Add back-compatibility to LMS timesteps #750
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. |
patil-suraj
approved these changes
Oct 6, 2022
| @@ -250,7 +256,14 @@ def add_noise( | |||
| sigmas = self.sigmas.to(original_samples.device) | |||
| schedule_timesteps = self.timesteps.to(original_samples.device) | |||
| timesteps = timesteps.to(original_samples.device) | |||
| step_indices = [(schedule_timesteps == t).nonzero().item() for t in timesteps] | |||
| if isinstance(timesteps, torch.IntTensor) or isinstance(timesteps, torch.LongTensor): | |||
| warnings.warn( | |||
There was a problem hiding this comment.
Please use the deprecate functionality here
| or isinstance(timestep, torch.IntTensor) | ||
| or isinstance(timestep, torch.LongTensor) | ||
| ): | ||
| warnings.warn( |
There was a problem hiding this comment.
Please use the deprecate functionality here: #659
| @@ -215,7 +210,18 @@ def step( | |||
|
|
|||
| if isinstance(timestep, torch.Tensor): | |||
| timestep = timestep.to(self.timesteps.device) | |||
| step_index = (self.timesteps == timestep).nonzero().item() | |||
| if ( | |||
There was a problem hiding this comment.
This could lead to some nasty silent bugs though if the "new" passed timesteps are ints instead of float no? Not sure whether this is a good idea tbh
prathikr
pushed a commit
to prathikr/diffusers
that referenced
this pull request
Oct 26, 2022
* Add back-compatibility to LMS timesteps * style
yoonseokjin
pushed a commit
to yoonseokjin/diffusers
that referenced
this pull request
Dec 25, 2023
* Add back-compatibility to LMS timesteps * style
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.
Now the legacy pipelines that support LMS won't break because of the integer timesteps :)
For instance: https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/CLIP_Guided_Stable_diffusion_with_diffusers.ipynb