Jaret Burkett 3b1f7b0948 Allow user to set the attention backend. Add method to recomver from the occasional OOM if it is a rare event. Still exit if it ooms 3 times in a row.		2025-09-27 08:56:15 -06:00
..
data_transfer_object	Initial support for qwen image edit plus	2025-09-24 11:39:10 -06:00
keymaps	…
models	Initial support for qwen image edit plus	2025-09-24 11:39:10 -06:00
optimizers	Added a basic torch profiler that can be used in config during development to find some obvious issues.	2025-06-17 13:03:39 -06:00
orig_configs	…
samplers	WIP on mean flow loss. Still a WIP.	2025-06-12 08:00:51 -06:00
timestep_weighing	…
util	Add stepped loss type	2025-09-22 15:50:12 -06:00
__init__.py	…
accelerator.py	…
assistant_lora.py	…
basic.py	…
buckets.py	…
civitai.py	…
clip_vision_adapter.py	…
config.py	…
config_modules.py	Allow user to set the attention backend. Add method to recomver from the occasional OOM if it is a rare event. Still exit if it ooms 3 times in a row.	2025-09-27 08:56:15 -06:00
control_generator.py	…
cuda_malloc.py	…
custom_adapter.py	More work on mean flow loss. Moved it to an adapter. Still not functioning properly though.	2025-06-16 07:17:35 -06:00
data_loader.py	Initial support for finetuning qwen image. Will only work with caching for now, need to add controls everywhere.	2025-08-21 16:41:17 -06:00
dataloader_mixins.py	Remove dropout from cached text embeddings even if used specifies it so blank prompts are not cached.	2025-09-26 11:50:53 -06:00
dequantize.py	…
ema.py	…
embedding.py	…
esrgan_utils.py	…
extension.py	Added support for finetuning OmniGen2.	2025-06-25 13:58:16 -06:00
guidance.py	…
image_utils.py	…
inversion_utils.py	…
ip_adapter.py	…
job.py	…
kohya_lora.py	…
kohya_model_util.py	…
layers.py	…
llvae.py	…
logging_aitk.py	…
lora_special.py	Add ability to train a full rank LoRA. (experimental)	2025-09-09 07:36:25 -06:00
lorm.py	…
losses.py	…
lycoris_special.py	…
lycoris_utils.py	…
metadata.py	…
network_mixins.py	Add ability to train a full rank LoRA. (experimental)	2025-09-09 07:36:25 -06:00
optimizer.py	…
paths.py	Switch to unified text encoder for wan models. Pred for 2.2 14b	2025-08-14 10:07:18 -06:00
photomaker.py	…
photomaker_pipeline.py	…
pipelines.py	…
pixel_shuffle_encoder.py	…
print.py	…
progress_bar.py	…
prompt_utils.py	Preperation for audio	2025-09-02 07:26:50 -06:00
reference_adapter.py	…
resampler.py	…
sampler.py	WIP on mean flow loss. Still a WIP.	2025-06-12 08:00:51 -06:00
saving.py	…
scheduler.py	…
sd_device_states_presets.py	…
stable_diffusion_model.py	Initial support for qwen image edit plus	2025-09-24 11:39:10 -06:00
style.py	…
timer.py	…
train_pipelines.py	…
train_tools.py	…
unloader.py	Fix issue with fake text encoder unload	2025-08-14 09:33:44 -06:00