From 175193623b39027ffcfe0c0ae250dbce564ed6ef Mon Sep 17 00:00:00 2001 From: Kohya S Date: Mon, 26 Feb 2024 23:29:41 +0900 Subject: [PATCH] update readme --- README.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/README.md b/README.md index e1b6a26c..9cc79cc0 100644 --- a/README.md +++ b/README.md @@ -249,6 +249,13 @@ ControlNet-LLLite, a novel method for ControlNet with SDXL, is added. See [docum ## Change History +### Masked loss + +`train_network.py` and `sdxl_train_network.py` now support the masked loss. `--masked_loss` option is added. + +ControlNet dataset is used to specify the mask. The mask images should be the RGB images. The pixel value 255 in R channel is treated as the mask (the loss is calculated only for the pixels with the mask), and 0 is treated as the non-mask. See details for the dataset specification in the [LLLite documentation](./docs/train_lllite_README.md#preparing-the-dataset). + + ### Working in progress - `train_network.py` and `sdxl_train_network.py` are modified to record some dataset settings in the metadata of the trained model (`caption_prefix`, `caption_suffix`, `keep_tokens_separator`, `secondary_separator`, `enable_wildcard`).