Skip to content

Issues: Vchitect/Latte

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

51 Open 23 Closed
51 Open 23 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

Question: evaluate the FVD question Further information is requested
#80 opened May 23, 2024 by Alienge
5
the code of variant 4 enhancement New feature or request
#79 opened May 20, 2024 by pangpangjy
1
how to place and preprocess these datasets question Further information is requested
#78 opened May 8, 2024 by renyuanzhe
6
Question: model code and design choices question Further information is requested
#77 opened Apr 30, 2024 by mrartemevmorphic
1
视频帧率 question Further information is requested
#76 opened Apr 30, 2024 by fenghe12
1
question on t2v model training question Further information is requested
#75 opened Apr 28, 2024 by diffusion-lover
1
有关时长的问题。 question Further information is requested
#74 opened Apr 27, 2024 by LinQianhe02grey
3
About video VAE question Further information is requested
#73 opened Apr 23, 2024 by Darius-H
1
Is autoregression possible? enhancement New feature or request
#71 opened Apr 16, 2024 by zhaohm14
3
FaceForensics数据集 question Further information is requested
#67 opened Mar 31, 2024 by likeatingcake
2
Some weights of AutoencoderKL were not initialized from the model checkpoint at /path/to/Latte/t2v_required_models/ and are newly initialized because the shapes did not match: duplicate This issue or pull request already exists
#66 opened Mar 27, 2024 by likeatingcake
2
CUDA out of memory question Further information is requested
#64 opened Mar 25, 2024 by likeatingcake
4
image_size = [256,512] question Further information is requested
#62 opened Mar 24, 2024 by likeatingcake
4
RuntimeError: "LayerNormKernelImpl" not implemented for 'Half' duplicate This issue or pull request already exists
#60 opened Mar 21, 2024 by likeatingcake
1
What is the difference between Latte and ViViT? question Further information is requested
#59 opened Mar 21, 2024 by Leeeshuz
2
Why choose these datasets and why not compare with pika, SVD or Gen2? question Further information is requested
#57 opened Mar 12, 2024 by qiuhaining
1
Extra key in ucf101.pt question Further information is requested
#56 opened Mar 11, 2024 by wang-muhan
7
About resume checkpoint question Further information is requested
#55 opened Mar 9, 2024 by kaiw7
2
About Training Speed question Further information is requested
#54 opened Mar 8, 2024 by ZekaiGalaxy
5
diffusion noise modify question Further information is requested
#53 opened Mar 7, 2024 by ErwinKC
1
t2v只支持16帧吗？我改成更多比如32帧就啥都看不到了 enhancement New feature or request
#50 opened Mar 5, 2024 by epcsoft
1
如何复现主页展示的t2v效果？ question Further information is requested
#49 opened Mar 5, 2024 by HRain1016
3
Train code of t2v？ question Further information is requested
#48 opened Mar 5, 2024 by kings-rgb
2
About evaluation question Further information is requested
#47 opened Mar 5, 2024 by kaiw7
3
t2i代码疑问 question Further information is requested
#46 opened Mar 5, 2024 by LiuhanChen-github
1
ProTip! Add no:assignee to see everything that’s not assigned.