bmaltais / kohya_ss

bmaltais/kohya_ss Issues

dreambooth lora extraction = bad results.
Updated 10 days ago
Could anyone help me qq?
Updated 13 days ago
MultipleInvalid: extra keys not allowed @ data['datasets'][0]['subsets'][1]['is_reg']
Updated 13 days ago
Multi GPU training not working
Updated 14 days ago
I'm going to use the 4090 to fine-tune the large model of SDXL but I keep saying cuda is insufficient when I drive bisz to 1.
Updated 15 days ago2
path with spaces error
Updated 15 days ago1
How to train LORA with textEncoder 1 only. I get sdxl_train_network.py: error: unrecognized arguments: --train_text_encoder --learning_rate_te2=0"
Updated 16 days ago1
new SD3 branch train error
Updated 17 days ago20
Strange [Errno 13]. I think it's my fault.
Updated 17 days ago3
Cache latents error
Closed 17 days ago1
any way to disable scheduled huber loss
Updated 18 days ago4
does sdxl lora training train both text encoders or only 1?
Updated 18 days ago3
SD# Not seeing any samples
Updated 18 days ago2
Is it possible to train a LoRA model on a CPU? Has anyone successfully done this?
Updated 20 days ago2
An error occurs when running the second line of gui.bat
Updated 20 days ago2
Can't train for some reason
Updated 20 days ago
Is SD3 training available?
Updated 22 days ago14
Support for LORA Training
Updated 22 days ago11
[feature request] Kolors training
Updated 22 days ago1
Finetuning SDXL with TE2 set to 0, but TE2 is still training
Closed a month ago9
ImportError: cannot import name 'train_util' from 'library'
Closed 24 days ago4
Multi Concept, Multi Resolution, Multi Regularzation image training?
Updated a month ago
AttributeError: 'DistributedDataParallel' object has no attribute 'text_model'
Updated a month ago2
How to train LORA with multiple GPUs
Updated a month ago5
Is there a way to hard code the config file in Lora training?
Updated a month ago12
Python3.10 required but Debian "Bookworm" 12.5 only has Python3.11
Updated a month ago2
Feature Request: model name = WANDB-run name
Closed a month ago4
Dreambooth extration with DoRA
Closed a month ago1
dreamboth checkpoint save error
Closed a month ago3
RuntimeError: The size of tensor a (8) must match the size of tensor b (6) at non-singleton dimension 3
Updated a month ago2
Stable Diffusion 3
Updated a month ago25
how to uninstall kohya_ss completely.
Closed a month ago3
how to use Accelerate Lora tab to select which gpu ID to use
Closed a month ago10
change command Print for easy formatting and run in terminal
Closed a month ago3
when loading saved Preset, Learning Rate always auto-fills
Updated a month ago5
Docker Container Approach -- Permission issues for generating BLIP captioning
Closed a month ago3
Conflict between venv configuration and conda in Linux environment
Closed a month ago1
Cannot use sdxl fine tune
Closed a month ago2
Is there a way to train SD3 with LoRA in free Colab?
Closed a month ago1
bug Adaptive noise scale from JSON not load or not update GUI
Updated a month ago2
bug in apply settings Noise offset type
Updated a month ago3
voluptuous.error.MultipleInvalid: extra keys not allowed @ data['settings'] why?
Updated a month ago1
Cannot start DoRa training due to error
Updated a month ago6
How to extract LyCORIS keep small size by good effect.
Updated a month ago
controlnet lllite-RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 0 but got size 16 for tensor number 1 in the list.
Closed 2 months ago
IMPORTANT: You are using gradio version 4.26.0, however version 4.29.0 is available, please upgrade.
Closed 2 months ago1
No AVX CPU (former mining rig) - workaround (?)
Closed 2 months ago4
Error with accelerate site package - unknown keys
Updated 2 months ago1
LORA training does not start, it keeps crashing - W socket.cpp:663] [c10d] The client socket has failed to connect to [DESKTOP-413GD2B]:12345
Closed 2 months ago4
Nothing pops up when I click start training
Closed 2 months ago