aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-19 17:54:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #17 from kashif/patch-2

Browse Source 
added diffusion-gan thoughts
This commit is contained in:
Phil Wang
2022-04-20 12:10:26 -07:00
committed by GitHub
parent faebf4c8b8 1d8f37befe
commit 8cc9016cb0
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -413,6 +413,7 @@ Offer training wrappers
- [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] 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) - [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]) (figure out if latent diffusion + cascading ddpm can be used in conjunction) - [ ] 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)
- [ ] Extend diffusion head to use diffusion-gan (potentially using lightweight-gan) to speed up inference
- [ ] become an expert with unets, cleanup unet code, make it fully configurable, port all learnings over to https://github.com/lucidrains/x-unet - [ ] 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 - [ ] train on a toy task, offer in colab