Use torch.special.expm1
#6388
Open
Use torch.special.expm1
#6388
+1
−1
Conversation
This file contains 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
This function provides greater precision than `exp(x) - 1` for small values of `x`. Found with TorchFix https://github.com/pytorch-labs/torchfix/
blepping
reviewed
Jan 8, 2025
| @@ -40,7 +40,7 @@ def get_sigmas_polyexponential(n, sigma_min, sigma_max, rho=1., device='cpu'): | |||
| def get_sigmas_vp(n, beta_d=19.9, beta_min=0.1, eps_s=1e-3, device='cpu'): | |||
| """Constructs a continuous VP noise schedule.""" | |||
| t = torch.linspace(1, eps_s, n, device=device) | |||
| sigmas = torch.sqrt(torch.exp(beta_d * t ** 2 / 2 + beta_min * t) - 1) | |||
| sigmas = torch.sqrt(torch.special.expm1(beta_d * t ** 2 / 2 + beta_min * t)) | |||
There was a problem hiding this comment.
You should just be able to do:
sigmas = torch.sqrt((beta_d * t ** 2 / 2 + beta_min * t).expm1())That's the approach other stuff in ComfyUI that uses expm1 takes (see k_diffusion/sampling.py)
There was a problem hiding this comment.
That's also fine, doesn't matter.
There was a problem hiding this comment.
doesn't matter.
The result is the same, generally it's easier from a code maintenance perspective if different parts of the code implementing something don't each use a different approach.
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Outdated suggestions cannot be applied.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.
This function provides greater precision than
exp(x) - 1for small values ofx.Found with TorchFix https://github.com/pytorch-labs/torchfix/