Skip to content

Issues: kohya-ss/musubi-tuner

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

33 Open 44 Closed
33 Open 44 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

Training samples broken with 2025-02-26 commit
#106 opened Feb 27, 2025 by Enyakk
Tutorial on best practices for training video loras (hunyuan example)
#105 opened Feb 27, 2025 by paul-lupu
1
Sample data
#103 opened Feb 26, 2025 by Ishihara-Masabumi
AttributeError: 'Config' object has no attribute 'define_bool_state'
#102 opened Feb 26, 2025 by Ishihara-Masabumi
support WanX 2.1?
#101 opened Feb 26, 2025 by JoshonSmith
1
Frame selection question
#99 opened Feb 25, 2025 by paul-lupu
1
Training Hunyuan Video Checkpoint Finetuning
#98 opened Feb 24, 2025 by aperire
4
xdit multi gpu
#94 opened Feb 21, 2025 by mr-lab
Any plans to support the first released (Skyreels)I2V model based on Hunyuan?
#93 opened Feb 21, 2025 by shanque56666
3
What can I try if my loss isn't coming down?
#92 opened Feb 20, 2025 by jnz86
22
Support for loading a smaller model for sample generation?
#91 opened Feb 20, 2025 by jnz86
Cannot offload / swap blocks. RuntimeError: "fill cpu" not implemented for Float8_efm3fn
#90 opened Feb 18, 2025 by jnz86
8
loss can't decay during training hunyuan lora
#89 opened Feb 18, 2025 by qingyuan18
5
Support for prompts text file input for multi-video-generation
#87 opened Feb 17, 2025 by glmcdona
1
Cosine LR decay doesn't seem to work
#81 opened Feb 10, 2025 by paul-lupu
Per-epoch loss computation over just the epoch instead of snapshot of total average
#79 opened Feb 10, 2025 by largestack
Adding Metadata to .MP4 File
#77 opened Feb 10, 2025 by GarbageHaus
2
distributed training across multiple machines
#74 opened Feb 6, 2025 by zzk88862
1
Can the model generated through LoRA training (using hv_train_network.py) be directly used for inference (hv_generate_video.py) without running merge_lora.py?
#71 opened Feb 2, 2025 by JamesTensor
Artifiacts and pixlated outpot
#70 opened Feb 1, 2025 by abozahran
3
convert_lora.py fails on Lycoris LoKr
#68 opened Jan 30, 2025 by Enyakk
2
Training produced lora with zero effect
#66 opened Jan 28, 2025 by vladislav-kostin
4
--split_attn increases training speed, contrary to docs
#65 opened Jan 26, 2025 by xmodo99
3
double block training
#64 opened Jan 26, 2025 by elen07zz
1
deepspeed support
#62 opened Jan 26, 2025 by lovejing0306
ProTip! no:milestone will show everything without a milestone.