Kohya S. bbd160b4ca sd3 schedule free opt (#1605) ...

* New ScheduleFree support for Flux (#1600)

* init

* use no schedule

* fix typo

* update for eval()

* fix typo

* update

* Update train_util.py

* Update requirements.txt

* update sfwrapper WIP

* no need to check schedulefree optimizer

* remove debug print

* comment out schedulefree wrapper

* update readme

---------

Co-authored-by: 青龍聖者@bdsqlsz <865105819@qq.com>

2024-09-18 07:55:04 +09:00

..

ipex

Bump crate-ci/typos from 1.19.0 to 1.21.0, fix typos, and updated _typos.toml (Close #1307)

2024-06-05 16:31:55 +09:00

__init__.py

Proposed file structure rework and required file changes

2022-12-18 15:24:46 -05:00

adafactor_fused.py

add stochastic rounding, fix single block

2024-08-21 21:04:10 +09:00

attention_processors.py

update diffusers to 1.16 | train_network

2023-06-01 20:39:26 +09:00

config_util.py

Refactor caching mechanism for latents and text encoder outputs, etc.

2024-07-27 13:50:05 +09:00

custom_train_functions.py

fix to work cond mask and alpha mask

2024-05-26 22:01:37 +09:00

deepspeed_utils.py

make deepspeed_utils

2024-02-27 21:30:46 +09:00

device_utils.py

revert logging #1137

2024-02-25 10:43:14 +09:00

flux_models.py

Fix issue with attention mask not being applied in single blocks

2024-08-24 12:39:54 +09:00

flux_train_utils.py

Improve wandb logging (#1576)

2024-09-11 22:21:16 +09:00

flux_utils.py

T5XXL LoRA training, fp8 T5XXL support

2024-09-04 21:33:17 +09:00

huggingface_util.py

Replace print with logger if they are logs (#905)

2024-02-04 18:14:34 +09:00

hypernetwork.py

update diffusers to 1.16 | train_network

2023-06-01 20:39:26 +09:00

lpw_stable_diffusion.py

Replace print with logger if they are logs (#905)

2024-02-04 18:14:34 +09:00

model_util.py

Merge branch 'dev' into dev_device_support

2024-02-12 13:01:54 +09:00

original_unet.py

Replace print with logger if they are logs (#905)

2024-02-04 18:14:34 +09:00

sai_model_spec.py

update FLUX LoRA training

2024-08-10 23:42:05 +09:00

sd3_models.py

add FLUX.1 LoRA training

2024-08-09 22:56:48 +09:00

sd3_train_utils.py

Improve wandb logging (#1576)

2024-09-11 22:21:16 +09:00

sd3_utils.py

Refactor caching mechanism for latents and text encoder outputs, etc.

2024-07-27 13:50:05 +09:00

sdxl_lpw_stable_diffusion.py

Fix dtype issue in PyTorch 2.0 for generating samples in training sdxl network

2024-01-22 12:43:37 +09:00

sdxl_model_util.py

update readme and help message etc.

2024-05-12 17:55:08 +09:00

sdxl_original_unet.py

fix sdxl timestep embedding

2024-03-15 21:05:00 +09:00

sdxl_train_util.py

Refactor caching mechanism for latents and text encoder outputs, etc.

2024-07-27 13:50:05 +09:00

slicing_vae.py

Replace print with logger if they are logs (#905)

2024-02-04 18:14:34 +09:00

strategy_base.py

feat: Support multi-resolution training with caching latents to disk

2024-08-20 21:39:43 +09:00

strategy_flux.py

T5XXL LoRA training, fp8 T5XXL support

2024-09-04 21:33:17 +09:00

strategy_sd3.py

support attn mask for l+g/t5

2024-08-05 20:51:34 +09:00

strategy_sd.py

fix typos

2024-07-27 13:51:50 +09:00

strategy_sdxl.py

Fix npz path for verification

2024-08-05 20:26:30 +09:00

train_util.py

sd3 schedule free opt (#1605)

2024-09-18 07:55:04 +09:00

utils.py

Merge branch 'dev' into sd3

2024-09-07 10:59:22 +09:00