VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-09 06:45:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

update README, format code

Browse Source
This commit is contained in:
Kohya S
2024-09-07 10:45:18 +09:00
parent 16bb5699ac
commit 0005867ba5
3 changed files with 10 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@@ -139,7 +139,12 @@ The majority of scripts is licensed under ASL 2.0 (including codes from Diffuser
### Working in progress ### Working in progress
- When enlarging images in the script (when the size of the training image is small and bucket_no_upscale is not specified), it has been changed to use Pillow's resize and LANCZOS interpolation instead of OpenCV2's resize and Lanczos4 interpolation. The quality of the image enlargement may be slightly improved. PR [#1426](https://github.com/kohya-ss/sd-scripts/pull/1426) Thanks to sdbds!
- Sample image generation during training now works on non-CUDA devices. PR [#1433](https://github.com/kohya-ss/sd-scripts/pull/1433) Thanks to millie-v!
- `--v_parameterization` is available in `sdxl_train.py`. The results are unpredictable, so use with caution. PR [#1505](https://github.com/kohya-ss/sd-scripts/pull/1505) Thanks to liesened! - `--v_parameterization` is available in `sdxl_train.py`. The results are unpredictable, so use with caution. PR [#1505](https://github.com/kohya-ss/sd-scripts/pull/1505) Thanks to liesened!
- Fused optimizer is available for SDXL training. PR [#1259](https://github.com/kohya-ss/sd-scripts/pull/1259) Thanks to 2kpr! - Fused optimizer is available for SDXL training. PR [#1259](https://github.com/kohya-ss/sd-scripts/pull/1259) Thanks to 2kpr!
- The memory usage during training is significantly reduced by integrating the optimizer's backward pass with step. The training results are the same as before, but if you have plenty of memory, the speed will be slower. - The memory usage during training is significantly reduced by integrating the optimizer's backward pass with step. The training results are the same as before, but if you have plenty of memory, the speed will be slower.
- Specify the `--fused_backward_pass` option in `sdxl_train.py`. At this time, only AdaFactor is supported. Gradient accumulation is not available. - Specify the `--fused_backward_pass` option in `sdxl_train.py`. At this time, only AdaFactor is supported. Gradient accumulation is not available.

4
library/utils.py
View File

@@ -11,6 +11,7 @@ import cv2
from PIL import Image from PIL import Image
import numpy as np import numpy as np
def fire_in_thread(f, *args, **kwargs): def fire_in_thread(f, *args, **kwargs):
threading.Thread(target=f, args=args, kwargs=kwargs).start() threading.Thread(target=f, args=args, kwargs=kwargs).start()
@@ -80,8 +81,8 @@ def setup_logging(args=None, log_level=None, reset=False):
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
logger.info(msg_init) logger.info(msg_init)
def pil_resize(image, size, interpolation=Image.LANCZOS):
def pil_resize(image, size, interpolation=Image.LANCZOS):
pil_image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB)) pil_image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
# use Pillow resize # use Pillow resize
@@ -92,6 +93,7 @@ def pil_resize(image, size, interpolation=Image.LANCZOS):
return resized_cv2 return resized_cv2
# TODO make inf_utils.py # TODO make inf_utils.py