lucidrains/autoregressive-diffusion-pytorch
A PyTorch implementation of autoregressive diffusion models for image generation.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of the Autoregressive Image Generation architecture from the paper ‘without Vector Quantization’. It includes models for both sequential data and image generation treated as sequences of patches, along with training utilities. The implementation supports flow matching as an alternative approach.
Frequently asked
- What is lucidrains/autoregressive-diffusion-pytorch?
- A PyTorch implementation of autoregressive diffusion models for image generation.
- Is autoregressive-diffusion-pytorch open source?
- Yes — lucidrains/autoregressive-diffusion-pytorch is open source, released under the MIT license.
- What language is autoregressive-diffusion-pytorch written in?
- lucidrains/autoregressive-diffusion-pytorch is primarily written in Python.
- How popular is autoregressive-diffusion-pytorch?
- lucidrains/autoregressive-diffusion-pytorch has 438 stars on GitHub.
- Where can I find autoregressive-diffusion-pytorch?
- lucidrains/autoregressive-diffusion-pytorch is on GitHub at https://github.com/lucidrains/autoregressive-diffusion-pytorch.