Phil Wang 59b1a77d4d be a bit more conservative and stick with layernorm (without bias) for now, given @borisdayma results https://twitter.com/borisdayma/status/1517227191477571585

2022-04-22 11:14:54 -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

cli.py

give time tokens a surface area of 2 tokens as default, make it so researcher can customize which unet actually is conditioned on image embeddings and/or text encodings

2022-04-20 10:04:47 -07:00

dalle2_pytorch.py

be a bit more conservative and stick with layernorm (without bias) for now, given @borisdayma results https://twitter.com/borisdayma/status/1517227191477571585

2022-04-22 11:14:54 -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

get ready for all the training related classes and functions

2022-04-12 09:54:50 -07:00

vqgan_vae.py

prepare for latent diffusion in the first DDPM of the cascade in the Decoder

2022-04-21 17:54:31 -07:00