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

74 Open 405 Closed
74 Open 405 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

Not working on ComfyUI anymore
#620 opened Dec 23, 2024 by icemagno
1 of 2 tasks
CogvideoX1.5的图生视频在降低分辨率进行推理后，生成的视频画面下侧全是条纹，微调后并没有改善
#619 opened Dec 22, 2024 by DataAIPlayer
1 of 2 tasks
@zRzRzRzRzRzRzR
4
cogvideox微调的代码选择
#618 opened Dec 20, 2024 by AmazDeng
@zRzRzRzRzRzRzR
3
Can't use xformers in "THUDM/CogVideoX1.5-5B-I2V"
#617 opened Dec 20, 2024 by Eom-taeseon
@OleehyO
1
Human Evaluation Ambiguity
#616 opened Dec 19, 2024 by antragoudaras
@yzy-thu @OleehyO
2
咨询下1.5的帧数问题 sat
#614 opened Dec 18, 2024 by wmm-coding
1 of 2 tasks
@OleehyO
7
Missing pipe on samples, can't get to the decoder
#613 opened Dec 17, 2024 by AinzAkaOver
2 tasks done
@OleehyO
2
run interpolation based on cogVideoX1.5B (i2v model convert)
#606 opened Dec 16, 2024 by Suprhimp
@OleehyO
1
Cogs Video X 1.5 Finetuning Quick questions sat
#602 opened Dec 14, 2024 by ArEnSc
@zRzRzRzRzRzRzR
4
THUDM/cogvlm2-llama3-caption VRAM requirement OOM
#597 opened Dec 12, 2024 by wr0124
@zRzRzRzRzRzRzR
2
How to run CogVideoX1.5-5B-I2V as int8?
#596 opened Dec 11, 2024 by FurkanGozukara
@zRzRzRzRzRzRzR
3
Difference between DDIMScheduler and CogVideoXDDIMScheduler
#595 opened Dec 11, 2024 by DanahYatim
@yzy-thu @zRzRzRzRzRzRzR
After fine-tuning, the generated videos exhibited a significant grid pattern.
#590 opened Dec 9, 2024 by Junsheng121
@zRzRzRzRzRzRzR
4
About setting of VAE
#589 opened Dec 7, 2024 by txytju
@yzy-thu @zRzRzRzRzRzRzR
3
Missing Keys - Inference I2V - SAT
#586 opened Dec 6, 2024 by antragoudaras
1 of 2 tasks
@zRzRzRzRzRzRzR
4
What's the difference between CogVideoX1.5 and CogVideoX1.0 t2v version?
#582 opened Dec 5, 2024 by maozezhong
@zRzRzRzRzRzRzR
1
量化模型如何加载lora
#580 opened Dec 4, 2024 by mrlihellohorld
2 tasks
@zRzRzRzRzRzRzR
4
The VAE encoder is very slow
#579 opened Dec 4, 2024 by jiujing23333
@zRzRzRzRzRzRzR
Found black and white video when sampling CogVideoX1.5-5B 10s using code from huggingface.
#578 opened Dec 3, 2024 by DZY-irene
1 of 2 tasks
@zRzRzRzRzRzRzR
3
Could CogVideoX1.5-5B-I2V theoretically be adapted into a video-to-video model without training?
#577 opened Dec 3, 2024 by yiboz2001
@zRzRzRzRzRzRzR
1
Any plan for "Identity-Preserving T2V Generation"
#576 opened Dec 3, 2024 by JoshonSmith
The value of each transformerblock in the infer phase is particularly large
#573 opened Dec 3, 2024 by lgs00
1
Extrapolation with multiple images - UsingContextParallelEncoder3D class - SAT sat
#571 opened Dec 2, 2024 by antragoudaras
@zRzRzRzRzRzRzR
2
The performance of the cogvideo1.5-I2V model shows a significant difference between SAT and Diffusers.
#570 opened Dec 2, 2024 by lovejing0306
1 of 2 tasks
8
Using t2v Cogvideox1.5-5B model, the videos generated with the prompts on the homepage are completely different, and the top and bottom of the videos are the same (repeating parts of the video)
#566 opened Dec 2, 2024 by lgao-matax
1 of 2 tasks
@zRzRzRzRzRzRzR
3
ProTip! Follow long discussions with comments:>50.