Refactor LoraAdapter and its SD implementation #190
Merged
Conversation
This file contains 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
limiteinductive
force-pushed
the
pr/add-conv-lora
branch
2 times, most recently
from
cda03a7 to
e299a53
Compare
deltheil
reviewed
Jan 18, 2024
limiteinductive
force-pushed
the
pr/add-conv-lora
branch
from
e299a53 to
3b67d76
Compare
deltheil
previously approved these changes
Jan 18, 2024
limiteinductive
force-pushed
the
pr/add-conv-lora
branch
from
3b67d76 to
def2c60
Compare
deltheil
approved these changes
Jan 18, 2024
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Outdated suggestions cannot be applied.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.
Currently, the Lora implementation only allows converting/loading LoRAs for SD1 that target only Linear layers. It has been a long-standing issue that we should be able to load LoRAs commonly found on CivitAI hubs (generally trained with https://github.com/AUTOMATIC1111/stable-diffusion-webui or with https://github.com/KohakuBlueleaf/LyCORIS)
#116
In the following PRs, we will add the possibility to load/unload multiple LoRAs for inference.
The previous training scripts for LoRA are now obsolete; they will be added back in a follow-up PR.