Open Reproduction Effort to reproduce MUSE

Open-muse is a project to openly reproduce the transformer-based MUSE text-to-image model. The open-muse repo contains the model implementation, training code and everything related to training. All the artefacts of this project, such as the training checkpoints and final models will be uploaded to this organization.

Training Logs:

All training logs can be found in this W&B Project

Steps:

1. Setup the codebase and train a class-conditional model on imagenet.
2. Conduct text2image experiments on CC12M.
3. Train improved VQGANs models.
4. Train the full (base-256) model on LAION + COYO.
5. Train the full (base-512) model on LAION + COYO.

Weekly Log

...