yinboc/dito

Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"

33
/ 100
Emerging

This project helps machine learning researchers efficiently process and represent large collections of images. It takes image folders, like those used for ImageNet, and transforms them into compact, meaningful numerical 'tokens'. This output is ideal for training other image generation models more quickly and with less computational power, benefiting researchers focused on cutting-edge image synthesis and analysis.

166 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer working with large image datasets and need an efficient way to tokenize them for downstream generative models like latent diffusion models.

Not ideal if you are looking for an out-of-the-box solution for general image editing, classification, or directly generating images without further model training.

deep-learning image-generation machine-learning-research computer-vision generative-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

166

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Jan 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yinboc/dito"

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