Svgdreamer

🚀 SVGDreamer

SVGDreamer is an advanced text - to - SVG generation model. It uses a multi - particle optimization approach to create high - quality vector graphics, generating multiple SVG variants simultaneously for diverse and creative outputs.

🚀 Quick Start

SVGDreamer offers two ways to generate SVG images. You can either make a direct API call or use the Inference Client.

Direct API Call

import requests

API_URL = "https://api-inference.huggingface.co/models/jree423/svgdreamer"
headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

output = query({
    "inputs": "a majestic eagle soaring through clouds",
    "parameters": {
        "n_particle": 6,
        "num_iter": 1000,
        "guidance_scale": 7.5,
        "style": "iconography",
        "width": 224,
        "height": 224,
        "seed": 42
    }
})

Using the Inference Client

from huggingface_hub import InferenceClient

client = InferenceClient("jree423/svgdreamer")
result = client.post(
    json={
        "inputs": "a cyberpunk cityscape at night",
        "parameters": {
            "n_particle": 4,
            "style": "pixel_art",
            "guidance_scale": 8.0
        }
    }
)

✨ Features

• Multi - Particle Generation: Simultaneously creates multiple SVG variants.
• Style Control: Supports various artistic styles such as iconography, pixel art, sketch, and painting.
• High Quality: Produces detailed and aesthetically pleasing vector graphics.
• Flexible Parameters: Provides extensive customization options for fine - tuning the output.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

The basic usage examples are shown in the "Quick Start" section above, including direct API call and using the Inference Client.

Advanced Usage

You can adjust the parameters according to your specific needs. For example, increasing the num_iter parameter can improve the quality of the generated SVG, but it will also take longer.

# Example of advanced usage with more iterations
import requests

API_URL = "https://api-inference.huggingface.co/models/jree423/svgdreamer"
headers = {"Authorization": "Bearer YOUR_HF_TOKEN"}

def query(payload):
    response = requests.post(API_URL, headers=headers, json=payload)
    return response.json()

output = query({
    "inputs": "a beautiful castle in the mountains",
    "parameters": {
        "n_particle": 8,
        "num_iter": 2000,
        "guidance_scale": 8.5,
        "style": "painting",
        "width": 448,
        "height": 448,
        "seed": 123
    }
})

📚 Documentation

Parameters

Output Format

The model returns a list of JSON objects, one for each particle, containing:

• particle_id: Unique identifier for the particle
• svg: The generated SVG content as a string
• svg_base64: Base64 encoded SVG for easy transmission
• prompt: The input text prompt
• style: The style used for generation
• parameters: The parameters used for generation

Styles

• Iconography: Clean, minimalist vector graphics suitable for icons and logos. Example: "a simple house icon".
• Pixel Art: Retro - style graphics with pixelated aesthetics. Example: "a pixel art character".
• Sketch: Hand - drawn style with organic lines and artistic flair. Example: "a sketch of a mountain landscape".
• Painting: Rich, painterly style with complex color gradients. Example: "an oil painting of a sunset".

Examples

• Nature Scenes: "a forest with tall pine trees", "ocean waves crashing on rocks", "a field of sunflowers under blue sky".
• Characters and Objects: "a friendly robot character", "a vintage bicycle", "a magical wizard casting spells".
• Abstract Art: "geometric patterns in bright colors", "flowing organic shapes", "mandala design with intricate details".

🔧 Technical Details

• Base Model: Stable Diffusion 2.1
• Framework: PyTorch + Diffusers
• Vector Rendering: DiffVG (differentiable vector graphics)
• Optimization: Multi - particle VPSD (Vector Particle - based Score Distillation)
• Parallel Processing: Simultaneous optimization of multiple SVG representations

📄 License

This model is released under the MIT License.

Citation

@inproceedings{xing2024svgdreamer,
  title={SVGDreamer: Text Guided SVG Generation with Diffusion Model},
  author={Xing, XiMing and others},
  booktitle={CVPR},
  year={2024}
}