Research paper for text-guided SVG generation using diffusion
Top 74.7% on sourcepulse
SVGDreamer is a CVPR 2024 paper implementing a diffusion-based approach for text-guided SVG generation. It targets researchers and artists seeking to synthesize high-quality vector graphics from textual descriptions, offering control over style and editing capabilities.
How It Works
SVGDreamer utilizes a diffusion model to generate SVG paths. It employs a two-stage process: first, a Sketch-Inference-and-Vector-Editing (SIVE) stage for initial shape generation and refinement, followed by a Vector-SVG-Path-Diffusion (VPSD) stage to produce the final SVG output. This approach aims to balance synthesis quality with vector graphic editing potential.
Quick Start & Requirements
bash script/install.sh
or use the provided Docker script bash script/run_svgdreamer_docker.sh
.diffuser.download=True
in conf/config.yaml
.enable_xformers=True
is recommended for faster optimization. state.mprec='fp16'
can reduce GPU memory usage.Highlighted Details
skip_sive
, token_ind
, result_path
, and x.vpsd.t_schedule
.Maintenance & Community
The project is associated with the CVPR 2024 paper. Links to community channels or roadmaps are not explicitly provided in the README.
Licensing & Compatibility
Limitations & Caveats
The README mentions a "TODO" list, indicating ongoing development. Specific limitations or known bugs are not detailed.
3 months ago
1 week