showlab/D-AR

the official repo for "D-AR: Diffusion via Autoregressive Models"

39
/ 100
Emerging

This project offers a novel way for AI researchers and practitioners to generate high-quality images. By converting image pixels into sequences of tokens, it allows for image creation using autoregressive models, similar to how text is generated. Researchers working on new image generation techniques can use this to explore a different paradigm, inputting existing image datasets and outputting models capable of generating new images.

135 stars.

Use this if you are an AI researcher or machine learning engineer looking to experiment with a new methodology for image generation, specifically bridging diffusion models with autoregressive architectures.

Not ideal if you are an end-user simply looking for a tool to generate images without deep technical involvement in model architecture and training.

AI research Image generation Machine learning engineering Generative models Deep learning
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 4 / 25

How are scores calculated?

Stars

135

Forks

2

Language

Python

License

MIT

Last pushed

Jan 29, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/showlab/D-AR"

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