StableDiffusion/KohyaSS
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

2023/02/09 (v20.7.1)

Browse Source 
- Caption dropout is supported in ``train_db.py``, ``fine_tune.py`` and ``train_network.py``. Thanks to forestsource!
        - ``--caption_dropout_rate`` option specifies the dropout rate for captions (0~1.0, 0.1 means 10% chance for dropout). If dropout occurs, the image is trained with the empty caption. Default is 0 (no dropout).
        - ``--caption_dropout_every_n_epochs`` option specifies how many epochs to drop captions. If ``3`` is specified, in epoch 3, 6, 9 ..., images are trained with all captions empty. Default is None (no dropout).
        - ``--caption_tag_dropout_rate`` option specified the dropout rate for tags (comma separated tokens) (0~1.0, 0.1 means 10% chance for dropout). If dropout occurs, the tag is removed from the caption. If ``--keep_tokens`` option is set, these tokens (tags) are not dropped. Default is 0 (no droupout).
        - The bulk image downsampling script is added. Documentation is [here](https://github.com/kohya-ss/sd-scripts/blob/main/train_network_README-ja.md#%E7%94%BB%E5%83%8F%E3%83%AA%E3%82%B5%E3%82%A4%E3%82%BA%E3%82%B9%E3%82%AF%E3%83%AA%E3%83%97%E3%83%88) (in Jpanaese). Thanks to bmaltais!
        - Typo check is added. Thanks to shirayu!
    - Add option to autolaunch the GUI in a browser and set the server_port. USe either `gui.ps1 --inbrowser --server_port 3456`or `gui.cmd -inbrowser -server_port 3456`
This commit is contained in:
bmaltais 2023-02-09 19:17:17 -05:00
parent 09d3a72cd8
commit 90c0d55457
2 changed files with 16 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -143,6 +143,14 @@ Then redo the installation instruction within the kohya_ss venv.
## Change history
* 2023/02/09 (v20.7.1)
- Caption dropout is supported in ``train_db.py``, ``fine_tune.py`` and ``train_network.py``. Thanks to forestsource!
- ``--caption_dropout_rate`` option specifies the dropout rate for captions (0~1.0, 0.1 means 10% chance for dropout). If dropout occurs, the image is trained with the empty caption. Default is 0 (no dropout).
- ``--caption_dropout_every_n_epochs`` option specifies how many epochs to drop captions. If ``3`` is specified, in epoch 3, 6, 9 ..., images are trained with all captions empty. Default is None (no dropout).
- ``--caption_tag_dropout_rate`` option specified the dropout rate for tags (comma separated tokens) (0~1.0, 0.1 means 10% chance for dropout). If dropout occurs, the tag is removed from the caption. If ``--keep_tokens`` option is set, these tokens (tags) are not dropped. Default is 0 (no droupout).
- The bulk image downsampling script is added. Documentation is [here](https://github.com/kohya-ss/sd-scripts/blob/main/train_network_README-ja.md#%E7%94%BB%E5%83%8F%E3%83%AA%E3%82%B5%E3%82%A4%E3%82%BA%E3%82%B9%E3%82%AF%E3%83%AA%E3%83%97%E3%83%88) (in Jpanaese). Thanks to bmaltais!
- Typo check is added. Thanks to shirayu!
- Add option to autolaunch the GUI in a browser and set the server_port. USe either `gui.ps1 --inbrowser --server_port 3456`or `gui.cmd -inbrowser -server_port 3456`
* 2023/02/06 (v20.7.0)
- ``--bucket_reso_steps`` and ``--bucket_no_upscale`` options are added to training scripts (fine tuning, DreamBooth, LoRA and Textual Inversion) and ``prepare_buckets_latents.py``.
- ``--bucket_reso_steps`` takes the steps for buckets in aspect ratio bucketing. Default is 64, same as before.

18
tools/resize_images_to_resolutions.py
View File

@ -4,13 +4,10 @@ import argparse
import shutil
import math
def resize_images(src_img_folder, dst_img_folder, max_resolution="512x512", divisible_by=1):
def resize_images(src_img_folder, dst_img_folder, max_resolution="512x512", divisible_by=1, caption_extension=''):
# Split the max_resolution string by "," and strip any whitespaces
max_resolutions = [res.strip() for res in max_resolution.split(',')]
# # Calculate max_pixels from max_resolution string
# max_pixels = int(max_resolution.split("x")[0]) * int(max_resolution.split("x")[1])
# Create destination folder if it does not exist
if not os.path.exists(dst_img_folder):
os.makedirs(dst_img_folder)
@ -20,7 +17,7 @@ def resize_images(src_img_folder, dst_img_folder, max_resolution="512x512", divi
# Check if the image is png, jpg or webp
if not filename.endswith(('.png', '.jpg', '.webp')):
# Copy the file to the destination folder if not png, jpg or webp
shutil.copy(os.path.join(src_img_folder, filename), os.path.join(dst_img_folder, filename))
# shutil.copy(os.path.join(src_img_folder, filename), os.path.join(dst_img_folder, filename))
continue
# Load image
@ -42,8 +39,8 @@ def resize_images(src_img_folder, dst_img_folder, max_resolution="512x512", divi
new_height = int(img.shape[0] * math.sqrt(scale_factor))
new_width = int(img.shape[1] * math.sqrt(scale_factor))
# Resize image
img = cv2.resize(img, (new_width, new_height))
# Resize image using area interpolation (best when downsampling)
img = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_AREA)
# Calculate the new height and width that are divisible by divisible_by
new_height = new_height if new_height % divisible_by == 0 else new_height - new_height % divisible_by
@ -59,8 +56,8 @@ def resize_images(src_img_folder, dst_img_folder, max_resolution="512x512", divi
new_filename = base + '+' + max_resolution + '.jpg'
# copy caption file with right name if one exist
if os.path.exists(os.path.join(src_img_folder, base + '.txt')):
shutil.copy(os.path.join(src_img_folder, base + '.txt'), os.path.join(dst_img_folder, new_filename + '.txt'))
if os.path.exists(os.path.join(src_img_folder, base + caption_extension)):
shutil.copy(os.path.join(src_img_folder, base + caption_extension), os.path.join(dst_img_folder, new_filename + caption_extension))
# Save resized image in dst_img_folder
cv2.imwrite(os.path.join(dst_img_folder, new_filename), img, [cv2.IMWRITE_JPEG_QUALITY, 100])
@ -73,8 +70,9 @@ def main():
parser.add_argument('dst_img_folder', type=str, help='Destination folder to save the resized images')
parser.add_argument('--max_resolution', type=str, help='Maximum resolution(s) in the format "512x512,448x448,384x384, etc, etc"', default="512x512,448x448,384x384")
parser.add_argument('--divisible_by', type=int, help='Ensure new dimensions are divisible by this value', default=1)
parser.add_argument('--caption_extension', type=str, help='Extension of caption files to copy with resized images"', default=".txt")
args = parser.parse_args()
resize_images(args.src_img_folder, args.dst_img_folder, args.max_resolution)
resize_images(args.src_img_folder, args.dst_img_folder, args.max_resolution, args.divisible_by, args.caption_extension)
if __name__ == '__main__':
main()