feat: additional --preview-interval values - #1915
Merged
Merged
Conversation
Contributor
Author
|
@leejet, could you please explain? If I uderstood correctly, in d9b6e27/src/runtime/preview_interval.h:
So the logic is same, except the case when Got it, I forgot samplers with 2 denoising passes, like "auto denoised_opt = model(x, sigmas[i], -(i + 1));". |
This file contains hidden or 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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Additional values for
--preview-intervaloption ofsd-cli:0should preview only the last step of base-resolution sampling.Can be used in
--hiresgenerations to save (in--preview-path) the base-resolution result together with the high-resolution final image, skipping simultaneous high-resolution sampling + decoding.With feat: support numbering for preview images #1895, can save all base-resolution results of batch generations.
less than 0should decode only the-Nth single image (to preview a sample and not to slow the generation down).Additional Information
For example,
--steps 20 --hires --preview-interval 20and--steps 20 --hires --preview-interval 0make identical "base + high" images, but with less memory.Peak memory usage (SD 1.5, 256×512 -> 448×896, CPU):
Also, I have enabled "last step" preview for "high noise" video pass, but I didn't test any video generations and not sure if this is much useful.
The
sd-servershould be unaffected because it doesn't set the preview interval and uses default "every step" value.Checklist