Skip to content

Issues: PKU-YuanGroup/Open-Sora-Plan

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

209 Open 88 Closed
209 Open 88 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

为什么需要在算生成质量的指标的时候，进行resale和crop 呢？
#452 opened Sep 22, 2024 by aleeyang
Potential bug of sequential parallel training for i2v models
#451 opened Sep 19, 2024 by jinjinw
inference speed
#450 opened Sep 19, 2024 by yja1
1
support newer diffusers version
#447 opened Sep 18, 2024 by yuanzhi-zhu
1
[bug] potential CPU memory leak OOM
#445 opened Sep 17, 2024 by spacegoing
6
想学习【文生视频】快加学习交流群
#444 opened Sep 17, 2024 by km1994
[Bug]? Not CFG latent_model_input Instead of latents?
#442 opened Sep 16, 2024 by GloryyrolG
1
Training the vae fails to add the number of frames to 29
#441 opened Sep 12, 2024 by Catcher-o
1
sp加速训练策略和非sp策略的疑问
#438 opened Sep 9, 2024 by windIsMyHeart
1
关于训练方法和数据集切分问题？
#437 opened Sep 9, 2024 by xiaohutongxue-sunny
1
Train Iterations for I2V
#434 opened Sep 6, 2024 by GloryyrolG
Train with Ckpts with Different Frames
#433 opened Sep 6, 2024 by GloryyrolG
1
Image to video not adopt SVD's image to video?
#431 opened Sep 5, 2024 by trouble-maker007
Best practices for images to video generation？
#430 opened Sep 5, 2024 by trouble-maker007
OSError: LanguageBind/Open-Sora-Plan-v1.2.0 does not appear to have a file named diffusion_pytorch_model.bin.
#429 opened Sep 4, 2024 by DZY-irene
Where can I find the parameters for the v1.2 model that generates the best results
#428 opened Sep 4, 2024 by DZY-irene
2
Image2Video Mask value Not as expected
#427 opened Sep 3, 2024 by xesdiny
What's the version of the open-sora model reported in Report 1.2?
#424 opened Sep 3, 2024 by vanche
1
Parallel Inference using xDiT
#417 opened Aug 30, 2024 by feifeibear
The amount of training data used to train the video generation model?
#415 opened Aug 29, 2024 by trouble-maker007
1
what plan of VAE in next version? any news?
#414 opened Aug 28, 2024 by laohur
1
t2v stage3 training
#413 opened Aug 28, 2024 by CCchenxiaoxue
2
[Bug] sp_size is not handled by Collate and T2V_Dataset
#412 opened Aug 28, 2024 by spacegoing
Can Not Use Attention Maps Padding
#411 opened Aug 28, 2024 by spacegoing
29x480p checkpoint seems broken
#410 opened Aug 27, 2024 by helia95
1
ProTip! Follow long discussions with comments:>50.