nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source 
Former-commit-id: a1cc0b26a3b156d7708e8df0cfe42aad33b1c946
This commit is contained in:
lb203
2024-03-07 13:45:01 +08:00
committed by GitHub
parent c521999f80
commit f507bb4947
1 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6 -3
View File
@@ -38,6 +38,7 @@ Project stages:
## Todo
#### Setup the codebase and train a unconditional model on landscape dataset
- [x] Fix typo & Update readme. 🤝 Thanks to [@mio2333](https://github.com/mio2333), [@CreamyLong](https://github.com/CreamyLong), [@chg0901](https://github.com/chg0901)
- [x] Setup repo-structure.
- [x] Add Video-VQGAN model, which is borrowed from [VideoGPT](https://github.com/wilson1yan/VideoGPT).
- [x] Support variable aspect ratios, resolutions, durations training on [DiT](https://github.com/facebookresearch/DiT).
@@ -47,14 +48,15 @@ Project stages:
- [x] Add VAE model, which is borrowed from [Stable Diffusion](https://github.com/CompVis/latent-diffusion).
- [x] Joint dynamic mask input with VAE.
- [ ] Make the codebase ready for the cluster training. Add SLURM scripts.
- [x] Refactor VideoGPT. 🤝 Thanks to [@qqingzheng](https://github.com/qqingzheng), [@luo3300612](https://github.com/luo3300612)
- [x] Add sampling script.
- [ ] Incorporating [SiT](https://github.com/willisma/SiT).
- [ ] Incorporating [SiT](https://github.com/willisma/SiT). 🤝 Thanks to [@khan-yin](https://github.com/khan-yin)
#### Train models that boost resolution and duration
- [ ] Add [PI](https://arxiv.org/abs/2306.15595) to support out-of-domain size.
- [x] Extract offline feature.
- [x] Add frame interpolation model.
- [x] Add super resolution model.
- [x] Add frame interpolation model. 🤝 Thanks to [@yunyangge](https://github.com/yunyangge)
- [x] Add super resolution model. 🤝 Thanks to [@Linzy19](https://github.com/Linzy19)
- [x] Add accelerate to automatically manage training.
- [ ] Joint training with images.
- [ ] Incorporating NaViT.
@@ -73,6 +75,7 @@ Project stages:
- [x] Add xformers.
- [x] Support mixed precision training.
- [x] Add gradient checkpoint.
- [ ] Support for ReBased and Ring attention. 🤝 Thanks to [@kabachuha](https://github.com/kabachuha)
- [ ] Train using the deepspeed engine.
#### Control model with more condition