FoundationVision OmniTokenizer issues

FoundationVision / OmniTokenizer

[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.

https://www.wangjunke.info/OmniTokenizer/

MIT License

263 stars 7 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

error when initializing the OmniTokenizer

#20 dongzhuoyao opened 2 months ago
2
The motion fluency of the reconstructed video is very poor, similar to the frame skipping effect of the original video.

#19 hyc9 opened 3 months ago
0
Training Collapse

#18 JewelChen2019 opened 4 months ago
0
Considering multi window size

#17 daiyixiang666 opened 4 months ago
0
Native support for multiple resolutions?

#16 Jason3900 opened 4 months ago
0
maybe bugs in loss backward?

#15 shinshiner opened 4 months ago
3
two tiny problems

#14 dreamofuture opened 4 months ago
0
The provided checkpoint is trained by this code?

#13 shinshiner closed 4 months ago
1
Wrong reshape order in PEG still exists

#12 dreamofuture closed 4 months ago
2
Wrong reshape order in PEG

#11 dreamofuture closed 4 months ago
1
cuda segment fault in PEG->forward->self.dsconv(x)

#10 dreamofuture closed 4 months ago
0
Question about the gan_feat_loss

#9 hyc9 closed 4 months ago
1
NaN value in loss

#8 wusize opened 4 months ago
3
Inquiry about the version of pytorch lightning

#7 hyc9 closed 5 months ago
3
Could you please adde a script for demo video reconstruction?

#6 BingliangLi closed 5 months ago
1
It takes a **HUGE** memory

#5 lucasjinreal closed 5 months ago
2
Will the tokenize image tokens able to do understanding?

#4 lucasjinreal closed 5 months ago
1
Similar to issue #2, would you like to compare this ckpt with stability's vqvae/vae and tencent's open-magvit2?

#3 StarCycle closed 5 months ago
1
Considered doing VQ with LFQ?

#2 iamlockelightning closed 5 months ago
1
Update README.md

#1 eltociear closed 5 months ago
0