From cc30676a3f609f653b1310c18918a6d08b8b0760 Mon Sep 17 00:00:00 2001 From: Phil Wang Date: Wed, 13 Apr 2022 18:34:09 -0700 Subject: [PATCH] lengthen todo --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 4f0d9aa..c0065a9 100644 --- a/README.md +++ b/README.md @@ -317,6 +317,7 @@ For the layperson, no worries, training will all be automated into a CLI tool, a - [ ] figure out all the current bag of tricks needed to make DDPMs great (starting with the blur trick mentioned in paper) - [ ] train on a toy task, offer in colab - [ ] add attention to unet - apply some personal tricks with efficient attention +- [ ] figure out the big idea behind latent diffusion and what can be ported over ## Citations