You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+10-44Lines changed: 10 additions & 44 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -137,15 +137,16 @@ The majority of scripts is licensed under ASL 2.0 (including codes from Diffuser
137
137
138
138
## Change History
139
139
140
-
### Mar XX, 2024 / 2024/3/XX: v0.8.6
140
+
### Apr 7, 2024 / 2024-04-07: v0.8.6
141
141
142
142
#### Highlights
143
143
144
144
- The dependent libraries are updated. Please see [Upgrade](#upgrade) and update the libraries.
145
145
- Especially `imagesize` is newly added, so if you cannot update the libraries immediately, please install with `pip install imagesize==1.4.1` separately.
146
146
-`bitsandbytes==0.43.0`, `prodigyopt==1.0`, `lion-pytorch==0.0.6` are included in the requirements.txt.
147
+
-`bitsandbytes` no longer requires complex procedures as it now officially supports Windows.
147
148
- Also, the PyTorch version is updated to 2.1.2 (PyTorch does not need to be updated immediately). In the upgrade procedure, PyTorch is not updated, so please manually install or update torch, torchvision, xformers if necessary (see [Upgrade PyTorch](#upgrade-pytorch)).
148
-
- When logging to wandb is enabled, the entire command line is exposed. Therefore, it is recommended to write the API key of wandb and the token of HuggingFace in the configuration file (`.toml`). Thanks to bghira for raising the issue.
149
+
- When logging to wandb is enabled, the entire command line is exposed. Therefore, it is recommended to write wandb API key and HuggingFace token in the configuration file (`.toml`). Thanks to bghira for raising the issue.
149
150
- A warning is displayed at the start of training if such information is included in the command line.
150
151
- Also, if there is an absolute path, the path may be exposed, so it is recommended to specify a relative path or write it in the configuration file. In such cases, an INFO log is displayed.
151
152
- See [#1123](https://github.com/kohya-ss/sd-scripts/pull/1123) and PR [#1240](https://github.com/kohya-ss/sd-scripts/pull/1240) for details.
@@ -223,6 +224,7 @@ See PR [#1228](https://github.com/kohya-ss/sd-scripts/pull/1228/) for details.
@@ -315,27 +317,14 @@ The LoRA supported by `train_network.py` has been named to avoid confusion. The
315
317
316
318
In addition to 1., LoRA for Conv2d layers with 3x3 kernel
317
319
318
-
LoRA-LierLa is the default LoRA type for `train_network.py` (without `conv_dim` network arg). LoRA-LierLa can be used with [our extension](https://github.com/kohya-ss/sd-webui-additional-networks) for AUTOMATIC1111's Web UI, or with the built-in LoRA feature of the Web UI.
319
-
320
-
To use LoRA-C3Lier with Web UI, please use our extension.
LoRA-LierLa is the default LoRA type for `train_network.py` (without `conv_dim` network arg).
321
+
<!--
322
+
LoRA-LierLa can be used with [our extension](https://github.com/kohya-ss/sd-webui-additional-networks) for AUTOMATIC1111's Web UI, or with the built-in LoRA feature of the Web UI.
335
323
336
-
LoRA-C3Lierを使いWeb UIで生成するには拡張を使用してください。
324
+
To use LoRA-C3Lier with Web UI, please use our extension.
325
+
-->
337
326
338
-
## Sample image generation during training
327
+
###Sample image generation during training
339
328
A prompt file might look like this, for example
340
329
341
330
```
@@ -356,26 +345,3 @@ masterpiece, best quality, 1boy, in business suit, standing at street, looking b
356
345
*`--s` Specifies the number of steps in the generation.
357
346
358
347
The prompt weighting such as `( )` and `[ ]` are working.
359
-
360
-
## サンプル画像生成
361
-
プロンプトファイルは例えば以下のようになります。
362
-
363
-
```
364
-
# prompt 1
365
-
masterpiece, best quality, (1girl), in white shirts, upper body, looking at viewer, simple background --n low quality, worst quality, bad anatomy,bad composition, poor, low effort --w 768 --h 768 --d 1 --l 7.5 --s 28
366
-
367
-
# prompt 2
368
-
masterpiece, best quality, 1boy, in business suit, standing at street, looking back --n (low quality, worst quality), bad anatomy,bad composition, poor, low effort --w 576 --h 832 --d 2 --l 5.5 --s 40
0 commit comments