|
|
| CARVIEW |
Example generated vectors
VectorFusion generates vector graphics from diverse captions. Search through SVGs in our gallery.
Infinitely scalable assets
Vector graphics are compact but can be scaled to arbitrary size while staying sharp. Caption: "a train. minimal flat 2d vector icon. lineal color. on a white background. trending on artstation."
One-stage text-to-SVG generation
We optimize vector graphics by optimizing an image-text loss based on Score Distillation Sampling. VectorFusion uses an inverse graphics approach, enabled by the DiffVG differentiable SVG renderer.
Generating 128 SVG paths from scratch.
Fine-tuning for better quality and speed
VectorFusion also supports a more efficient and higher quality multi-stage setting. First, our method samples raster images from the Stable Diffusion text-to-image diffusion model. VectorFusion then traces those samples automatically with LIVE. However, these samples are often difficult to convert to vector graphics, dull, or don't reflect all the details of the text. Fine-tuning with Score Distillation Sampling improves vibrancy and consistency with the text.
Generating 64 SVG paths, initialized from a diffusion sample.
Pixel art
By restricting SVG paths to be squares on a grid following Pixray, VectorFusion can generate a retro video game pixel art style.
Pixel art generated with VectorFusion, initialized by pixelating a diffusion sample.
Sketches
It's simple to extend our method to support text-to-sketch generation. We start by drawing 16 random strokes, then optimize our latent Score Distillation Sampling loss to learn an abstract line drawing that reflects the user-supplied text.
Sketches generated with VectorFusion.
Citation
@article{jain2022vectorfusion,
author = {Jain, Ajay and Xie, Amber and Abbeel, Pieter},
title = {VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models},
journal = {arXiv},
year = {2022},
}