Merge pull request kohya-ss#1085 from kohya-ss/dev

Dev

Author: kohya-ss

README.md

@@ -249,6 +249,18 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum
 
 ## Change History
 
+### Jan 27, 2024 / 2024/1/27: v0.8.3
+
+- Fixed a bug that the training crashes when `--fp8_base` is specified with `--save_state`. PR [#1079](https://github.com/kohya-ss/sd-scripts/pull/1079) Thanks to feffy380!
+  - `safetensors` is updated. Please see [Upgrade](#upgrade) and update the library.
+- Fixed a bug that the training crashes when `network_multiplier` is specified with multi-GPU training. PR [#1084](https://github.com/kohya-ss/sd-scripts/pull/1084) Thanks to fireicewolf!
+- Fixed a bug that the training crashes when training ControlNet-LLLite.
+
+- `--fp8_base` 指定時に `--save_state` での保存がエラーになる不具合が修正されました。 PR [#1079](https://github.com/kohya-ss/sd-scripts/pull/1079) feffy380 氏に感謝します。
+  - `safetensors` がバージョンアップされていますので、[Upgrade](#upgrade) を参照し更新をお願いします。
+- 複数 GPU での学習時に `network_multiplier` を指定するとクラッシュする不具合が修正されました。 PR [#1084](https://github.com/kohya-ss/sd-scripts/pull/1084) fireicewolf 氏に感謝します。
+- ControlNet-LLLite の学習がエラーになる不具合を修正しました。 
+
 ### Jan 23, 2024 / 2024/1/23: v0.8.2
 
 - [Experimental] The `--fp8_base` option is added to the training scripts for LoRA etc. The base model (U-Net, and Text Encoder when training modules for Text Encoder) can be trained with fp8. PR [#1057](https://github.com/kohya-ss/sd-scripts/pull/1057) Thanks to KohakuBlueleaf!

library/train_util.py

@@ -1774,6 +1774,7 @@ def __init__(
             tokenizer,
             max_token_length,
             resolution,
+            network_multiplier,
             enable_bucket,
             min_bucket_reso,
             max_bucket_reso,

requirements.txt

@@ -8,7 +8,7 @@ einops==0.6.1
 pytorch-lightning==1.9.0
 # bitsandbytes==0.39.1
 tensorboard==2.10.1
-safetensors==0.3.1
+safetensors==0.4.2
 # gradio==3.16.2
 altair==4.2.2
 easygui==0.98.3

train_network.py

@@ -774,7 +774,7 @@ def remove_model(old_ckpt_name):
                         else:
                             raise NotImplementedError("multipliers for each sample is not supported yet")
                         # print(f"set multiplier: {multipliers}")
-                        network.set_multiplier(multipliers)
+                        accelerator.unwrap_model(network).set_multiplier(multipliers)
 
                     with torch.set_grad_enabled(train_text_encoder), accelerator.autocast():
                         # Get the text embedding for conditioning