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: docs/config_README-en.md
+5-8Lines changed: 5 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,9 +1,6 @@
1
-
Original Source by kohya-ss
1
+
First version: A.I Translation by Model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO, editing by Darkstorm2150
2
2
3
-
First version:
4
-
A.I Translation by Model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO, editing by Darkstorm2150
5
-
6
-
Some parts are manually added.
3
+
Document is updated and maintained manually.
7
4
8
5
# Config Readme
9
6
@@ -267,10 +264,10 @@ The following command line argument options are ignored if a configuration file
267
264
*`--reg_data_dir`
268
265
*`--in_json`
269
266
270
-
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.
267
+
For the command line options listed below, if an option is specified in both the command line arguments and the configuration file, the value from the configuration file will be given priority. Unless otherwise noted, the option names are the same.
271
268
272
-
| Command Line Argument Option |Prioritized Configuration File Option |
-**`--controlnet_model_name_or_path`**: Specifies the path to a ControlNet model compatible with FLUX.1. This allows for training a LoRA that works in conjunction with ControlNet. This is an advanced feature and requires a compatible ControlNet model.
647
+
648
+
-**`--loss_type`**: Specifies the loss function for training. The default is `l2`.
649
+
-`l1`: L1 loss.
650
+
-`l2`: L2 loss (mean squared error).
651
+
-`huber`: Huber loss.
652
+
-`smooth_l1`: Smooth L1 loss.
653
+
654
+
-**`--huber_schedule`**, **`--huber_c`**, **`--huber_scale`**: These are parameters for Huber loss. They are used when `--loss_type` is set to `huber` or `smooth_l1`.
655
+
656
+
-**`--t5xxl_max_token_length`**: Specifies the maximum token length for the T5-XXL text encoder. For details, refer to the [`sd3_train_network.md` guide](sd3_train_network.md).
657
+
658
+
-**`--weighting_scheme`**, **`--logit_mean`**, **`--logit_std`**, **`--mode_scale`**: These options allow you to adjust the loss weighting for each timestep. For details, refer to the [`sd3_train_network.md` guide](sd3_train_network.md).
659
+
660
+
-**`--fused_backward_pass`**: Fuses the backward pass and optimizer step to reduce VRAM usage. For details, refer to the [`sdxl_train_network.md` guide](sdxl_train_network.md).
0 commit comments