fix EDMDiscretization sigma_min for correct sampling noise scheduling #114
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
|
Good catch, thanks @johngull |
JimmyDefends
added a commit
to JimmyDefends/generative-models
that referenced
this pull request
Sep 27, 2023
…heduling (Stability-AI#114)" This reverts commit 477d8b9.
LinearFalcon
pushed a commit
to LinearFalcon/generative-models
that referenced
this pull request
Jul 6, 2024
SevanBrodjian
pushed a commit
to SevanBrodjian/sd-latent-exploration
that referenced
this pull request
Aug 12, 2024
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Outdated suggestions cannot be applied.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.
I found a mistake in implementing "Elucidating the Design Space of Diffusion-Based Generative Models" noise scheduling.
In the EDMDiscretization you use
sigma_min=0.02, but the value used in the original paper is 0.002.This fix may influence the final quality of the sampling process.
Vital that you DO NOT need to retrain models because of this fix. The EDMSampling contains correct sampling of sigmas during training.
