Fix dylora create_modules error when training sdxl #1126
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
I didn't test DyLoRA with SDXL. Thank you for this! |
nana0304
pushed a commit
to nana0304/sd-scripts
that referenced
this pull request
Jun 4, 2025
Fix dylora create_modules error when training sdxl
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fix
networks/dyrola.pyso that it works withsdxl_train_network.py.In the latest implementation, when defining
self.text_encoder_lorasinside the__init__function ofDyLoRANetworkinnetwork/dylora.py, thecreate_modulesfunction expects an input of typeCLIPTextModel. However, the actual input is either aList[CLIPTextModel]orCLIPTextModel, leading to a bug when the input is aList[CLIPTextModel]. This has been corrected to align with the definition ofself.text_encoder_lorasinnetwork/lora.py, allowing thetext_encoderto accept inputs of typeList[CLIPTextModel].