896 x 1152`      | 7:9             |
| `1216 x 832`      | 19:13           |
| `832 x 1216`      | 13:19           |
| `1344 x 768`      | 7:4 Horizontal  |
| `768 x 1344`      | 4:7 Vertical    |
| `1536 x 640`      | 12:5 Horizontal |
| `640 x 1536`      | 5:12 Vertical   |

### Acknowledgements

The development and release of Artisan XL would not have been possible without the invaluable contributions and support from the following individuals and organizations:

- **[Kohya SS](https://github.com/kohya-ss)**: For training scripts.

## Limitations

While Artisan XL offers exceptional capabilities in fine art generation, it's important to note:

1. The model specializes in fine art styles and may not perform as well for other genres.
2. Results can vary based on prompt quality and settings.
3. As with all AI models, occasional unexpected outputs may occur.

## Contact

For any inquiries, collaborations, or custom training requests, please contact:
grigory@theartisan.ai

We're excited to see what you create with Artisan XL! Happy art-making!