Skip to content

Commit

Permalink
add some out link resources in readme
Browse files Browse the repository at this point in the history
  • Loading branch information
CIntellifusion committed May 18, 2024
1 parent 3f655f1 commit fbbe556
Showing 1 changed file with 22 additions and 2 deletions.
24 changes: 22 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
@@ -45,7 +45,7 @@ for further details please refer to `./UnoncditionalDiffusion/experiments.pptx`
- [x] train on mnist
- [ ] diffusion on other latent space: text , audio , mesh , etc.

## 实现计划
## Implementation Plan

基于`UnconditionalDiffusion/main.py`采用相同的dataset,类似的Trainer设置。但是将scheduler,models(unet,vit),和vae分开。

@@ -55,7 +55,7 @@ VAE的部分follow其他实现,写成first_stage_condition。



# Task 3Conditional Diffusion
# Task 3 Conditional Diffusion

- [ ] pretrained text model for condition
- [ ] different condition type: vanilla , token , cross attention etc.
@@ -73,5 +73,25 @@ VAE的部分follow其他实现,写成first_stage_condition。



# Other Resources for starting Diffusion

[DDPM implementation1](https://zhuanlan.zhihu.com/p/617895786)

[Course Level Diffusion Project: sast2023](https://github.com/Kevin-thu/sast2023-cv?tab=readme-ov-file)

- provide a latent diffusion base on Pytorch Lightning
- implement core functions yourself

[DiffusionFastForward: Train Diffusion from scratch](https://github.com/mikonvergence/DiffusionFastForward)

- provides some training costs record
- some other resources









0 comments on commit fbbe556

Please sign in to comment.