Skip to content

Issues: kohya-ss/sd-scripts

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

547 Open 467 Closed
547 Open 467 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

--blocks_to_swap is supported on linux?
#1656 opened Sep 29, 2024 by al-swaiti
⚡Add Support for LoRA Training on Flux-Dev2Pro Models
#1652 opened Sep 29, 2024 by sashaok123
1
Dataset maker sd1.5 - wd-tagger module stopped working on colab
#1645 opened Sep 27, 2024 by nevo993
Regarding the Multi-Level Caption
#1643 opened Sep 26, 2024 by sdbds
3
Kohya_ss native trainer colab broken yesterday. Captured before/ after install log. Jax, Key array.
#1641 opened Sep 25, 2024 by SarahPeterson2854
1
Was "Validation Loss" ever successfully implemented?
#1638 opened Sep 24, 2024 by mostlyhuman
Specify blocks to Train w/ Finetuning?
#1636 opened Sep 24, 2024 by setothegreat
1
FLUX LoRA Training - Text Encoder active training indicated when it should be disabled with --network_train_unet_only
#1634 opened Sep 22, 2024 by Enyakk
2
FLUX: Bleeding?
#1633 opened Sep 22, 2024 by DarkAlchy
Issue Reminder
#1630 opened Sep 21, 2024 by lynrayy
how to use flux full-finetune safetensors in diffusers?
#1626 opened Sep 21, 2024 by neuron-party
Strange behavior with --network_args parameter
#1624 opened Sep 21, 2024 by codecomputation
TypeError: get_cosine_schedule_with_warmup() got an unexpected keyword argument 'num_decay_steps'
#1618 opened Sep 19, 2024 by AndreR
3
[Feature Request] Decouple linear1 and linear2 Flux layers in network_args
#1613 opened Sep 19, 2024 by EricBCoding
5
Flux merge tool does not properly handle LoRA keys from AI-Toolkit when merging w/ Flux.dev model - All keys "Unused" / Unchanged model file outputted
#1612 opened Sep 18, 2024 by CCpt5
9
Flux fine-tune text encoder rate is too high; need to be able to set separately
#1607 opened Sep 17, 2024 by BelieveDiffusion
2
poolFD failed error when caching latents for flux finetuning
#1601 opened Sep 15, 2024 by huxian0402
4
Error loading fbgemm.dll
#1597 opened Sep 14, 2024 by AndreR
1
How to convert a safetensors(finetuned sdxl model) to diffusers dir format?
#1596 opened Sep 13, 2024 by laolongboy
FLUX training for 8GB VRAM?
#1595 opened Sep 12, 2024 by cocktailpeanut
12
error when use deepspeed for FLUX.1 fine-tuning
#1591 opened Sep 11, 2024 by huxian0402
flux lora training does not start
#1589 opened Sep 10, 2024 by nim00e
3
Flux textual_inversion
#1588 opened Sep 10, 2024 by aiXander
9
*Possible important fixes for some issues with flux
#1584 opened Sep 10, 2024 by DriveHabits
[Feature request] --caption_dropout_rate when cache te output enhancement New feature or request
#1583 opened Sep 10, 2024 by gesen2egee
ProTip! Adding no:label will show everything without a label.