LTH14/JiT
A PyTorch implementation of JiT, a minimalist transformer-based diffusion model for high-resolution image generation.
Not currently ranked — collecting fresh signals.
star history
JiT is a pixel-space diffusion model that denoises images directly in pixel space rather than using latent compression. This PyTorch re-implementation reproduces the research paper “Back to Basics: Let Denoising Generative Models Denoise” by Li et al., originally implemented in JAX/TPU. The model supports training on ImageNet at 256x256 resolution with transformer architectures such as JiT-B/16.
Frequently asked
- What is LTH14/JiT?
- A PyTorch implementation of JiT, a minimalist transformer-based diffusion model for high-resolution image generation.
- Is JiT open source?
- Yes — LTH14/JiT is open source, released under the MIT license.
- What language is JiT written in?
- LTH14/JiT is primarily written in Python.
- How popular is JiT?
- LTH14/JiT has 2.4k stars on GitHub.
- Where can I find JiT?
- LTH14/JiT is on GitHub at https://github.com/LTH14/JiT.