add noise strength parameter similar to NAI #5373
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
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Outdated suggestions cannot be applied.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.
Describe what this pull request is trying to achieve.
Apply suggested changes from those discussions: #5351 #4988
Multiply initial noise N(0,1) by small factor which leads to slightly more detailed img2img results without using high denoise values.
Basically this addition allows to unbalance noise-denoise cycle in your favor.
As stated in discussions, feature is similar to NAI "noise strength", but not yet confirmed to be exactly the same
Additional notes and description of your changes
I have a strong feeling that some of those settings might be the thing, but better, since those are internal parameters for samplers. I followed them values right into the sampler, but didnt trace further.
I tried using churn, increased eta threshold and tested different values for Euler sampler but it doesnt look like more or less noise being added, it's just a bit different.
Environment this was tested in
Screenshots or videos of your changes
