lucidrains/parti-pytorch
A PyTorch implementation of Google's Parti text-to-image model using pure transformer architecture with ViT VQGan VAE.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of Google’s Parti, a pure attention-based text-to-image neural network. It includes working training code for ViT VQGan VAE used as the image tokenizer, and supports generation of images from text prompts using transformer-based architectures. The implementation enables both training the VAE encoder-decoder and running inference with the full Parti model.
Frequently asked
- What is lucidrains/parti-pytorch?
- A PyTorch implementation of Google's Parti text-to-image model using pure transformer architecture with ViT VQGan VAE.
- Is parti-pytorch open source?
- Yes — lucidrains/parti-pytorch is open source, released under the MIT license.
- What language is parti-pytorch written in?
- lucidrains/parti-pytorch is primarily written in Python.
- How popular is parti-pytorch?
- lucidrains/parti-pytorch has 537 stars on GitHub.
- Where can I find parti-pytorch?
- lucidrains/parti-pytorch is on GitHub at https://github.com/lucidrains/parti-pytorch.