From 124ec45876a9f07820b42fda0d7ca9019de773d5 Mon Sep 17 00:00:00 2001
From: Horizon1704 <92718180+Horizon1704@users.noreply.github.com>
Date: Sun, 10 Mar 2024 22:53:05 +0800
Subject: [PATCH 01/16] Add "encoding='utf-8'"

---
 library/train_util.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/library/train_util.py b/library/train_util.py
index d2b69edb..5f23dd13 100644
--- a/library/train_util.py
+++ b/library/train_util.py
@@ -3474,7 +3474,7 @@ def read_config_from_file(args: argparse.Namespace, parser: argparse.ArgumentPar
         exit(1)
 
     logger.info(f"Loading settings from {config_path}...")
-    with open(config_path, "r") as f:
+    with open(config_path, "r", encoding='utf-8') as f:
         config_dict = toml.load(f)
 
     # combine all sections into one

From 095b8035e63f7c79a232114d8f0e1ec27f431ebc Mon Sep 17 00:00:00 2001
From: gesen2egee <79357052+gesen2egee@users.noreply.github.com>
Date: Sun, 10 Mar 2024 23:33:38 +0800
Subject: [PATCH 02/16] save state on train end

---
 fine_tune.py                     | 2 +-
 library/train_util.py            | 5 +++++
 sdxl_train.py                    | 2 +-
 sdxl_train_control_net_lllite.py | 2 +-
 train_controlnet.py              | 2 +-
 train_db.py                      | 2 +-
 train_network.py                 | 2 +-
 train_textual_inversion.py       | 2 +-
 train_textual_inversion_XTI.py   | 2 +-
 9 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/fine_tune.py b/fine_tune.py
index 875a9195..46f12828 100644
--- a/fine_tune.py
+++ b/fine_tune.py
@@ -457,7 +457,7 @@ def train(args):
 
     accelerator.end_training()
 
-    if args.save_state and is_main_process:
+    if is_main_process and (args.save_state or args.save_state_on_train_end):        
         train_util.save_state_on_train_end(args, accelerator)
 
     del accelerator  # この後メモリを使うのでこれは消す
diff --git a/library/train_util.py b/library/train_util.py
index d2b69edb..b3ca15f5 100644
--- a/library/train_util.py
+++ b/library/train_util.py
@@ -2890,6 +2890,11 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
         action="store_true",
         help="save training state additionally (including optimizer states etc.) / optimizerなど学習状態も含めたstateを追加で保存する",
     )
+    parser.add_argument(
+        "--save_state_on_train_end",
+        action="store_true",
+        help="save training state additionally (including optimizer states etc.) on train end / optimizerなど学習状態も含めたstateを追加で保存する",
+    )   
     parser.add_argument("--resume", type=str, default=None, help="saved state to resume training / 学習再開するモデルのstate")
 
     parser.add_argument("--train_batch_size", type=int, default=1, help="batch size for training / 学習時のバッチサイズ")
diff --git a/sdxl_train.py b/sdxl_train.py
index e0df263d..107bb945 100644
--- a/sdxl_train.py
+++ b/sdxl_train.py
@@ -712,7 +712,7 @@ def train(args):
 
     accelerator.end_training()
 
-    if args.save_state:  # and is_main_process:
+    if args.save_state or args.save_state_on_train_end:        
         train_util.save_state_on_train_end(args, accelerator)
 
     del accelerator  # この後メモリを使うのでこれは消す
diff --git a/sdxl_train_control_net_lllite.py b/sdxl_train_control_net_lllite.py
index 1e5f9234..e99b4e35 100644
--- a/sdxl_train_control_net_lllite.py
+++ b/sdxl_train_control_net_lllite.py
@@ -549,7 +549,7 @@ def train(args):
 
     accelerator.end_training()
 
-    if is_main_process and args.save_state:
+    if is_main_process and (args.save_state or args.save_state_on_train_end):
         train_util.save_state_on_train_end(args, accelerator)
 
     if is_main_process:
diff --git a/train_controlnet.py b/train_controlnet.py
index dc73a91c..e44f0885 100644
--- a/train_controlnet.py
+++ b/train_controlnet.py
@@ -565,7 +565,7 @@ def train(args):
 
     accelerator.end_training()
 
-    if is_main_process and args.save_state:
+    if is_main_process and (args.save_state or args.save_state_on_train_end):
         train_util.save_state_on_train_end(args, accelerator)
 
     # del accelerator  # この後メモリを使うのでこれは消す→printで使うので消さずにおく
diff --git a/train_db.py b/train_db.py
index 8d36097a..41a9a7b9 100644
--- a/train_db.py
+++ b/train_db.py
@@ -444,7 +444,7 @@ def train(args):
 
     accelerator.end_training()
 
-    if args.save_state and is_main_process:
+    if is_main_process and (args.save_state or args.save_state_on_train_end):
         train_util.save_state_on_train_end(args, accelerator)
 
     del accelerator  # この後メモリを使うのでこれは消す
diff --git a/train_network.py b/train_network.py
index e0fa6945..4707d5ae 100644
--- a/train_network.py
+++ b/train_network.py
@@ -935,7 +935,7 @@ class NetworkTrainer:
 
         accelerator.end_training()
 
-        if is_main_process and args.save_state:
+        if is_main_process and args.save_state or args.save_state_on_train_end:
             train_util.save_state_on_train_end(args, accelerator)
 
         if is_main_process:
diff --git a/train_textual_inversion.py b/train_textual_inversion.py
index df1d8485..0266bc14 100644
--- a/train_textual_inversion.py
+++ b/train_textual_inversion.py
@@ -732,7 +732,7 @@ class TextualInversionTrainer:
 
         accelerator.end_training()
 
-        if args.save_state and is_main_process:
+        if is_main_process and (args.save_state or args.save_state_on_train_end):
             train_util.save_state_on_train_end(args, accelerator)
 
         if is_main_process:
diff --git a/train_textual_inversion_XTI.py b/train_textual_inversion_XTI.py
index 695fad2a..ad7c267e 100644
--- a/train_textual_inversion_XTI.py
+++ b/train_textual_inversion_XTI.py
@@ -586,7 +586,7 @@ def train(args):
 
     accelerator.end_training()
 
-    if args.save_state and is_main_process:
+    if is_main_process and (args.save_state or args.save_state_on_train_end):
         train_util.save_state_on_train_end(args, accelerator)
 
     updated_embs = text_encoder.get_input_embeddings().weight[token_ids_XTI].data.detach().clone()

From d282c450026dcfd5f1fd5856f5087ebaed47be46 Mon Sep 17 00:00:00 2001
From: gesen2egee <79357052+gesen2egee@users.noreply.github.com>
Date: Mon, 11 Mar 2024 23:56:09 +0800
Subject: [PATCH 03/16] Update train_network.py

---
 train_network.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/train_network.py b/train_network.py
index 4707d5ae..3db583f1 100644
--- a/train_network.py
+++ b/train_network.py
@@ -935,7 +935,7 @@ class NetworkTrainer:
 
         accelerator.end_training()
 
-        if is_main_process and args.save_state or args.save_state_on_train_end:
+        if is_main_process and (args.save_state or args.save_state_on_train_end):
             train_util.save_state_on_train_end(args, accelerator)
 
         if is_main_process:

From 948029fe61d9142f88374d6701223bf9f7ee5d47 Mon Sep 17 00:00:00 2001
From: kblueleaf <apolloyeh0123@gmail.com>
Date: Tue, 12 Mar 2024 19:11:45 +0800
Subject: [PATCH 04/16] random ip_noise_gamma strength

---
 library/train_util.py | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/library/train_util.py b/library/train_util.py
index b71e4edc..aa2d9b90 100644
--- a/library/train_util.py
+++ b/library/train_util.py
@@ -3100,6 +3100,13 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
         help="enable input perturbation noise. used for regularization. recommended value: around 0.1 (from arxiv.org/abs/2301.11706) "
         + "/  input perturbation noiseを有効にする。正則化に使用される。推奨値: 0.1程度 (arxiv.org/abs/2301.11706 より)",
     )
+    parser.add_argument(
+        "--ip_noise_gamma_random_strength",
+        type=bool,
+        default=False,
+        help="Use random strength between 0~ip_noise_gamma for input perturbation noise."
+        + "/ input perturbation noiseにおいて、0からip_noise_gammaの間でランダムな強度を使用します。",
+    )
     # parser.add_argument(
     #     "--perlin_noise",
     #     type=int,
@@ -4673,7 +4680,11 @@ def get_noise_noisy_latents_and_timesteps(args, noise_scheduler, latents):
     # Add noise to the latents according to the noise magnitude at each timestep
     # (this is the forward diffusion process)
     if args.ip_noise_gamma:
-        noisy_latents = noise_scheduler.add_noise(latents, noise + args.ip_noise_gamma * torch.randn_like(latents), timesteps)
+        if args.ip_noise_gamma_random_strength:
+            strength = torch.rand(1, device=latents.device) * args.ip_noise_gamma
+        else:
+            strength = args.ip_noise_gamma
+        noisy_latents = noise_scheduler.add_noise(latents, noise + strength * torch.randn_like(latents), timesteps)
     else:
         noisy_latents = noise_scheduler.add_noise(latents, noise, timesteps)
 

From 86399407b2bb5a93d691846acfa88e7ba38ae70d Mon Sep 17 00:00:00 2001
From: kblueleaf <apolloyeh0123@gmail.com>
Date: Tue, 12 Mar 2024 19:14:01 +0800
Subject: [PATCH 05/16] random noise_offset strength

---
 library/train_util.py | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/library/train_util.py b/library/train_util.py
index aa2d9b90..5282b524 100644
--- a/library/train_util.py
+++ b/library/train_util.py
@@ -3087,6 +3087,12 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
         default=None,
         help="enable noise offset with this value (if enabled, around 0.1 is recommended) / Noise offsetを有効にしてこの値を設定する（有効にする場合は0.1程度を推奨）",
     )
+    parser.add_argument(
+        "--noise_offset_random_strength",
+        type=bool,
+        default=False,
+        help="use random strength between 0~noise_offset for noise offset. / noise offsetにおいて、0からnoise_offsetの間でランダムな強度を使用します。",
+    )
     parser.add_argument(
         "--multires_noise_iterations",
         type=int,
@@ -4663,7 +4669,11 @@ def get_noise_noisy_latents_and_timesteps(args, noise_scheduler, latents):
     # Sample noise that we'll add to the latents
     noise = torch.randn_like(latents, device=latents.device)
     if args.noise_offset:
-        noise = custom_train_functions.apply_noise_offset(latents, noise, args.noise_offset, args.adaptive_noise_scale)
+        if args.noise_offset_random_strength:
+            noise_offset = torch.rand(1, device=latents.device) * args.noise_offset
+        else:
+            noise_offset = args.noise_offset
+        noise = custom_train_functions.apply_noise_offset(latents, noise, noise_offset, args.adaptive_noise_scale)
     if args.multires_noise_iterations:
         noise = custom_train_functions.pyramid_noise_like(
             noise, latents.device, args.multires_noise_iterations, args.multires_noise_discount

From 53954a1e2e05648bae6eb479720402968029cd3d Mon Sep 17 00:00:00 2001
From: kblueleaf <apolloyeh0123@gmail.com>
Date: Tue, 12 Mar 2024 19:24:27 +0800
Subject: [PATCH 06/16] use correct settings for parser

---
 library/train_util.py | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/library/train_util.py b/library/train_util.py
index 5282b524..73a76867 100644
--- a/library/train_util.py
+++ b/library/train_util.py
@@ -3089,8 +3089,7 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
     )
     parser.add_argument(
         "--noise_offset_random_strength",
-        type=bool,
-        default=False,
+        action="store_true",
         help="use random strength between 0~noise_offset for noise offset. / noise offsetにおいて、0からnoise_offsetの間でランダムな強度を使用します。",
     )
     parser.add_argument(
@@ -3108,8 +3107,7 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
     )
     parser.add_argument(
         "--ip_noise_gamma_random_strength",
-        type=bool,
-        default=False,
+        action="store_true",
         help="Use random strength between 0~ip_noise_gamma for input perturbation noise."
         + "/ input perturbation noiseにおいて、0からip_noise_gammaの間でランダムな強度を使用します。",
     )

From f9317052edb4ab3b3c531ac3b28825ee78b4a966 Mon Sep 17 00:00:00 2001
From: Kohya S <ykumeykume@gmail.com>
Date: Mon, 18 Mar 2024 08:53:23 +0900
Subject: [PATCH 07/16] update readme for timestep embs bug

---
 README.md | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 3639b7be..001446b7 100644
--- a/README.md
+++ b/README.md
@@ -252,12 +252,15 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 ### Mar 15, 2024 / 2024/3/15: v0.8.5
 
 - Fixed a bug that the value of timestep embedding during SDXL training was incorrect.
+  - Please update for SDXL training.
   - The inference with the generation script is also fixed.
-  - The impact is unknown, but please update for SDXL training.
+  - This fix appears to resolve an issue where unintended artifacts occurred in trained models under certain conditions. 
+We would like to express our deep gratitude to Mark Saint (cacoe) from leonardo.ai, for reporting the issue and cooperating with the verification, and to gcem156 for the advice provided in identifying the part of the code that needed to be fixed.
 
 - SDXL 学習時の timestep embedding の値が誤っていたのを修正しました。
+  - SDXL の学習時にはアップデートをお願いいたします。
   - 生成スクリプトでの推論時についてもあわせて修正しました。
-  - 影響の度合いは不明ですが、SDXL の学習時にはアップデートをお願いいたします。
+  - この修正により、特定の条件下で学習されたモデルに意図しないアーティファクトが発生する問題が解消されるようです。問題を報告いただき、また検証にご協力いただいた leonardo.ai の Mark Saint (cacoe) 氏、および修正点の特定に関するアドバイスをいただいた gcem156 氏に深く感謝いたします。
 
 ### Feb 24, 2024 / 2024/2/24: v0.8.4
 

From a7dff592d34a5dd9d306de822db70f0028676cab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=9D=92=E9=BE=8D=E8=81=96=E8=80=85=40bdsqlsz?=
 <qinglongshengzhe@gmail.com>
Date: Mon, 18 Mar 2024 22:29:05 +0800
Subject: [PATCH 08/16] Update tag_images_by_wd14_tagger.py

add WDV3
---
 finetune/tag_images_by_wd14_tagger.py | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/finetune/tag_images_by_wd14_tagger.py b/finetune/tag_images_by_wd14_tagger.py
index b56d921a..e63ec3eb 100644
--- a/finetune/tag_images_by_wd14_tagger.py
+++ b/finetune/tag_images_by_wd14_tagger.py
@@ -86,23 +86,26 @@ def main(args):
         logger.info(f"downloading wd14 tagger model from hf_hub. id: {args.repo_id}")
         files = FILES
         if args.onnx:
+            files = ["selected_tags.csv"]
             files += FILES_ONNX
+        else:
+            for file in SUB_DIR_FILES:
+                hf_hub_download(
+                    args.repo_id,
+                    file,
+                    subfolder=SUB_DIR,
+                    cache_dir=os.path.join(args.model_dir, SUB_DIR),
+                    force_download=True,
+                    force_filename=file,
+                )
         for file in files:
             hf_hub_download(args.repo_id, file, cache_dir=args.model_dir, force_download=True, force_filename=file)
-        for file in SUB_DIR_FILES:
-            hf_hub_download(
-                args.repo_id,
-                file,
-                subfolder=SUB_DIR,
-                cache_dir=os.path.join(args.model_dir, SUB_DIR),
-                force_download=True,
-                force_filename=file,
-            )
     else:
         logger.info("using existing wd14 tagger model")
 
     # 画像を読み込む
     if args.onnx:
+        import torch
         import onnx
         import onnxruntime as ort
 

From 5410a8c79b23c594bb340050b4a81e30d95cd7be Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=9D=92=E9=BE=8D=E8=81=96=E8=80=85=40bdsqlsz?=
 <qinglongshengzhe@gmail.com>
Date: Mon, 18 Mar 2024 22:31:00 +0800
Subject: [PATCH 09/16] Update requirements.txt

---
 requirements.txt | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/requirements.txt b/requirements.txt
index 279de350..326b65b3 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -22,9 +22,9 @@ huggingface-hub==0.20.1
 # for WD14 captioning (tensorflow)
 # tensorflow==2.10.1
 # for WD14 captioning (onnx)
-# onnx==1.14.1
-# onnxruntime-gpu==1.16.0
-# onnxruntime==1.16.0
+# onnx==1.15.1
+# onnxruntime-gpu==1.17.1
+# onnxruntime==1.17.1
 # this is for onnx: 
 # protobuf==3.20.3
 # open clip for SDXL

From a71c35ccd9c813821fcbd3f0e00d71fb5e6d91d6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=9D=92=E9=BE=8D=E8=81=96=E8=80=85=40bdsqlsz?=
 <qinglongshengzhe@gmail.com>
Date: Mon, 18 Mar 2024 22:31:59 +0800
Subject: [PATCH 10/16] Update requirements.txt

---
 requirements.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/requirements.txt b/requirements.txt
index 326b65b3..6898eccf 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -25,6 +25,9 @@ huggingface-hub==0.20.1
 # onnx==1.15.1
 # onnxruntime-gpu==1.17.1
 # onnxruntime==1.17.1
+# for cuda 12.1(default 11.8)
+# onnxruntime-gpu --extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/onnxruntime-cuda-12/pypi/simple/
+
 # this is for onnx: 
 # protobuf==3.20.3
 # open clip for SDXL

From 6c51c971d135a346d2f9081760f138b1c6515e9b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=9D=92=E9=BE=8D=E8=81=96=E8=80=85=40bdsqlsz?=
 <qinglongshengzhe@gmail.com>
Date: Wed, 20 Mar 2024 09:35:21 +0800
Subject: [PATCH 11/16] fix typo

---
 requirements.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements.txt b/requirements.txt
index 6898eccf..805f0501 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -22,7 +22,7 @@ huggingface-hub==0.20.1
 # for WD14 captioning (tensorflow)
 # tensorflow==2.10.1
 # for WD14 captioning (onnx)
-# onnx==1.15.1
+# onnx==1.15.0
 # onnxruntime-gpu==1.17.1
 # onnxruntime==1.17.1
 # for cuda 12.1(default 11.8)

From 80dbbf5e4875f56ff1e0d8aacea4e73b96a14b63 Mon Sep 17 00:00:00 2001
From: Kohya S <ykumeykume@gmail.com>
Date: Wed, 20 Mar 2024 16:14:57 +0900
Subject: [PATCH 12/16] tagger now stores model under repo_id subdir

---
 README.md                             |  9 ++++-
 finetune/tag_images_by_wd14_tagger.py | 55 ++++++++++++++++++---------
 2 files changed, 45 insertions(+), 19 deletions(-)

diff --git a/README.md b/README.md
index f0cad611..d0320403 100644
--- a/README.md
+++ b/README.md
@@ -260,7 +260,9 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
   - `keep_tokens_separator` is updated to be used twice in the caption. When you specify `keep_tokens_separator="|||"`, the part divided by the second `|||` is not shuffled or dropped and remains at the end.
   - The existing features `caption_prefix` and `caption_suffix` can be used together. `caption_prefix` and `caption_suffix` are processed first, and then `enable_wildcard`, `keep_tokens_separator`, shuffling and dropping, and `secondary_separator` are processed in order.
   - The examples are [shown below](#example-of-dataset-settings--データセット設定の記述例).
-
+- The support for v3 repositories is added to `tag_image_by_wd14_tagger.py` (`--onnx` option only). PR [#1192](https://github.com/kohya-ss/sd-scripts/pull/1192) Thanks to sdbds!
+  - Onnx may need to be updated. Onnx is not installed by default, so please install or update it with `pip install onnx==1.15.0 onnxruntime-gpu==1.17.1` etc. Please also check the comments in `requirements.txt`.
+- The model is now saved in the subdirectory as `--repo_id` in `tag_image_by_wd14_tagger.py` . This caches multiple repo_id models. Please delete unnecessary files under `--model_dir`.
 
 - Colab での動作時、ログ出力で停止してしまうようです。学習スクリプトに `--console_log_simple` オプションを指定し、rich のロギングを無効してお試しください。
 - `train_network.py` および `sdxl_train_network.py` で、学習したモデルのメタデータに一部のデータセット設定が記録されるよう修正しました（`caption_prefix`、`caption_suffix`、`keep_tokens_separator`、`secondary_separator`、`enable_wildcard`）。
@@ -269,6 +271,11 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
   - `enable_wildcard` を追加しました。`true` にするとワイルドカード記法 `{aaa|bbb|ccc}` が使えます。詳しくは記述例をご覧ください。
   - `keep_tokens_separator` をキャプション内に 2 つ使えるようにしました。たとえば `keep_tokens_separator="|||"` と指定したとき、`1girl, hatsune miku, vocaloid ||| stage, mic ||| best quality, rating: general` とキャプションを指定すると、二番目の `|||` で分割された部分はシャッフル、drop されず末尾に残ります。
   - 既存の機能 `caption_prefix` と `caption_suffix` とあわせて使えます。`caption_prefix` と `caption_suffix` は一番最初に処理され、その後、ワイルドカード、`keep_tokens_separator`、シャッフルおよび drop、`secondary_separator` の順に処理されます。
+- `tag_image_by_wd14_tagger.py` で v3 のリポジトリがサポートされました（`--onnx` 指定時のみ有効）。 PR [#1192](https://github.com/kohya-ss/sd-scripts/pull/1192) sdbds 氏に感謝します。
+  - Onnx のバージョンアップが必要になるかもしれません。デフォルトでは Onnx はインストールされていませんので、`pip install onnx==1.15.0 onnxruntime-gpu==1.17.1` 等でインストール、アップデートしてください。`requirements.txt` のコメントもあわせてご確認ください。
+- `tag_image_by_wd14_tagger.py` で、モデルを`--repo_id` のサブディレクトリに保存するようにしました。これにより複数のモデルファイルがキャッシュされます。`--model_dir` 直下の不要なファイルは削除願います。
+
+
 
 #### Example of dataset settings / データセット設定の記述例:
 
diff --git a/finetune/tag_images_by_wd14_tagger.py b/finetune/tag_images_by_wd14_tagger.py
index e63ec3eb..401c6d1e 100644
--- a/finetune/tag_images_by_wd14_tagger.py
+++ b/finetune/tag_images_by_wd14_tagger.py
@@ -12,8 +12,10 @@ from tqdm import tqdm
 
 import library.train_util as train_util
 from library.utils import setup_logging
+
 setup_logging()
 import logging
+
 logger = logging.getLogger(__name__)
 
 # from wd14 tagger
@@ -79,10 +81,15 @@ def collate_fn_remove_corrupted(batch):
 
 
 def main(args):
+    # model location is model_dir + repo_id
+    # repo id may be like "user/repo" or "user/repo/branch", so we need to remove slash
+    model_location = os.path.join(args.model_dir, args.repo_id.replace("/", "_"))
+
     # hf_hub_downloadをそのまま使うとsymlink関係で問題があるらしいので、キャッシュディレクトリとforce_filenameを指定してなんとかする
     # depreacatedの警告が出るけどなくなったらその時
     # https://github.com/toriato/stable-diffusion-webui-wd14-tagger/issues/22
-    if not os.path.exists(args.model_dir) or args.force_download:
+    if not os.path.exists(model_location) or args.force_download:
+        os.makedirs(args.model_dir, exist_ok=True)
         logger.info(f"downloading wd14 tagger model from hf_hub. id: {args.repo_id}")
         files = FILES
         if args.onnx:
@@ -94,12 +101,12 @@ def main(args):
                     args.repo_id,
                     file,
                     subfolder=SUB_DIR,
-                    cache_dir=os.path.join(args.model_dir, SUB_DIR),
+                    cache_dir=os.path.join(model_location, SUB_DIR),
                     force_download=True,
                     force_filename=file,
                 )
         for file in files:
-            hf_hub_download(args.repo_id, file, cache_dir=args.model_dir, force_download=True, force_filename=file)
+            hf_hub_download(args.repo_id, file, cache_dir=model_location, force_download=True, force_filename=file)
     else:
         logger.info("using existing wd14 tagger model")
 
@@ -109,7 +116,7 @@ def main(args):
         import onnx
         import onnxruntime as ort
 
-        onnx_path = f"{args.model_dir}/model.onnx"
+        onnx_path = f"{model_location}/model.onnx"
         logger.info("Running wd14 tagger with onnx")
         logger.info(f"loading onnx model: {onnx_path}")
 
@@ -126,7 +133,7 @@ def main(args):
         except:
             batch_size = model.graph.input[0].type.tensor_type.shape.dim[0].dim_param
 
-        if args.batch_size != batch_size and type(batch_size) != str:
+        if args.batch_size != batch_size and type(batch_size) != str and batch_size > 0:
             # some rebatch model may use 'N' as dynamic axes
             logger.warning(
                 f"Batch size {args.batch_size} doesn't match onnx model batch size {batch_size}, use model batch size {batch_size}"
@@ -137,19 +144,19 @@ def main(args):
 
         ort_sess = ort.InferenceSession(
             onnx_path,
-            providers=["CUDAExecutionProvider"]
-            if "CUDAExecutionProvider" in ort.get_available_providers()
-            else ["CPUExecutionProvider"],
+            providers=(
+                ["CUDAExecutionProvider"] if "CUDAExecutionProvider" in ort.get_available_providers() else ["CPUExecutionProvider"]
+            ),
         )
     else:
         from tensorflow.keras.models import load_model
 
-        model = load_model(f"{args.model_dir}")
+        model = load_model(f"{model_location}")
 
     # label_names = pd.read_csv("2022_0000_0899_6549/selected_tags.csv")
     # 依存ライブラリを増やしたくないので自力で読むよ
 
-    with open(os.path.join(args.model_dir, CSV_FILE), "r", encoding="utf-8") as f:
+    with open(os.path.join(model_location, CSV_FILE), "r", encoding="utf-8") as f:
         reader = csv.reader(f)
         l = [row for row in reader]
         header = l[0]  # tag_id,name,category,count
@@ -175,8 +182,8 @@ def main(args):
         imgs = np.array([im for _, im in path_imgs])
 
         if args.onnx:
-            if len(imgs) < args.batch_size:
-                imgs = np.concatenate([imgs, np.zeros((args.batch_size - len(imgs), IMAGE_SIZE, IMAGE_SIZE, 3))], axis=0)
+            # if len(imgs) < args.batch_size:
+            #     imgs = np.concatenate([imgs, np.zeros((args.batch_size - len(imgs), IMAGE_SIZE, IMAGE_SIZE, 3))], axis=0)
             probs = ort_sess.run(None, {input_name: imgs})[0]  # onnx output numpy
             probs = probs[: len(path_imgs)]
         else:
@@ -317,7 +324,9 @@ def setup_parser() -> argparse.ArgumentParser:
         help="directory to store wd14 tagger model / wd14 taggerのモデルを格納するディレクトリ",
     )
     parser.add_argument(
-        "--force_download", action="store_true", help="force downloading wd14 tagger models / wd14 taggerのモデルを再ダウンロードします"
+        "--force_download",
+        action="store_true",
+        help="force downloading wd14 tagger models / wd14 taggerのモデルを再ダウンロードします",
     )
     parser.add_argument("--batch_size", type=int, default=1, help="batch size in inference / 推論時のバッチサイズ")
     parser.add_argument(
@@ -332,8 +341,12 @@ def setup_parser() -> argparse.ArgumentParser:
         default=None,
         help="extension of caption file (for backward compatibility) / 出力されるキャプションファイルの拡張子（スペルミスしていたのを残してあります）",
     )
-    parser.add_argument("--caption_extension", type=str, default=".txt", help="extension of caption file / 出力されるキャプションファイルの拡張子")
-    parser.add_argument("--thresh", type=float, default=0.35, help="threshold of confidence to add a tag / タグを追加するか判定する閾値")
+    parser.add_argument(
+        "--caption_extension", type=str, default=".txt", help="extension of caption file / 出力されるキャプションファイルの拡張子"
+    )
+    parser.add_argument(
+        "--thresh", type=float, default=0.35, help="threshold of confidence to add a tag / タグを追加するか判定する閾値"
+    )
     parser.add_argument(
         "--general_threshold",
         type=float,
@@ -346,7 +359,9 @@ def setup_parser() -> argparse.ArgumentParser:
         default=None,
         help="threshold of confidence to add a tag for character category, same as --thres if omitted / characterカテゴリのタグを追加するための確信度の閾値、省略時は --thresh と同じ",
     )
-    parser.add_argument("--recursive", action="store_true", help="search for images in subfolders recursively / サブフォルダを再帰的に検索する")
+    parser.add_argument(
+        "--recursive", action="store_true", help="search for images in subfolders recursively / サブフォルダを再帰的に検索する"
+    )
     parser.add_argument(
         "--remove_underscore",
         action="store_true",
@@ -359,9 +374,13 @@ def setup_parser() -> argparse.ArgumentParser:
         default="",
         help="comma-separated list of undesired tags to remove from the output / 出力から除外したいタグのカンマ区切りのリスト",
     )
-    parser.add_argument("--frequency_tags", action="store_true", help="Show frequency of tags for images / 画像ごとのタグの出現頻度を表示する")
+    parser.add_argument(
+        "--frequency_tags", action="store_true", help="Show frequency of tags for images / 画像ごとのタグの出現頻度を表示する"
+    )
     parser.add_argument("--onnx", action="store_true", help="use onnx model for inference / onnxモデルを推論に使用する")
-    parser.add_argument("--append_tags", action="store_true", help="Append captions instead of overwriting / 上書きではなくキャプションを追記する")
+    parser.add_argument(
+        "--append_tags", action="store_true", help="Append captions instead of overwriting / 上書きではなくキャプションを追記する"
+    )
     parser.add_argument(
         "--caption_separator",
         type=str,

From 46331a9e8ef695ea0b5a19686202d011109a56b6 Mon Sep 17 00:00:00 2001
From: Victor Espinoza-Guerra <thesilvervelvets@gmail.com>
Date: Wed, 20 Mar 2024 00:31:01 -0700
Subject: [PATCH 13/16] English Translation of config_README-ja.md (#1175)

* Add files via upload

Creating template to work on.

* Update config_README-en.md

Total Conversion from Japanese to English.

* Update config_README-en.md

* Update config_README-en.md

* Update config_README-en.md
---
 docs/config_README-en.md | 279 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 279 insertions(+)
 create mode 100644 docs/config_README-en.md

diff --git a/docs/config_README-en.md b/docs/config_README-en.md
new file mode 100644
index 00000000..a0727934
--- /dev/null
+++ b/docs/config_README-en.md
@@ -0,0 +1,279 @@
+Original Source by kohya-ss
+
+A.I Translation by Model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO, editing by Darkstorm2150
+
+# Config Readme
+
+This README is about the configuration files that can be passed with the `--dataset_config` option.
+
+## Overview
+
+By passing a configuration file, users can make detailed settings.
+
+* Multiple datasets can be configured
+   * For example, by setting `resolution` for each dataset, they can be mixed and trained.
+   * In training methods that support both the DreamBooth approach and the fine-tuning approach, datasets of the DreamBooth method and the fine-tuning method can be mixed.
+* Settings can be changed for each subset
+   * A subset is a partition of the dataset by image directory or metadata. Several subsets make up a dataset.
+   * Options such as `keep_tokens` and `flip_aug` can be set for each subset. On the other hand, options such as `resolution` and `batch_size` can be set for each dataset, and their values are common among subsets belonging to the same dataset. More details will be provided later.
+
+The configuration file format can be JSON or TOML. Considering the ease of writing, it is recommended to use [TOML](https://toml.io/ja/v1.0.0-rc.2). The following explanation assumes the use of TOML.
+
+
+Here is an example of a configuration file written in TOML.
+
+```toml
+[general]
+shuffle_caption = true
+caption_extension = '.txt'
+keep_tokens = 1
+
+# This is a DreamBooth-style dataset
+[[datasets]]
+resolution = 512
+batch_size = 4
+keep_tokens = 2
+
+  [[datasets.subsets]]
+  image_dir = 'C:\hoge'
+  class_tokens = 'hoge girl'
+  # This subset uses keep_tokens = 2 (the value of the parent datasets)
+
+  [[datasets.subsets]]
+  image_dir = 'C:\fuga'
+  class_tokens = 'fuga boy'
+  keep_tokens = 3
+
+  [[datasets.subsets]]
+  is_reg = true
+  image_dir = 'C:\reg'
+  class_tokens = 'human'
+  keep_tokens = 1
+
+# This is a fine-tuning dataset
+[[datasets]]
+resolution = [768, 768]
+batch_size = 2
+
+  [[datasets.subsets]]
+  image_dir = 'C:\piyo'
+  metadata_file = 'C:\piyo\piyo_md.json'
+  # This subset uses keep_tokens = 1 (the value of [general])
+```
+
+In this example, three directories are trained as a DreamBooth-style dataset at 512x512 (batch size 4), and one directory is trained as a fine-tuning dataset at 768x768 (batch size 2).
+
+## Settings for datasets and subsets
+
+Settings for datasets and subsets are divided into several registration locations.
+
+* `[general]`
+    * This is where options that apply to all datasets or all subsets are specified.
+    * If there are options with the same name in the dataset-specific or subset-specific settings, the dataset-specific or subset-specific settings take precedence.
+* `[[datasets]]`
+    * `datasets` is where settings for datasets are registered. This is where options that apply individually to each dataset are specified.
+	* If there are subset-specific settings, the subset-specific settings take precedence.
+* `[[datasets.subsets]]`
+    * `datasets.subsets` is where settings for subsets are registered. This is where options that apply individually to each subset are specified.
+
+Here is an image showing the correspondence between image directories and registration locations in the previous example.
+
+```
+C:\
+├─ hoge  ->  [[datasets.subsets]] No.1  ┐                        ┐
+├─ fuga  ->  [[datasets.subsets]] No.2  |->  [[datasets]] No.1   |->  [general]
+├─ reg   ->  [[datasets.subsets]] No.3  ┘                        |
+└─ piyo  ->  [[datasets.subsets]] No.4  -->  [[datasets]] No.2   ┘
+```
+
+The image directory corresponds to each `[[datasets.subsets]]`. Then, multiple `[[datasets.subsets]]` are combined to form one `[[datasets]]`. All `[[datasets]]` and `[[datasets.subsets]]` belong to `[general]`.
+
+The available options for each registration location may differ, but if the same option is specified, the value in the lower registration location will take precedence. You can check how the `keep_tokens` option is handled in the previous example for better understanding.
+
+Additionally, the available options may vary depending on the method that the learning approach supports.
+
+* Options specific to the DreamBooth method
+* Options specific to the fine-tuning method
+* Options available when using the caption dropout technique
+
+When using both the DreamBooth method and the fine-tuning method, they can be used together with a learning approach that supports both.
+When using them together, a point to note is that the method is determined based on the dataset, so it is not possible to mix DreamBooth method subsets and fine-tuning method subsets within the same dataset.
+In other words, if you want to use both methods together, you need to set up subsets of different methods belonging to different datasets.
+
+In terms of program behavior, if the `metadata_file` option exists, it is determined to be a subset of fine-tuning. Therefore, for subsets belonging to the same dataset, as long as they are either "all have the `metadata_file` option" or "all have no `metadata_file` option," there is no problem.
+
+Below, the available options will be explained. For options with the same name as the command-line argument, the explanation will be omitted in principle. Please refer to other READMEs.
+
+### Common options for all learning methods
+
+These are options that can be specified regardless of the learning method.
+
+#### Data set specific options
+
+These are options related to the configuration of the data set. They cannot be described in `datasets.subsets`.
+
+
+| Option Name | Example Setting | `[general]` | `[[datasets]]` |
+| ---- | ---- | ---- | ---- |
+| `batch_size` | `1` | o | o |
+| `bucket_no_upscale` | `true` | o | o |
+| `bucket_reso_steps` | `64` | o | o |
+| `enable_bucket` | `true` | o | o |
+| `max_bucket_reso` | `1024` | o | o |
+| `min_bucket_reso` | `128` | o | o |
+| `resolution` | `256`, `[512, 512]` | o | o |
+
+* `batch_size`
+    * This corresponds to the command-line argument `--train_batch_size`.
+
+These settings are fixed per dataset. That means that subsets belonging to the same dataset will share these settings. For example, if you want to prepare datasets with different resolutions, you can define them as separate datasets as shown in the example above, and set different resolutions for each.
+
+#### Options for Subsets
+
+These options are related to subset configuration.
+
+| Option Name | Example | `[general]` | `[[datasets]]` | `[[dataset.subsets]]` |
+| ---- | ---- | ---- | ---- | ---- |
+| `color_aug` | `false` | o | o | o |
+| `face_crop_aug_range` | `[1.0, 3.0]` | o | o | o |
+| `flip_aug` | `true` | o | o | o |
+| `keep_tokens` | `2` | o | o | o |
+| `num_repeats` | `10` | o | o | o |
+| `random_crop` | `false` | o | o | o |
+| `shuffle_caption` | `true` | o | o | o |
+| `caption_prefix` | `"masterpiece, best quality, "` | o | o | o |
+| `caption_suffix` | `", from side"` | o | o | o |
+
+* `num_repeats`
+    * Specifies the number of repeats for images in a subset. This is equivalent to `--dataset_repeats` in fine-tuning but can be specified for any training method.
+* `caption_prefix`, `caption_suffix`
+    * Specifies the prefix and suffix strings to be appended to the captions. Shuffling is performed with these strings included. Be cautious when using `keep_tokens`.
+
+### DreamBooth-specific options
+
+DreamBooth-specific options only exist as subsets-specific options.
+
+#### Subset-specific options
+
+Options related to the configuration of DreamBooth subsets.
+
+| Option Name | Example Setting | `[general]` | `[[datasets]]` | `[[dataset.subsets]]` |
+| ---- | ---- | ---- | ---- | ---- |
+| `image_dir` | `'C:\hoge'` | - | - | o (required) |
+| `caption_extension` | `".txt"` | o | o | o |
+| `class_tokens` | `"sks girl"` | - | - | o |
+| `is_reg` | `false` | - | - | o |
+
+Firstly, note that for `image_dir`, the path to the image files must be specified as being directly in the directory. Unlike the previous DreamBooth method, where images had to be placed in subdirectories, this is not compatible with that specification. Also, even if you name the folder something like "5_cat", the number of repeats of the image and the class name will not be reflected. If you want to set these individually, you will need to explicitly specify them using `num_repeats` and `class_tokens`.
+
+* `image_dir`
+    * Specifies the path to the image directory. This is a required option.
+    * Images must be placed directly under the directory.
+* `class_tokens`
+    * Sets the class tokens.
+    * Only used during training when a corresponding caption file does not exist. The determination of whether or not to use it is made on a per-image basis. If `class_tokens` is not specified and a caption file is not found, an error will occur.
+* `is_reg`
+    * Specifies whether the subset images are for normalization. If not specified, it is set to `false`, meaning that the images are not for normalization.
+
+### Fine-tuning method specific options
+
+The options for the fine-tuning method only exist for subset-specific options.
+
+#### Subset-specific options
+
+These options are related to the configuration of the fine-tuning method's subsets.
+
+| Option name | Example setting | `[general]` | `[[datasets]]` | `[[dataset.subsets]]` |
+| ---- | ---- | ---- | ---- | ---- |
+| `image_dir` | `'C:\hoge'` | - | - | o |
+| `metadata_file` | `'C:\piyo\piyo_md.json'` | - | - | o (required) |
+
+* `image_dir`
+    * Specify the path to the image directory. Unlike the DreamBooth method, specifying it is not mandatory, but it is recommended to do so.
+        * The case where it is not necessary to specify is when the `--full_path` is added to the command line when generating the metadata file.
+    * The images must be placed directly under the directory.
+* `metadata_file`
+    * Specify the path to the metadata file used for the subset. This is a required option.
+        * It is equivalent to the command-line argument `--in_json`.
+    * Due to the specification that a metadata file must be specified for each subset, it is recommended to avoid creating a metadata file with images from different directories as a single metadata file. It is strongly recommended to prepare a separate metadata file for each image directory and register them as separate subsets.
+
+### Options available when caption dropout method can be used
+
+The options available when the caption dropout method can be used exist only for subsets. Regardless of whether it's the DreamBooth method or fine-tuning method, if it supports caption dropout, it can be specified.
+
+#### Subset-specific options
+
+Options related to the setting of subsets that caption dropout can be used for.
+
+| Option Name | `[general]` | `[[datasets]]` | `[[dataset.subsets]]` |
+| ---- | ---- | ---- | ---- |
+| `caption_dropout_every_n_epochs` | o | o | o |
+| `caption_dropout_rate` | o | o | o |
+| `caption_tag_dropout_rate` | o | o | o |
+
+## Behavior when there are duplicate subsets
+
+In the case of the DreamBooth dataset, if there are multiple `image_dir` directories with the same content, they are considered to be duplicate subsets. For the fine-tuning dataset, if there are multiple `metadata_file` files with the same content, they are considered to be duplicate subsets. If duplicate subsets exist in the dataset, subsequent subsets will be ignored.
+
+However, if they belong to different datasets, they are not considered duplicates. For example, if you have subsets with the same `image_dir` in different datasets, they will not be considered duplicates. This is useful when you want to train with the same image but with different resolutions.
+
+```toml
+# If data sets exist separately, they are not considered duplicates and are both used for training.
+
+[[datasets]]
+resolution = 512
+
+  [[datasets.subsets]]
+  image_dir = 'C:\hoge'
+
+[[datasets]]
+resolution = 768
+
+  [[datasets.subsets]]
+  image_dir = 'C:\hoge'
+```
+
+## Command Line Argument and Configuration File
+
+There are options in the configuration file that have overlapping roles with command line argument options.
+
+The following command line argument options are ignored if a configuration file is passed:
+
+* `--train_data_dir`
+* `--reg_data_dir`
+* `--in_json`
+
+The following command line argument options are given priority over the configuration file options if both are specified simultaneously. In most cases, they have the same names as the corresponding options in the configuration file.
+
+| Command Line Argument Option   | Prioritized Configuration File Option |
+| ------------------------------- | ------------------------------------- |
+| `--bucket_no_upscale`           |                                       |
+| `--bucket_reso_steps`           |                                       |
+| `--caption_dropout_every_n_epochs` |                                       |
+| `--caption_dropout_rate`        |                                       |
+| `--caption_extension`           |                                       |
+| `--caption_tag_dropout_rate`    |                                       |
+| `--color_aug`                   |                                       |
+| `--dataset_repeats`             | `num_repeats`                          |
+| `--enable_bucket`               |                                       |
+| `--face_crop_aug_range`         |                                       |
+| `--flip_aug`                    |                                       |
+| `--keep_tokens`                 |                                       |
+| `--min_bucket_reso`              |                                       |
+| `--random_crop`                 |                                       |
+| `--resolution`                  |                                       |
+| `--shuffle_caption`             |                                       |
+| `--train_batch_size`            | `batch_size`                           |
+
+## Error Guide
+
+Currently, we are using an external library to check if the configuration file is written correctly, but the development has not been completed, and there is a problem that the error message is not clear. In the future, we plan to improve this problem.
+
+As a temporary measure, we will list common errors and their solutions. If you encounter an error even though it should be correct or if the error content is not understandable, please contact us as it may be a bug.
+
+* `voluptuous.error.MultipleInvalid: required key not provided @ ...`: This error occurs when a required option is not provided. It is highly likely that you forgot to specify the option or misspelled the option name.
+  * The error location is indicated by `...` in the error message. For example, if you encounter an error like `voluptuous.error.MultipleInvalid: required key not provided @ data['datasets'][0]['subsets'][0]['image_dir']`, it means that the `image_dir` option does not exist in the 0th `subsets` of the 0th `datasets` setting.
+* `voluptuous.error.MultipleInvalid: expected int for dictionary value @ ...`: This error occurs when the specified value format is incorrect. It is highly likely that the value format is incorrect. The `int` part changes depending on the target option. The example configurations in this README may be helpful.
+* `voluptuous.error.MultipleInvalid: extra keys not allowed @ ...`: This error occurs when there is an option name that is not supported. It is highly likely that you misspelled the option name or mistakenly included it.
+
+

From 5f6196e4c71763250da316cc0f4ce15db1696017 Mon Sep 17 00:00:00 2001
From: Kohya S <ykumeykume@gmail.com>
Date: Wed, 20 Mar 2024 16:35:23 +0900
Subject: [PATCH 14/16] update readme

---
 README.md | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index d0320403..f8601c1b 100644
--- a/README.md
+++ b/README.md
@@ -33,6 +33,7 @@ Most of the documents are written in Japanese.
 * [Training guide - common](./docs/train_README-ja.md) : data preparation, options etc... 
   * [Chinese version](./docs/train_README-zh.md)
 * [Dataset config](./docs/config_README-ja.md) 
+  * [English version](./docs/config_README-en.md)
 * [DreamBooth training guide](./docs/train_db_README-ja.md)
 * [Step by Step fine-tuning guide](./docs/fine_tune_README_ja.md):
 * [training LoRA](./docs/train_network_README-ja.md)
@@ -263,6 +264,8 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 - The support for v3 repositories is added to `tag_image_by_wd14_tagger.py` (`--onnx` option only). PR [#1192](https://github.com/kohya-ss/sd-scripts/pull/1192) Thanks to sdbds!
   - Onnx may need to be updated. Onnx is not installed by default, so please install or update it with `pip install onnx==1.15.0 onnxruntime-gpu==1.17.1` etc. Please also check the comments in `requirements.txt`.
 - The model is now saved in the subdirectory as `--repo_id` in `tag_image_by_wd14_tagger.py` . This caches multiple repo_id models. Please delete unnecessary files under `--model_dir`.
+- The options `--noise_offset_random_strength` and `--ip_noise_gamma_random_strength` are added to each training script. These options can be used to vary the noise offset and ip noise gamma in the range of 0 to the specified value. PR [#1177](https://github.com/kohya-ss/sd-scripts/pull/1177) Thanks to KohakuBlueleaf!
+- The [English version of the dataset settings documentation](./docs/config_README-en.md) is added. PR [#1175](https://github.com/kohya-ss/sd-scripts/pull/1175) Thanks to darkstorm2150!
 
 - Colab での動作時、ログ出力で停止してしまうようです。学習スクリプトに `--console_log_simple` オプションを指定し、rich のロギングを無効してお試しください。
 - `train_network.py` および `sdxl_train_network.py` で、学習したモデルのメタデータに一部のデータセット設定が記録されるよう修正しました（`caption_prefix`、`caption_suffix`、`keep_tokens_separator`、`secondary_separator`、`enable_wildcard`）。
@@ -274,7 +277,8 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 - `tag_image_by_wd14_tagger.py` で v3 のリポジトリがサポートされました（`--onnx` 指定時のみ有効）。 PR [#1192](https://github.com/kohya-ss/sd-scripts/pull/1192) sdbds 氏に感謝します。
   - Onnx のバージョンアップが必要になるかもしれません。デフォルトでは Onnx はインストールされていませんので、`pip install onnx==1.15.0 onnxruntime-gpu==1.17.1` 等でインストール、アップデートしてください。`requirements.txt` のコメントもあわせてご確認ください。
 - `tag_image_by_wd14_tagger.py` で、モデルを`--repo_id` のサブディレクトリに保存するようにしました。これにより複数のモデルファイルがキャッシュされます。`--model_dir` 直下の不要なファイルは削除願います。
-
+- 各学習スクリプトに、noise offset、ip noise gammaを、それぞれ 0~指定した値の範囲で変動させるオプション `--noise_offset_random_strength` および `--ip_noise_gamma_random_strength` が追加されました。 PR [#1177](https://github.com/kohya-ss/sd-scripts/pull/1177) KohakuBlueleaf 氏に感謝します。
+- データセット設定の[英語版ドキュメント](./docs/config_README-en.md) が追加されました。PR [#1175](https://github.com/kohya-ss/sd-scripts/pull/1175) darkstorm2150 氏に感謝します。
 
 
 #### Example of dataset settings / データセット設定の記述例:

From 3b0db0f17f46148abe345c5cdce76ff707bdccd3 Mon Sep 17 00:00:00 2001
From: Kohya S <ykumeykume@gmail.com>
Date: Wed, 20 Mar 2024 17:45:35 +0900
Subject: [PATCH 15/16] update readme

---
 README.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index f8601c1b..81c176a7 100644
--- a/README.md
+++ b/README.md
@@ -266,6 +266,8 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 - The model is now saved in the subdirectory as `--repo_id` in `tag_image_by_wd14_tagger.py` . This caches multiple repo_id models. Please delete unnecessary files under `--model_dir`.
 - The options `--noise_offset_random_strength` and `--ip_noise_gamma_random_strength` are added to each training script. These options can be used to vary the noise offset and ip noise gamma in the range of 0 to the specified value. PR [#1177](https://github.com/kohya-ss/sd-scripts/pull/1177) Thanks to KohakuBlueleaf!
 - The [English version of the dataset settings documentation](./docs/config_README-en.md) is added. PR [#1175](https://github.com/kohya-ss/sd-scripts/pull/1175) Thanks to darkstorm2150!
+- The `.toml` file for the dataset config is now read in UTF-8 encoding. PR [#1167](https://github.com/kohya-ss/sd-scripts/pull/1167) Thanks to Horizon1704!
+
 
 - Colab での動作時、ログ出力で停止してしまうようです。学習スクリプトに `--console_log_simple` オプションを指定し、rich のロギングを無効してお試しください。
 - `train_network.py` および `sdxl_train_network.py` で、学習したモデルのメタデータに一部のデータセット設定が記録されるよう修正しました（`caption_prefix`、`caption_suffix`、`keep_tokens_separator`、`secondary_separator`、`enable_wildcard`）。
@@ -279,7 +281,7 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 - `tag_image_by_wd14_tagger.py` で、モデルを`--repo_id` のサブディレクトリに保存するようにしました。これにより複数のモデルファイルがキャッシュされます。`--model_dir` 直下の不要なファイルは削除願います。
 - 各学習スクリプトに、noise offset、ip noise gammaを、それぞれ 0~指定した値の範囲で変動させるオプション `--noise_offset_random_strength` および `--ip_noise_gamma_random_strength` が追加されました。 PR [#1177](https://github.com/kohya-ss/sd-scripts/pull/1177) KohakuBlueleaf 氏に感謝します。
 - データセット設定の[英語版ドキュメント](./docs/config_README-en.md) が追加されました。PR [#1175](https://github.com/kohya-ss/sd-scripts/pull/1175) darkstorm2150 氏に感謝します。
-
+- データセット設定の `.toml` ファイルが UTF-8 encoding で読み込まれるようになりました。PR [#1167](https://github.com/kohya-ss/sd-scripts/pull/1167) Horizon1704 氏に感謝します。
 
 #### Example of dataset settings / データセット設定の記述例:
 

From 855add067b06464eaa47ed55840da0f17d675762 Mon Sep 17 00:00:00 2001
From: Kohya S <ykumeykume@gmail.com>
Date: Wed, 20 Mar 2024 18:14:05 +0900
Subject: [PATCH 16/16] update option help and readme

---
 README.md             | 7 +++++--
 library/train_util.py | 8 ++++----
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index 81c176a7..804bad84 100644
--- a/README.md
+++ b/README.md
@@ -253,6 +253,7 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 ### Working in progress
 
 - Colab seems to stop with log output. Try specifying `--console_log_simple` option in the training script to disable rich logging.
+- The `.toml` file for the dataset config is now read in UTF-8 encoding. PR [#1167](https://github.com/kohya-ss/sd-scripts/pull/1167) Thanks to Horizon1704!
 - `train_network.py` and `sdxl_train_network.py` are modified to record some dataset settings in the metadata of the trained model (`caption_prefix`, `caption_suffix`, `keep_tokens_separator`, `secondary_separator`, `enable_wildcard`).
 - Some features are added to the dataset subset settings.
   - `secondary_separator` is added to specify the tag separator that is not the target of shuffling or dropping. 
@@ -266,10 +267,11 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 - The model is now saved in the subdirectory as `--repo_id` in `tag_image_by_wd14_tagger.py` . This caches multiple repo_id models. Please delete unnecessary files under `--model_dir`.
 - The options `--noise_offset_random_strength` and `--ip_noise_gamma_random_strength` are added to each training script. These options can be used to vary the noise offset and ip noise gamma in the range of 0 to the specified value. PR [#1177](https://github.com/kohya-ss/sd-scripts/pull/1177) Thanks to KohakuBlueleaf!
 - The [English version of the dataset settings documentation](./docs/config_README-en.md) is added. PR [#1175](https://github.com/kohya-ss/sd-scripts/pull/1175) Thanks to darkstorm2150!
-- The `.toml` file for the dataset config is now read in UTF-8 encoding. PR [#1167](https://github.com/kohya-ss/sd-scripts/pull/1167) Thanks to Horizon1704!
+- The options `--save_state_on_train_end` are added to each training script. PR [#1168](https://github.com/kohya-ss/sd-scripts/pull/1168) Thanks to gesen2egee!
 
 
 - Colab での動作時、ログ出力で停止してしまうようです。学習スクリプトに `--console_log_simple` オプションを指定し、rich のロギングを無効してお試しください。
+- データセット設定の `.toml` ファイルが UTF-8 encoding で読み込まれるようになりました。PR [#1167](https://github.com/kohya-ss/sd-scripts/pull/1167) Horizon1704 氏に感謝します。
 - `train_network.py` および `sdxl_train_network.py` で、学習したモデルのメタデータに一部のデータセット設定が記録されるよう修正しました（`caption_prefix`、`caption_suffix`、`keep_tokens_separator`、`secondary_separator`、`enable_wildcard`）。
 - データセットのサブセット設定にいくつかの機能を追加しました。
   - シャッフルの対象とならないタグ分割識別子の指定 `secondary_separator` を追加しました。`secondary_separator=";;;"` のように指定します。`secondary_separator` で区切ることで、その部分はシャッフル、drop 時にまとめて扱われます。詳しくは記述例をご覧ください。
@@ -281,7 +283,8 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 - `tag_image_by_wd14_tagger.py` で、モデルを`--repo_id` のサブディレクトリに保存するようにしました。これにより複数のモデルファイルがキャッシュされます。`--model_dir` 直下の不要なファイルは削除願います。
 - 各学習スクリプトに、noise offset、ip noise gammaを、それぞれ 0~指定した値の範囲で変動させるオプション `--noise_offset_random_strength` および `--ip_noise_gamma_random_strength` が追加されました。 PR [#1177](https://github.com/kohya-ss/sd-scripts/pull/1177) KohakuBlueleaf 氏に感謝します。
 - データセット設定の[英語版ドキュメント](./docs/config_README-en.md) が追加されました。PR [#1175](https://github.com/kohya-ss/sd-scripts/pull/1175) darkstorm2150 氏に感謝します。
-- データセット設定の `.toml` ファイルが UTF-8 encoding で読み込まれるようになりました。PR [#1167](https://github.com/kohya-ss/sd-scripts/pull/1167) Horizon1704 氏に感謝します。
+- 各学習スクリプトに、学習終了時に state を保存する `--save_state_on_train_end` オプションが追加されました。 PR [#1168](https://github.com/kohya-ss/sd-scripts/pull/1168) gesen2egee 氏に感謝します。
+
 
 #### Example of dataset settings / データセット設定の記述例:
 
diff --git a/library/train_util.py b/library/train_util.py
index 23961505..a13985ee 100644
--- a/library/train_util.py
+++ b/library/train_util.py
@@ -2936,13 +2936,13 @@ def add_training_arguments(parser: argparse.ArgumentParser, support_dreambooth:
     parser.add_argument(
         "--save_state",
         action="store_true",
-        help="save training state additionally (including optimizer states etc.) / optimizerなど学習状態も含めたstateを追加で保存する",
+        help="save training state additionally (including optimizer states etc.) when saving model / optimizerなど学習状態も含めたstateをモデル保存時に追加で保存する",
     )
     parser.add_argument(
         "--save_state_on_train_end",
         action="store_true",
-        help="save training state additionally (including optimizer states etc.) on train end / optimizerなど学習状態も含めたstateを追加で保存する",
-    )   
+        help="save training state (including optimizer states etc.) on train end / optimizerなど学習状態も含めたstateを学習完了時に保存する",
+    )
     parser.add_argument("--resume", type=str, default=None, help="saved state to resume training / 学習再開するモデルのstate")
 
     parser.add_argument("--train_batch_size", type=int, default=1, help="batch size for training / 学習時のバッチサイズ")
@@ -3550,7 +3550,7 @@ def read_config_from_file(args: argparse.Namespace, parser: argparse.ArgumentPar
         exit(1)
 
     logger.info(f"Loading settings from {config_path}...")
-    with open(config_path, "r", encoding='utf-8') as f:
+    with open(config_path, "r", encoding="utf-8") as f:
         config_dict = toml.load(f)
 
     # combine all sections into one