ai-toolkit/toolkit
Jaret Burkett bfb373c8fa Prep for future breaking changes in newer versions of transformers library 2026-04-10 12:04:32 -06:00
..
audio Add support for ACE-Step 1.5 and ACE-Step 1.5 XL. Also added dataset captioning through the UI. (#785) 2026-04-09 15:02:03 -06:00
data_transfer_object Add support for ACE-Step 1.5 and ACE-Step 1.5 XL. Also added dataset captioning through the UI. (#785) 2026-04-09 15:02:03 -06:00
keymaps
memory_management Do not copy pin memory if it fails, just move 2025-11-17 18:04:00 +00:00
models Add support for ACE-Step 1.5 and ACE-Step 1.5 XL. Also added dataset captioning through the UI. (#785) 2026-04-09 15:02:03 -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 Added new timestep weighing strategy 2025-06-04 01:16:02 -06:00
util Add Mac OS support for Apple Silicon (#770) 2026-03-30 09:37:47 -06:00
__init__.py
accelerator.py Fallback unwrapping logic if fails 2025-05-21 03:10:33 -06:00
assistant_lora.py
basic.py Add Mac OS support for Apple Silicon (#770) 2026-03-30 09:37:47 -06:00
buckets.py
civitai.py
clip_vision_adapter.py
config.py
config_modules.py Add support for ACE-Step 1.5 and ACE-Step 1.5 XL. Also added dataset captioning through the UI. (#785) 2026-04-09 15:02:03 -06:00
control_generator.py Remove easy-dwpose from the default requierments 2025-12-20 07:16:20 -07:00
cuda_malloc.py
custom_adapter.py Prep for future breaking changes in newer versions of transformers library 2026-04-10 12:04:32 -06:00
data_loader.py Add support for ACE-Step 1.5 and ACE-Step 1.5 XL. Also added dataset captioning through the UI. (#785) 2026-04-09 15:02:03 -06:00
dataloader_mixins.py Add support for ACE-Step 1.5 and ACE-Step 1.5 XL. Also added dataset captioning through the UI. (#785) 2026-04-09 15:02:03 -06:00
dequantize.py
ema.py Increase ema feedback amount. Normalize the dfe 4 image embeds 2025-06-10 08:01:13 -06:00
embedding.py
esrgan_utils.py
extension.py Added support for finetuning OmniGen2. 2025-06-25 13:58:16 -06:00
guidance.py Add model hooks to polarity loss 2025-04-17 09:00:10 -06:00
image_utils.py Adjust dataloader tester to handle videos to test them 2025-10-21 14:47:23 -06:00
inversion_utils.py
ip_adapter.py Prep for future breaking changes in newer versions of transformers library 2026-04-10 12:04:32 -06:00
job.py
kohya_lora.py Removed all submodules. Submodule free now, yay. 2025-04-18 10:39:15 -06:00
kohya_model_util.py
layers.py
llvae.py
logging_aitk.py Add loss graph to the ui 2025-12-18 10:08:59 -07:00
lora_special.py Add LTX-2 Support (#644) 2026-01-13 04:55:30 -07:00
lorm.py
losses.py Small updates and bug fixes for various things 2025-06-03 20:08:35 -06:00
lycoris_special.py
lycoris_utils.py
metadata.py
network_mixins.py Add method to do continuious lora merging in for low vram full finetuning. 2026-02-26 09:00:41 -07:00
optimizer.py Fixed adafactor eps 2025-10-26 05:47:25 -06:00
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 Pixel shuffle adapter. Some bug fixes thrown in 2025-03-29 21:15:01 -06:00
print.py
progress_bar.py
prompt_utils.py Fixed issue on z-image that prevented training at a larger batch size 2026-03-10 15:43:25 -06:00
reference_adapter.py Prep for future breaking changes in newer versions of transformers library 2026-04-10 12:04:32 -06:00
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 Add Mac OS support for Apple Silicon (#770) 2026-03-30 09:37:47 -06:00
style.py
timer.py
train_pipelines.py
train_tools.py Added initial support for f-lite model 2025-05-01 11:15:18 -06:00
unloader.py Fix issue where text encoder was not fully unloaded in some instances 2025-11-19 09:01:00 -07:00