From b8e8d3c16464d184bfaf464d9a54c04288bce5f9 Mon Sep 17 00:00:00 2001 From: Phil Wang Date: Wed, 20 Apr 2022 11:34:51 -0700 Subject: [PATCH] thoughts --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index df7c7ce..abf5087 100644 --- a/README.md +++ b/README.md @@ -412,7 +412,7 @@ Offer training wrappers - [x] add efficient attention in unet - [x] be able to finely customize what to condition on (text, image embed) for specific unet in the cascade (super resolution ddpms near the end may not need too much conditioning) - [x] offload unets not being trained on to CPU for memory efficiency (for training each resolution unets separately) -- [ ] build out latent diffusion architecture, make it completely optional (additional autoencoder + some regularizations [kl and vq regs]) +- [ ] build out latent diffusion architecture, make it completely optional (additional autoencoder + some regularizations [kl and vq regs]) (figure out if latent diffusion + cascading ddpm can be used in conjunction) - [ ] become an expert with unets, cleanup unet code, make it fully configurable, port all learnings over to https://github.com/lucidrains/x-unet - [ ] train on a toy task, offer in colab