Skip to content

Issues: FoundationVision/VAR

Beta
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

43 Open 107 Closed
43 Open 107 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

Decode intermediate steps
#162 opened May 8, 2025 by oskarjor
About rejection sampling
#161 opened May 6, 2025 by dt-3t
Question regarding d12 version
#160 opened Apr 29, 2025 by minhnn1
汇报代码中一个可能导致torch自动权重初始化失效的操作 bug Something isn't working enhancement New feature or request
#159 opened Apr 26, 2025 by yusijin02
请教：目前 FID 的计算结果无法复现
#156 opened Apr 5, 2025 by Ameis-god
The training command in Training Scripts doesn't work
#155 opened Apr 4, 2025 by LingyuLi-math
train time v. depth
#154 opened Apr 3, 2025 by andyxzhu
train.py文件中，验证集结果打印错误
#153 opened Apr 2, 2025 by Iron-head
请问该如何启用半精度训练的模式？
#152 opened Apr 2, 2025 by zhuzil
What is the minimum amount of memory needed to train this minimal model(d16)?
#151 opened Apr 2, 2025 by Zephyrose
Refining Previous Tokens discussion This doesn't seem right
#150 opened Mar 29, 2025 by matt-bendel
3
New work based on VAR in Image Restoration Research Third-party repositories or research which use VAR
#148 opened Mar 20, 2025 by quyp2000
1
请教高手：关于./model/basic_var.py 实现的SelfAttention的两个问题
#140 opened Feb 26, 2025 by mswwd
VQVAE Training Code
#133 opened Jan 23, 2025 by wojfran
Some doubts about quantization loss
#132 opened Jan 21, 2025 by xiaoShen110141
1
Transformer每个尺度的输入为什么是整个f_hat而不是前一个尺度的特征
#126 opened Jan 15, 2025 by Niax23
3
Training code for VQ-VAE is not reproducible
#125 opened Jan 14, 2025 by zelaki
Question on training code of vae
#123 opened Jan 10, 2025 by XiaomanWuu
6
is it make sense to try image loss in stage 2?
#122 opened Jan 9, 2025 by AlexzQQQ
5
progressive training
#118 opened Dec 27, 2024 by RohollahHS
Does the demo website still exists?
#117 opened Dec 22, 2024 by BlackTea-c
6
How to train the vqvae？
#114 opened Dec 20, 2024 by Longhzzz
4
question！
#111 opened Dec 17, 2024 by bxhsort
2
[New!] The 3D version of VAR is coming🔥. With 512-Byte code can represent and generate delicated geometry, with 2000× compression 🔥 and better F-score 🔥. Research Third-party repositories or research which use VAR
#107 opened Dec 13, 2024 by sparse-mvs-2
1
how to fine tune the model on my own dataset
#103 opened Dec 9, 2024 by 96-211
4
ProTip! no:milestone will show everything without a milestone.