metadata
language: en
license: mit
tags:
- vector-graphics
- svg
- text-to-image
- diffsketcher
pipeline_tag: text-to-image
widget:
- text: a beautiful mountain landscape
- text: a colorful sunset over the ocean
- text: a cute cat sitting on a windowsill
DiffSketcher - Vector Graphics Model
This repository contains the DiffSketcher model for generating vector graphics (SVG) from text prompts.
Model Description
DiffSketcher is a diffusion-based vector graphics generation model that creates high-quality SVG images from text descriptions. The model uses a combination of diffusion models and vector optimization techniques to produce clean, scalable vector graphics.
Usage
You can use this model through the Hugging Face Inference API:
import requests
API_URL = "https://api-inference.huggingface.co/models/jree423/diffsketcher"
headers = {"Authorization": "Bearer YOUR_API_TOKEN"}
def query(payload):
response = requests.post(API_URL, headers=headers, json=payload)
return response.json()
output = query({
"prompt": "a beautiful mountain landscape"
})
# Save the SVG output
with open("output.svg", "w") as f:
f.write(output["svg"])
Limitations
- The model may take some time to generate complex images
- The quality of the output depends on the clarity and specificity of the prompt
- Some complex concepts may not be rendered accurately
Citation
If you use this model in your research, please cite the original DiffSketcher paper:
@inproceedings{xing2023diffsketcher,
title={DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models},
author={Ximing Xing and Chuang Wang and Haitao Zhou and Jing Zhang and Qian Yu and Dong Xu},
booktitle={Advances in Neural Information Processing Systems},
year={2023}
}