GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — Add PLMS sampling and do one 2x size batch per sampling step by crowsonkb · Pull Request #51 · CompVis/latent-diffusion

Conversation

@crowsonkb

@crowsonkb crowsonkb commented Apr 15, 2022

Copy link
Copy Markdown
Contributor

Changes in this PR:

  • PLMS sampling (https://arxiv.org/abs/2202.09778) for high quality outputs in 50 steps or acceptable quality outputs in 25-35 steps
  • The sampling code for classifier-free guidance did two forward passes per sampling step, this PR combines them into one batch.

Sorry, something went wrong.

Uh oh!

There was an error while loading. Please reload this page.
averkij, huameinan219, bjmeo8, q121q, pseudo-usama, XuZhang1211, and hadipash reacted with thumbs up emoji
All reactions
  • 👍 7 reactions
crowsonkb added 4 commits April 4, 2022 14:45
@crowsonkb
Add PLMS sampling
f0c4e09
@crowsonkb
Combine the two classifier-free guidance model outputs into a single …
66df437 
…batch
@crowsonkb
Alter credit in README
c8122e7
@crowsonkb
Merge branch 'CompVis:main' into main
add3f1b
srelbo
srelbo reviewed Apr 15, 2022
View reviewed changes
Comment thread README.md
As a rule of thumb, higher values of `scale` produce better samples at the cost of a reduced output diversity.
Furthermore, increasing `ddim_steps` generally also gives higher quality samples, but returns are diminishing for values > 250.
Fast sampling (i.e. low values of `ddim_steps`) while retaining good quality can be achieved by using `--ddim_eta 0.0`.
Faster sampling (i.e. even lower values of `ddim_steps`) while retaining good quality can be achieved by using `--ddim_eta 0.0` and `--plms` (see [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://arxiv.org/abs/2202.09778)).

@srelbo srelbo Apr 15, 2022

Copy link
Copy Markdown

There was a problem hiding this comment.

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Wow, love it!

Sorry, something went wrong.

Uh oh!

There was an error while loading. Please reload this page.
All reactions
@rromb

rromb commented Apr 15, 2022

Copy link
Copy Markdown
Collaborator

Thank you very much, this looks great :)
All reactions

Sorry, something went wrong.

Uh oh!

There was an error while loading. Please reload this page.
@rromb
rromb merged commit 4c8bff3 into CompVis:main Apr 15, 2022
@kaihe kaihe mentioned this pull request Apr 18, 2022
terminate called after throwing an instance of 'c10::Error' #17
Closed
@patrickvonplaten patrickvonplaten mentioned this pull request Aug 16, 2022
[PNDM] Stable diffusion huggingface/diffusers#186
Merged
@Ahmer-444 Ahmer-444 mentioned this pull request Oct 12, 2022
CompVis/Stable Diffusion/LDM - Diffusion Models Implementation Support facebookincubator/AITemplate#39
Open
YiqiaoYAN pushed a commit to YiqiaoYAN/latent_diffusion that referenced this pull request Apr 23, 2025
@rromb
Merge pull request CompVis#51 from crowsonkb/main
38194d3 
Add PLMS sampling and do one 2x size batch per sampling step
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

1 more reviewer
@srelbo srelbo srelbo left review comments
Reviewers whose approvals may not affect merge requirements

Uh oh!

There was an error while loading. Please reload this page.

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Uh oh!

There was an error while loading. Please reload this page.

3 participants

@crowsonkb @rromb @srelbo
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.
You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.