support v prediction models #57
Closed
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
|
@lllyasviel in case you were hesitant to merge just in case it didn't work, I did the circles test on WD 1.5, which uses v prediction and training went just fine. The following images are from step 3300 @ 4 batch size Also just wanted to say really nice work that you guys are doing. I must admit I was pretty surprised to see Waifu Diffusion in the research paper, pretty cool to see something I worked on actually getting used for research lol |
|
on my extended training runs vs non v prediction models, something is definitely not working right. Closing this PR until I can figure out what it is and fix it. |
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Outdated suggestions cannot be applied.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.
Add support for an arg that allows support of SD 2.x models with v prediction