Phil Wang 77141882c8 complete vit-vqgan from https://arxiv.org/abs/2110.04627

2022-04-26 17:20:47 -07:00

..

data

bring in the simple tokenizer released by openai, but also plan on leaving room for custom tokenizer with yttm

2022-04-12 09:23:17 -07:00

__init__.py

refactor blurring training augmentation to be taken care of by the decoder, with option to downsample to previous resolution before upsampling (cascading ddpm). this opens up the possibility of cascading latent ddpm

2022-04-22 11:09:17 -07:00

attention.py

nevermind, it could be working, but only when i stabilize it with the feedforward layer + tanh as proposed in vit-vqgan paper (which will be built into the repository later for the latent diffusion)

2022-04-26 12:43:31 -07:00

cli.py

some outlines to the eventual CLI endpoint

2022-04-24 09:27:15 -07:00

dalle2_pytorch.py

be able to turn off warning for use of LazyLinear by passing in text embedding dimension for unet

2022-04-26 11:42:46 -07:00

tokenizer.py

bring in the simple tokenizer released by openai, but also plan on leaving room for custom tokenizer with yttm

2022-04-12 09:23:17 -07:00

train.py

bring in the exponential moving average wrapper, to get ready for training

2022-04-25 19:24:13 -07:00

vqgan_vae.py

complete vit-vqgan from https://arxiv.org/abs/2110.04627

2022-04-26 17:20:47 -07:00