StyleGAN3 CLIP-based guidance

StyleGAN3 + CLIP

StyleGAN3 + inversion + CLIP

This repo is a collection of Jupyter notebooks made to easily play with StyleGAN3[^1] and CLIP[^2] for a text-based guided image generation.

Both notebooks are heavily based on this notebook, created by nshepperd (thank you!).

Special thanks too to Katherine Crowson for coming up with many improved sampling tricks, as well as some of the code.

[^1]: StyleGAN3 was created by NVIDIA. Here is the original repo.

[^2]: CLIP (Contrastive Language-Image Pre-Training) is a multimodal model made by OpenAI. For more information head over here.

Feel free to suggest any changes! If anyone has any idea what license should this repo use, please let me know.