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

68 Open 334 Closed
68 Open 334 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

CogVideoX1.5-5B-I2V how to finetune
#525 opened Nov 19, 2024 by YLongJin
Question about 3d patchify
#524 opened Nov 19, 2024 by Blueskyvvvvv
1.5版本的I2v模型如何支持768*1360
#521 opened Nov 19, 2024 by gongleii
4
T2V inference getting bad results
#520 opened Nov 19, 2024 by YanzuoLu
1 of 2 tasks
4
OOM after the video finished generating but before it could create an output - new I2V model with updated diffusers
#519 opened Nov 19, 2024 by sdes21
2 tasks
Why not use higher compression ratio in VAE?
#518 opened Nov 19, 2024 by culeao
THUDM/CogVideoX-5b-I2V is producing jibberish output
#517 opened Nov 18, 2024 by nitinmukesh
1 of 2 tasks
5
ValueError: Trying to set a tensor of shape torch.Size([3072, 128]) in "weight" (which has shape torch.Size([3072, 16, 2, 2])), this looks incorrect.
#516 opened Nov 18, 2024 by DennisFaucher
1 of 2 tasks
3
CogVideoX1.5-5B-SAT全量微调失败，位置编码部分对不上
#514 opened Nov 18, 2024 by hl0737
1 of 2 tasks
size mismatch for model.diffusion_model.mixins.patch_embed.proj.weight: copying a param with shape torch.Size([3072, 256]) from checkpoint, the shape in current model is torch.Size([3072, 128]).
#513 opened Nov 18, 2024 by echoanran
4
ImportError: cannot import name 'ActivationCasting' from 'torchao.float8.inference' in cli_demo_quantization.py
#509 opened Nov 17, 2024 by nitinmukesh
1 of 2 tasks
@zRzRzRzRzRzRzR
1
Assertion Error: world_size % group_num == 0 When finetune cogv1.5-i2v on distributed environment
#506 opened Nov 15, 2024 by hrcheng98
1 of 2 tasks
CUDA error: too many resources requested for launch
#505 opened Nov 15, 2024 by Junsheng121
@zRzRzRzRzRzRzR
CogvideX-Interpolation with CogVideoX1.5-5B-SAT or CogVideoX-5b-I2V
#504 opened Nov 15, 2024 by Suprhimp
2
When will the CogVideo1.5 tech report released
#503 opened Nov 14, 2024 by AmemiyaYuko
@zRzRzRzRzRzRzR
1
accelerate Lr-scheduler issue
#502 opened Nov 14, 2024 by LakshyaChaudhry
2 tasks
@zRzRzRzRzRzRzR
How to generate lower resolution videos with CogVideoX1.5-5B?
#499 opened Nov 13, 2024 by hitachinsk
1 of 2 tasks
@zRzRzRzRzRzRzR
prompt for I2V
#498 opened Nov 13, 2024 by TZLNC
While generating a 10-second video with CogVideoX-1.5, encountered (OOM) on machine with 80 GB of GPU memory.
#493 opened Nov 12, 2024 by DZY-irene
2 tasks done
@zRzRzRzRzRzRzR
6
V1.5版本生成视频闪烁
#492 opened Nov 12, 2024 by DidiD1
1 of 2 tasks
@zRzRzRzRzRzRzR
How to finetune with multi resolution?
#491 opened Nov 12, 2024 by trouble-maker007
@zRzRzRzRzRzRzR
2
Inference failed with custom finetuned model
#490 opened Nov 12, 2024 by jinhaaya
1 of 2 tasks
KeyError: 'ops' when full fine-tuning CogVideoX1.5-5B-SAT
#489 opened Nov 12, 2024 by JWargrave
1 of 2 tasks
@zRzRzRzRzRzRzR
1
Preparing dataset for training CogVideo1.5 I2V
#486 opened Nov 11, 2024 by Closertodeath
1 of 2 tasks
@zRzRzRzRzRzRzR
4
sampling is different between diffusers and sat ?
#482 opened Nov 11, 2024 by lith0613
@zRzRzRzRzRzRzR
1
ProTip! Find all open issues with in progress development work with linked:pr.