画像のアルファチャンネルをlossのマスクとして使用するオプションを追加 (#1223)

* Add alpha_mask parameter and apply masked loss

* Fix type hint in trim_and_resize_if_required function

* Refactor code to use keyword arguments in train_util.py

* Fix alpha mask flipping logic

* Fix alpha mask initialization

* Fix alpha_mask transformation

* Cache alpha_mask

* Update alpha_masks to be on CPU

* Set flipped_alpha_masks to Null if option disabled

* Check if alpha_mask is None

* Set alpha_mask to None if option disabled

* Add description of alpha_mask option to docs

library/config_util.py

@@ -78,6 +78,7 @@ class BaseSubsetParams:
     caption_tag_dropout_rate: float = 0.0
     token_warmup_min: int = 1
     token_warmup_step: float = 0
+    alpha_mask: bool = False
 
 
 @dataclass
@@ -538,6 +539,7 @@ def generate_dataset_group_by_blueprint(dataset_group_blueprint: DatasetGroupBlu
           random_crop: {subset.random_crop}
           token_warmup_min: {subset.token_warmup_min},
           token_warmup_step: {subset.token_warmup_step},
+          alpha_mask: {subset.alpha_mask},
       """
                 ),
                 "  ",