Merge pull request #1085 from kohya-ss/dev

Dev
update README.md
2026-04-08 14:34:23 +00:00 · 2024-01-27 18:32:06 +09:00 · 2024-01-27 18:31:01 +09:00 · 2024-01-27 18:23:52 +09:00 · 2024-01-27 18:22:00 +09:00 · 2024-01-26 22:34:35 +09:00
4 changed files with 15 additions and 2 deletions
--- a/README.md
+++ b/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!
--- a/library/train_util.py
+++ b/library/train_util.py
@@ -1774,6 +1774,7 @@ class ControlNetDataset(BaseDataset):
            tokenizer,
            max_token_length,
            resolution,
+            network_multiplier,
            enable_bucket,
            min_bucket_reso,
            max_bucket_reso,
--- a/requirements.txt
+++ b/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
--- a/train_network.py
+++ b/train_network.py
@@ -774,7 +774,7 @@ class NetworkTrainer:
                        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
Author	SHA1	Message	Date
Kohya S	cd19df49cd	Merge pull request #1085 from kohya-ss/dev Dev	2024-01-27 18:32:06 +09:00
Kohya S	736365bdd5	update README.md	2024-01-27 18:31:01 +09:00
Kohya S	6ceedb9448	Merge branch 'main' into dev	2024-01-27 18:23:52 +09:00
Kohya S	930a3912a7	Merge pull request #1084 from fireicewolf/devel Fix network multiplier cause crashed while use multi-GPUs	2024-01-27 18:22:00 +09:00
Kohya S	cf790d87c4	Merge pull request #1079 from feffy380/fix/fp8savestate Update safetensors to fix a crash with `--fp8_base --save_state`	2024-01-26 22:34:35 +09:00
DukeG	4e67fb8444	test	2024-01-26 20:22:49 +08:00
DukeG	50f631c768	test	2024-01-26 20:02:48 +08:00
DukeG	85bc371ebc	test	2024-01-26 18:58:47 +08:00
feffy380	322ee52c77	Update requirements.txt Update safetensors to fix a crash when using `--fp8_base --save_state`	2024-01-25 19:15:53 +01:00
Kohya S	c576f80639	Fix ControlNetLLLite training issue #1069	2024-01-25 18:43:07 +09:00