Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[img2imgalt] [UI Imporve] Overriding some params by default for convenience. #2375

Merged
merged 2 commits into from
Oct 13, 2022
Merged

[img2imgalt] [UI Imporve] Overriding some params by default for convenience. #2375

merged 2 commits into from
Oct 13, 2022

Conversation

aoirusann
Copy link
Contributor

Defect

According to wiki and my testing, these params should be fixed by default:

  • Sampling method: must be Euler
  • prompt/negative prompt: should be the same as original prompt/negative prompt.
  • Samping Steps: should be the same as decode steps
  • Denoising Strength: should be 1.0

Manual adjustments for these params should be saved.

Improvements

  • Automatically override Sampling method
  • Add checkboxes for overriding prompt, steps and strength.

Preview

image

The advice comes from #1852 .

@aoirusann
[img2imgalt] Add override in UI for convenience.
144d885 
Some params in img2imgalt are fixed,
such as `Sampling method` and  `Denosing Strength`.
And some params should be matched with those in decode, such as `steps`.
@aoirusann
Copy link
Contributor Author

@x02Sylvie might be interested.

@Ehplodor
Copy link

I know the sampler should be Euler, because that is the one user for noise re-encoding in IMG2IMG alternative script. However I consistently get good, often better, results with other samplers as well, on the decode part. I am simply hoping that this PR does not block other samplers ?

@aoirusann
Copy link
Contributor Author

I know the sampler should be Euler, because that is the one user for noise re-encoding in IMG2IMG alternative script. However I consistently get good, often better, results with other samplers as well, on the decode part. I am simply hoping that this PR does not block other samplers ?

@Ehplodor I'm sorry, I took it for granted that it had to be Euler. After some testing, I agree that other samplers should not be blocked.
This is what it looks like now:
image

@AUTOMATIC1111 AUTOMATIC1111 merged commit e548fc4 into AUTOMATIC1111:master Oct 13, 2022
@C43H66N12O12S2 C43H66N12O12S2 mentioned this pull request Oct 15, 2022
Closed
@Ehplodor Ehplodor mentioned this pull request Oct 18, 2022
Closed
@Ehplodor Ehplodor mentioned this pull request Nov 3, 2022
Open
1 task
DrakeRichards pushed a commit to DrakeRichards/stable-diffusion-webui that referenced this pull request Dec 20, 2023
@vladmandic
Merge pull request AUTOMATIC1111#2375 from vladmandic/master
9fad7d4 
update dev
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@AUTOMATIC1111 AUTOMATIC1111 AUTOMATIC1111 approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@aoirusann @Ehplodor @AUTOMATIC1111