Skip to content

Issues: THUDM/CogVideo

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

58 Open 484 Closed
58 Open 484 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

XDIT multi GPUs inference code runs OOM with 24 frames
#695 opened Feb 4, 2025 by danielajisafe
Question: concat_image and ops
#694 opened Feb 4, 2025 by yjhong89
Different fine-tuning modules
#693 opened Feb 4, 2025 by yjhong89
does it support multiple gpu
#691 opened Jan 28, 2025 by BASSEM45325
1 of 2 tasks
@zRzRzRzRzRzRzR
4
Inference with the new trained weight of i2v model?
#690 opened Jan 28, 2025 by zero1778
@zRzRzRzRzRzRzR
Video Reconstruction based on Inversion
#689 opened Jan 27, 2025 by JonathanLi19
@zRzRzRzRzRzRzR
3
How to load the sft finetuned model based on the diffusers version.
#688 opened Jan 27, 2025 by zyhbili
@zRzRzRzRzRzRzR
1
cogvideo 1.0全参数 diffuser 微调代码
#687 opened Jan 25, 2025 by linwenzhao1
@zRzRzRzRzRzRzR
2
Attention Mask for T5 / T2V Attention
#686 opened Jan 24, 2025 by karan-dalal
1 of 2 tasks
@zRzRzRzRzRzRzR
update will suitable for uoload pretrained model
#684 opened Jan 23, 2025 by renrenzsbbb
@zRzRzRzRzRzRzR
1
CogVideoX-5B-I2V生成更長秒數影片問題
#680 opened Jan 21, 2025 by Labibibidu
@zRzRzRzRzRzRzR
10
lateset Diffuser: Inference T2V meets patch_size_t error in CogVideoX-2B/5B
#676 opened Jan 20, 2025 by onevfall
2 tasks done
@OleehyO
2
Training-free acceleration for CogVideoX
#675 opened Jan 20, 2025 by LiewFeng
@zRzRzRzRzRzRzR
Issue in VAE compression
#674 opened Jan 17, 2025 by zhang-haojie
@zRzRzRzRzRzRzR
CogVideoX1.5-5B-I2V 4090 24g Cannot run
#673 opened Jan 17, 2025 by hjj-lmx
2 tasks done
@zRzRzRzRzRzRzR
7
Getting following error on google colab
#667 opened Jan 13, 2025 by smktech9
1 of 2 tasks
@OleehyO
1
Giving Transformers Layer cannot be '' error
#666 opened Jan 13, 2025 by smktech9
1 of 2 tasks
@OleehyO
2
CogVideoX and CogvideoX1.5 video quality
#664 opened Jan 13, 2025 by cdfan0627
@OleehyO
2
prepare_rotary_positional_embeddings training and inference are different
#663 opened Jan 13, 2025 by cdfan0627
@OleehyO
2
Theoritically, what limits the number of frames the model can inferrence?
#662 opened Jan 13, 2025 by HWT-WalterHu
@yzy-thu
2
Training video size
#661 opened Jan 13, 2025 by cdfan0627
@OleehyO
5
latent padding training and inference different
#660 opened Jan 12, 2025 by cdfan0627
@OleehyO
2
Reason for 49 frames (extra split for interpolation)
#659 opened Jan 12, 2025 by karan-dalal
2 tasks
@yzy-thu @zRzRzRzRzRzRzR @tengjiayan20
4
why 5b vae use a small latent scaling factor?
#658 opened Jan 12, 2025 by chengmengli06
@tengjiayan20
模型转为diffusers有精度损失
#655 opened Jan 11, 2025 by linwenzhao1
2 tasks
@zRzRzRzRzRzRzR
4
ProTip! Find all open issues with in progress development work with linked:pr.