Allow k pipeline to generate > 1 images #1645
Merged
Conversation
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
|
The documentation is not available anymore as the PR was closed or merged. |
patrickvonplaten
approved these changes
Dec 10, 2022
|
Thanks! |
tcapelle
pushed a commit
to tcapelle/diffusers
that referenced
this pull request
Dec 12, 2022
Allow k pipeline to generate > 1 images.
sliard
pushed a commit
to sliard/diffusers
that referenced
this pull request
Dec 21, 2022
Allow k pipeline to generate > 1 images.
yoonseokjin
pushed a commit
to yoonseokjin/diffusers
that referenced
this pull request
Dec 25, 2023
Allow k pipeline to generate > 1 images.
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Outdated suggestions cannot be applied.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.
K samplers expand the sigmas to match the batch dimension of the input sample, for example here: https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/sampling.py#LL128
However, we later expand the input inside
model_fnto account for cfg, but thetremained untouched. This fails for batch sizes > 1.Initially reported in the forums: https://discuss.huggingface.co/t/how-do-i-set-up-multiple-samples-to-display-in-a-colab-notebook-with-k-diffusion/27567