[draft] add LoRA layer support to IPU SD Pipeline #25
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
roscisz
force-pushed
the
roscisz/sd_lora_inference
branch
from
42e26e6 to
dab5b83
Compare
roscisz
force-pushed
the
roscisz/sd_lora_inference
branch
from
dab5b83 to
e1ccb00
Compare
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Outdated suggestions cannot be applied.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.
What does this PR do?
Adds LoRA layer loading and inference based on the existing diffusers mechanisms:
LoRACrossAttnProcessor and load_attn_procs
Removes unused dim var
Tested with our SD example for SSF, which is based on optimum-graphcore==0.6.1. Upgrading to the current optimum-graphcore isn't straightforward, hence this branch requires rebasing and testing against main.Tested with our SD example for SSF.
TODO: