| .. |
|
audio
|
…
|
|
|
data_transfer_object
|
Allow images to work with auto frame count, and include images in video datasets if they exist.
|
2026-08-08 20:26:28 -06:00 |
|
keymaps
|
…
|
|
|
memory_management
|
Fix offload buffer stream lifetime
|
2026-08-08 19:59:23 -04:00 |
|
models
|
Add support for MiniMax H3 T2V and I2V training
|
2026-08-03 10:17:39 -06:00 |
|
optimizers
|
Add code for automagic experiment
|
2026-08-01 10:04:46 -06:00 |
|
orig_configs
|
…
|
|
|
samplers
|
…
|
|
|
timestep_weighing
|
…
|
|
|
util
|
Fix backwards compatability for older versions of triton
|
2026-08-04 21:07:57 -06:00 |
|
__init__.py
|
…
|
|
|
accelerator.py
|
…
|
|
|
advanced_prompt_embeds.py
|
…
|
|
|
assistant_lora.py
|
…
|
|
|
basic.py
|
…
|
|
|
buckets.py
|
…
|
|
|
civitai.py
|
…
|
|
|
clip_vision_adapter.py
|
…
|
|
|
config.py
|
…
|
|
|
config_modules.py
|
Apply sigma to contrastive guidance to balance loss better. Prevent noise grads on images/non audio datasets. Prep for training adapters on MiniMax H3
|
2026-08-05 13:27:12 -06:00 |
|
control_generator.py
|
…
|
|
|
cuda_malloc.py
|
…
|
|
|
custom_adapter.py
|
…
|
|
|
data_loader.py
|
Allow images to work with auto frame count, and include images in video datasets if they exist.
|
2026-08-08 20:26:28 -06:00 |
|
dataloader_mixins.py
|
Allow images to work with auto frame count, and include images in video datasets if they exist.
|
2026-08-08 20:26:28 -06:00 |
|
dequantize.py
|
…
|
|
|
ema.py
|
…
|
|
|
embedding.py
|
…
|
|
|
esrgan_utils.py
|
…
|
|
|
extension.py
|
…
|
|
|
guidance.py
|
…
|
|
|
ideogram_caption.py
|
…
|
|
|
image_utils.py
|
…
|
|
|
inversion_utils.py
|
…
|
|
|
ip_adapter.py
|
…
|
|
|
job.py
|
…
|
|
|
kohya_lora.py
|
Restore device runtime scales for compiled adapters (#963)
|
2026-07-18 08:19:57 -06:00 |
|
kohya_model_util.py
|
…
|
|
|
layers.py
|
…
|
|
|
llvae.py
|
…
|
|
|
logging_aitk.py
|
…
|
|
|
lora_special.py
|
Reworked merge in out of loras with convrot weights for better roundtrip accuracy.
|
2026-08-02 08:29:17 -06:00 |
|
lorm.py
|
…
|
|
|
losses.py
|
…
|
|
|
lycoris_special.py
|
Restore device runtime scales for compiled adapters (#963)
|
2026-07-18 08:19:57 -06:00 |
|
lycoris_utils.py
|
…
|
|
|
metadata.py
|
…
|
|
|
network_mixins.py
|
Apply sigma to contrastive guidance to balance loss better. Prevent noise grads on images/non audio datasets. Prep for training adapters on MiniMax H3
|
2026-08-05 13:27:12 -06:00 |
|
optimizer.py
|
Fixed experiment opt name match
|
2026-08-01 17:43:36 -06:00 |
|
paths.py
|
Add support for MiniMax H3 T2V and I2V training
|
2026-08-03 10:17:39 -06:00 |
|
photomaker.py
|
…
|
|
|
photomaker_pipeline.py
|
…
|
|
|
pipelines.py
|
Remove k-sampler requirement and remove it form the cold. not used anymore anyway
|
2026-07-27 14:58:31 -06:00 |
|
pixel_shuffle_encoder.py
|
…
|
|
|
print.py
|
Remove print buffer. Add new line after sampling.
|
2026-07-16 11:37:23 -06:00 |
|
progress_bar.py
|
…
|
|
|
prompt_utils.py
|
feat: Add Anima support (#860)
|
2026-07-15 11:59:01 -06:00 |
|
reference_adapter.py
|
…
|
|
|
resampler.py
|
…
|
|
|
sampler.py
|
Remove k-sampler requirement and remove it form the cold. not used anymore anyway
|
2026-07-27 14:58:31 -06:00 |
|
saving.py
|
…
|
|
|
scheduler.py
|
…
|
|
|
sd_device_states_presets.py
|
…
|
|
|
stable_diffusion_model.py
|
Remove k-sampler requirement and remove it form the cold. not used anymore anyway
|
2026-07-27 14:58:31 -06:00 |
|
style.py
|
…
|
|
|
timer.py
|
…
|
|
|
train_pipelines.py
|
…
|
|
|
train_tools.py
|
…
|
|
|
unloader.py
|
…
|
|
|
win_console.py
|
Rework windows start and stop methods so that command windows dont appear. Stop with signal since we cannot signint.
|
2026-07-27 17:43:01 -06:00 |
