yang-song/score_sde_pytorch

PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

49
/ 100
Emerging

This project helps researchers and machine learning practitioners generate high-quality, realistic images from scratch, or perform advanced image manipulation like inpainting or colorization. You provide a dataset of images, and the system learns to generate new, diverse images that look similar to the originals. This is primarily for those working with advanced image generation models.

2,089 stars. No commits in the last 6 months.

Use this if you need to generate high-fidelity images, explore new sampling algorithms for generative models, or implement conditional image generation tasks such as class-conditional generation, inpainting, or colorization.

Not ideal if you are looking for a simple, off-the-shelf image generator without needing to dive into the underlying model architectures or training processes.

image-generation computer-vision-research deep-generative-models image-synthesis AI-art
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

2,089

Forks

352

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jul 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yang-song/score_sde_pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.