-
Notifications
You must be signed in to change notification settings - Fork 6.8k
[Community] Fix Scalings for Boundary Conditions for Consistency Training Script #6833
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.
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
base: main
Are you sure you want to change the base?
[Community] Fix Scalings for Boundary Conditions for Consistency Training Script #6833
Conversation
| c_skip_teacher, c_out_teacher = scalings_for_boundary_conditions(teacher_timesteps, args.sigma_min) | ||
| c_skip_student, c_out_student = scalings_for_boundary_conditions(student_timesteps, args.sigma_min) |
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.
Are we defaulting to reasonable values for these args?
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.
sigma_min defaults to 0.002, which is the value of
(Note that sigma_min should be a small positive value rather than 0 to avoid numerical issues when using ODE solvers.)
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.
Cool! Do you think it makes sense to add this info to the README as well?
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.
I have added documentation on the consistency training-specific hyperparameters to the README.
sayakpaul
left a comment
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.
Thank you! Just left a question.
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread. Please note that issues that do not follow the contributing guidelines are likely to be ignored. |
What does this PR do?
This PR fixes a bug in$= \epsilon$ in the original CM paper) when calculating $c_{\mbox{skip}}(\epsilon) = 1$ and $c_{\mbox{out}}(\epsilon) = 0$ . The implementation should now correctly follow the parameterization given in Appendix C of the original Consistency Models paper.
examples/research_projects/consistency_training/train_cm_ct_unconditional.pywhere thescalings_for_boundary_conditionsfunction does not take into accountsigma_min(c_skipandc_outand thus does not satisfy the consistency model boundary conditionBefore submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.
@patrickvonplaten
@sayakpaul
@patil-suraj