Size from network weights #491
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
more dadapataion optimizer, move docs, adaptive noise scale etc.
|
Thank you for this. I think this feature is quite useful! It seems to me that the parsing |
|
Agreed on the parsing function. Cheers! |
|
I'd like to rename the option to |
|
You are always welcome to make any and all changes to my PRs. I find things that are useful to me and share them, but I am in no means a great programmer. |
|
Hi, can you give some examples or detailed description on how to use sd-webui-lora-block-weight and sd-webui-supermerger to tweak block weights? Thanks very much! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
This PR add the
--size_from_weightsflag to override--dimandblockdimsand directly loads the previously trained LoRA no matter the shape.This allows finetuning a LoRA that has been resized with
resize_lora.py(see #243) or with an unknownblockdimsshape.My Current Workflow:
dim=128resize_lora.pywith--dynamic_method="sv_ratio" --dynamic_param=(between 10 and 20)to greatly reduce size and untrained noise.There may be a better way to handle the interpretation of block lrs. since there isn't a separate function in
lora.pyto call.