Skip to content

Commit 1fd9631

Browse files
Comments fix
Co-Authored-By: Ryan Dick <[email protected]>
1 parent 2227a23 commit 1fd9631

File tree

2 files changed

+2
-2
lines changed

2 files changed

+2
-2
lines changed

invokeai/backend/stable_diffusion/extensions/base.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -65,7 +65,7 @@ def patch_unet(self, unet: UNet2DConditionModel, original_weights: Dict[str, tor
6565
6666
Args:
6767
unet (UNet2DConditionModel): The UNet model on execution device to patch.
68-
cached_weights (Dict[str, torch.Tensor]]): A read-only copy of the model's original weights in CPU, for
68+
original_weights (Dict[str, torch.Tensor]]): A read-only copy of the model's original weights in CPU, for
6969
unpatching purposes. Extension can save tensor which being modified, if it is not saved yet, or can
7070
access original weight value.
7171
"""

invokeai/backend/stable_diffusion/extensions/lora.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -57,7 +57,7 @@ def patch_model(
5757
:param lora: LoRA model to patch in.
5858
:param lora_weight: LoRA patch weight.
5959
:param prefix: A string prefix that precedes keys used in the LoRAs weight layers.
60-
:param original_weights: TODO:
60+
:param original_weights: Dict of original weights, filled by weights which lora patches, used for unpatching.
6161
"""
6262

6363
# assert lora.device.type == "cpu"

0 commit comments

Comments
 (0)