aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-23 11:34:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

todo

Browse Source
This commit is contained in:
Phil Wang
2022-04-26 09:56:54 -07:00
committed by GitHub
parent 9878be760b
commit bdf5e9c009
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -594,7 +594,7 @@ Once built, images will be saved to the same directory the command is invoked
- [x] build out latent diffusion architecture, with the vq-reg variant (vqgan-vae), make it completely optional and compatible with cascading ddpms - [x] build out latent diffusion architecture, with the vq-reg variant (vqgan-vae), make it completely optional and compatible with cascading ddpms
- [x] for decoder, allow ability to customize objective (predict epsilon vs x0), in case latent diffusion does better with prediction of x0 - [x] for decoder, allow ability to customize objective (predict epsilon vs x0), in case latent diffusion does better with prediction of x0
- [x] use attention-based upsampling https://arxiv.org/abs/2112.11435 - [x] use attention-based upsampling https://arxiv.org/abs/2112.11435
- [ ] spend one day cleaning up tech debt in decoder - [ ] abstract interface for CLIP adapter class, so other CLIPs can be brought in - use inheritance just this once for sharing logic between decoder and prior network ddpms
- [ ] 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
- [ ] copy the cascading ddpm code to a separate repo (perhaps https://github.com/lucidrains/denoising-diffusion-pytorch) as the main contribution of dalle2 really is just the prior network - [ ] copy the cascading ddpm code to a separate repo (perhaps https://github.com/lucidrains/denoising-diffusion-pytorch) as the main contribution of dalle2 really is just the prior network
- [ ] transcribe code to Jax, which lowers the activation energy for distributed training, given access to TPUs - [ ] transcribe code to Jax, which lowers the activation energy for distributed training, given access to TPUs