issues
search
FoundationVision
/
OmniTokenizer
OmniTokenizer: one model and one weight for image-video joint tokenization.
https://www.wangjunke.info/OmniTokenizer/
MIT License
234
stars
5
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
error when initializing the OmniTokenizer
#20
dongzhuoyao
opened
3 weeks 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
1 month ago
0
Training Collapse
#18
JewelChen2019
opened
2 months ago
0
Considering multi window size
#17
daiyixiang666
opened
2 months ago
0
Native support for multiple resolutions?
#16
Jason3900
opened
2 months ago
0
maybe bugs in loss backward?
#15
shinshiner
opened
2 months ago
3
two tiny problems
#14
dreamofuture
opened
2 months ago
0
The provided checkpoint is trained by this code?
#13
shinshiner
closed
2 months ago
1
Wrong reshape order in PEG still exists
#12
dreamofuture
closed
3 months ago
2
Wrong reshape order in PEG
#11
dreamofuture
closed
3 months ago
1
cuda segment fault in PEG->forward->self.dsconv(x)
#10
dreamofuture
closed
3 months ago
0
Question about the gan_feat_loss
#9
hyc9
closed
3 months ago
1
NaN value in loss
#8
wusize
opened
3 months ago
3
Inquiry about the version of pytorch lightning
#7
hyc9
closed
3 months ago
3
Could you please adde a script for demo video reconstruction?
#6
BingliangLi
closed
3 months ago
1
It takes a **HUGE** memory
#5
lucasjinreal
closed
3 months ago
2
Will the tokenize image tokens able to do understanding?
#4
lucasjinreal
closed
3 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
3 months ago
1
Considered doing VQ with LFQ?
#2
iamlockelightning
closed
3 months ago
1
Update README.md
#1
eltociear
closed
3 months ago
0