Skip to content

Issues: FoundationVision/VAR

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

30 Open 52 Closed
30 Open 52 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Can you opensource the StyleGAN code when training Multi-scale VQ?
#90 opened Oct 22, 2024 by sunset-clouds
1
[New!] Try ImageFolder🚀 tokenizer for next-scale AR with shorter tokens length🔥, faster speed 🔥 and better FID🔥
#88 opened Oct 3, 2024 by lxa9867
1
Rejection sampling
#87 opened Sep 18, 2024 by wangf3014
Conflicting Instructions for computing FID
#86 opened Sep 15, 2024 by Kumbong
generate images with arbitrary resolutions
#84 opened Sep 1, 2024 by Leiii-Cao
Cannot reproduce results in Table 1, especially the IS score
#83 opened Aug 15, 2024 by adreamwu
1
How can I train VAR with my own data? Does the num_class parameter in VAR have any effect?
#82 opened Aug 14, 2024 by zhangqingwu
1
Question about the training dataset - tokenzier
#80 opened Aug 7, 2024 by Lucky-Light-Sun
How can i train this model by custom dataset
#79 opened Jul 19, 2024 by morestart
1
Weird/Inconsistency evaluation IS score.
#77 opened Jul 8, 2024 by ChenDRAG
3
we use VAR-CLIP train a TextToImage model on ImageNet,The result seems pretty good.
#75 opened Jul 3, 2024 by daixiangzi
3
About in-painting tasks
#74 opened Jun 30, 2024 by zhiyuanyou
1
Why multi-scale features partially shared a convolution network via PhiPartiallyShared
#73 opened Jun 18, 2024 by sunset-clouds
1
换个角度,ms codebbok是不是也可以等价于另一种latent diffusion?
#72 opened Jun 11, 2024 by YilanWang
1
Computation and Memory Consumption When Training Models
#71 opened Jun 10, 2024 by walking-shadow
for in/out painting
#70 opened Jun 7, 2024 by Youngwoo-git
Can not align FID with provided checkpoint
#69 opened Jun 6, 2024 by LiCHH
7
Finetuning on own data
#66 opened May 28, 2024 by LetsGoFir
1
T2I Generation
#64 opened May 22, 2024 by ucasyjz
3
There was no increase in speed after installing flash-attn and xformer.
#59 opened May 16, 2024 by kongwanbianjinyu
The 512 ckp?
#57 opened May 14, 2024 by FanqingM
2
Image reconstruction via Transformer.
#55 opened May 11, 2024 by minimini-1
1
Scalability to multimodal large language models?
#51 opened May 7, 2024 by DEBIHOOD
Can the training log be released?
#48 opened May 6, 2024 by daixiangzi
Training code for VAE
#28 opened Apr 19, 2024 by kl2004
22
ProTip! Updated in the last three days: updated:>2024-10-21.