Official implementation of Aligning Latent and Image Spaces to Connect the Unconnectable
Note: the tensorboard requirement is crucial, because otherwise upfirdn2d will not compile for some magical reason.
The project is based on https://github.com/NVlabs/stylegan2-ada-pytorch (but with difaugs disabled) I am not a lawyer, but I suppose that NVidia License applies to this project: https://nvlabs.github.io/stylegan2-ada-pytorch/license.html