Welcome to PyTorch-SVGRender documentation!
Pytorch-SVGRender is the go-to library for state-of-the-art differentiable rendering methods for image vectorization.
PyTorch-SVGRender originated within academic research and has since undergone extensive development and consolidation through practical implementation, driven by the overarching objective of propelling advancements in the realm of vector graphics rendering.
Note
This project is under active development.
Installation
- Installation
How to install the PyTorch-SVGRender.
Table of Contents
- DiffVG: Differentiable Vector Graphics Rasterization for Editing and Learning
Differentiable Vector Graphics Rasterization.
- CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
Task: Text-to-SVG
- StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation
Task: Text-and-Img-to-SVG
- LIVE: Towards Layer-wise Image Vectorization
Task: Img-to-SVG
- CLIPFont: Texture Guided Vector WordArt Generation
Task: Text-and-Glyph-to-Glyph
- CLIPasso: Semantically-Aware Object Sketching
Task: Img-to-Sketch
- CLIPascene: Scene Sketching with Different Types and Levels of Abstraction
Task: Img-to-Sketch
- VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models
Task: Text-to-SVG
- DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
Task: Text-to-Sketch
- Word-As-Image: Word-As-Image for Semantic Typography
Task: Text-and-Glyph-to-Glyph
- SVGDreamer: Text Guided SVG Generation with Diffusion Model
Task: Text-to-SVG
API Documentation
- API
TODO
About Us
- Authors:
Ximing Xing and Juncheng Hu
- Contact:
- Organization:
- Status:
This is a “work in progress”
- Version:
1.0
- Copyright:
2024, Ximing Xing
- Licence:
This work is licensed under a Mozilla Public License Version 2.0