VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-17 17:24:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: metadata dataset degradation and make it work (#2186)

Browse Source 
* fix: support dataset with metadata

* feat: support another tagger model

* fix: improve handling of image size and caption/tag processing in FineTuningDataset

* fix: enhance metadata loading to support JSONL format in FineTuningDataset

* feat: enhance image loading and processing in ImageLoadingPrepDataset with batch support and output options

* fix: improve image path handling and memory management in dataset classes

* Update finetune/tag_images_by_wd14_tagger.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: add return type annotation for process_tag_replacement function and ensure tags are returned

* feat: add artist category threshold for tagging

* doc: add comment for clarification

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Kohya S.
2026-01-18 15:17:07 +09:00
committed by GitHub
parent f7f971f50d
commit c6bc632ec6
4 changed files with 553 additions and 317 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/wd14_tagger_README-en.md
View File

@@ -5,9 +5,11 @@ This document is based on the information from this github page (https://github.
Using onnx for inference is recommended. Please install onnx with the following command:
```powershell
pip install onnx==1.15.0 onnxruntime-gpu==1.17.1
pip install onnx onnxruntime-gpu
```
See [the official documentation](https://onnxruntime.ai/docs/install/#python-installs) for more details.
The model weights will be automatically downloaded from Hugging Face.
# Usage
@@ -49,6 +51,8 @@ python tag_images_by_wd14_tagger.py --onnx --repo_id SmilingWolf/wd-swinv2-tagge
# Options
All options can be checked with `python tag_images_by_wd14_tagger.py --help`.
## General Options
- `--onnx`: Use ONNX for inference. If not specified, TensorFlow will be used. If using TensorFlow, please install TensorFlow separately.

6
docs/wd14_tagger_README-ja.md
View File

@@ -5,9 +5,11 @@
onnx を用いた推論を推奨します。以下のコマンドで onnx をインストールしてください。
```powershell
pip install onnx==1.15.0 onnxruntime-gpu==1.17.1
pip install onnx onnxruntime-gpu
```
詳細は[公式ドキュメント](https://onnxruntime.ai/docs/install/#python-installs)をご覧ください。
モデルの重みはHugging Faceから自動的にダウンロードしてきます。
# 使い方
@@ -48,6 +50,8 @@ python tag_images_by_wd14_tagger.py --onnx --repo_id SmilingWolf/wd-swinv2-tagge
# オプション
全てオプションは `python tag_images_by_wd14_tagger.py --help` で確認できます。
## 一般オプション
- `--onnx` : ONNX を使用して推論します。指定しない場合は TensorFlow を使用します。TensorFlow 使用時は別途 TensorFlow をインストールしてください。