Multi-Resolution Noise #471
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
|
Thank you for this! This is interesting, and the implementation looks quite good! I will test and merge as soon as I have time. |
|
I've merged. Thank you again for this! |
|
@kohya-ss and @pamparamm Quick question... when using multi-res should the original noise option be left to 0... or is it still required to be set? |
|
@pamparamm Can you post some examples showing the effect of this option? |
|
Oh cool! Fun to see this in use. 0.8 was from early tests and I've since (like you) figured out that much lower values work better :) |
wkpark
pushed a commit
to wkpark/sd-scripts
that referenced
this pull request
Feb 27, 2024
…alpha Change step of network_alpha from 1 to 0.1
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Outdated suggestions cannot be applied.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.
Support for multi-resolution noise (pyramid noise implementation by Jonathan Whitaker)
Works fine with LoRA and LyCORIS, haven't tested with other training approaches.
Adds new arguments:
--multires_noise_iterationsto enable multires noise (recommended values are 6-10), and--multires_noise_discount(recommended value by Jonathan is 0.8. I find that value too high for LoRAs with small datasets, so I would recommend something around 0.1-0.3).Resolves #334