resolve LoCon/LoHA/LyCORIS poblem #18
Open
+36
−9
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
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Outdated suggestions cannot be applied.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.
Hello:
I found that errors occur (IndexError: list index out of range) when using both a LoRA model and a LoCon/LoHA/LyCORIS model simultaneously, and there are also issues with incomplete model loading when using the LoCon/LoHA/LyCORIS model.
This is because you used "_11_1_proj_out" and "_11_mlp_fc2" to determine if it's the last layer of the model, but the LoCon model happens to not have the "_11_1_proj_out" and "_11_mlp_fc2" layer. As a result, your "text_model_encoder_counter" and "diffusion_model_counter" counter will calculate incorrectly, leading to a failed model loading.
Therefore, this pull request starts by checking whether there has been "_11_1_proj_out" and "_11_mlp_fc2" at the beginning of each loop to determine if the model is a LoCon/LoHA/LyCORIS model. If it is, then it will correct the calculation of your "text_model_encoder_counter" and "diffusion_model_counter" counter to solve the problem.
Another issue is that when both sub-promote blocks use the same LoRA, there is a problem of duplicate accumulation of the LoRA weight. I have also made corrections, please review and thank you.