Repository Issue Activity (beta)

#3604 Kontext caption tab delete callback allows unauthenticated arbitrary file deletion (hidden-field trust + path traversal)

#3603 HuggingFace token written in cleartext to setup.log on plain GUI startup

#3602 No "Train U-Net Only" option for Anima training

#3600 Consider using pre-built Flash Attention kernels via `kernels`

#3470 How to install for AMD ROCm on Linux?

#3275 Update via Stability Matrix fails and makes previous versions not work

#3590 ValueError: Unsupported attention mode: None

#3598 UnicodeEncodeError: 'charmap' codec can't encode characters in position 19-22: character maps

#3591 Bad keys in Anima finetune output model

#567 ModuleNotFoundError: No module named 'torch._dynamo'

#3587 v26.0.0 - UnicodeEncodeError: 'charmap' codec can't encode characters in position 19-22: character maps to <undefined>

#1400 Blip Captioning not working

#1236 Error while running BLIP captioning in Kohya_ss version kohya_ss-21.8.3

#3435 Incorporate More Meaningful/Useful Diagnostics

#3374 [Help] "No data found" error when training model – train_data_dir issue

#2428 ’not found data‘error when training

#3181 Kohya_ss LoRA Training Error: No Data Found Despite Correct Folder Setup

#3004 ERROR No data found. Please verify arguments (train_data_dir must be the train_network.py:212 parent of folders with images) /

#2771 Flux LoRA resumes wrong epochs

#3380 Questions about continuing training

#2520 49 sec/it on 4090

#3200 Severe Training Slowdown – xFormers Ignored, SDPA Used Instead

#3467 How to speed up training

#3257 Large speed decrease with newest version

#3378 The problem with training speed