[Refactor] Remove set_seed #289
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
src/diffusers/pipelines/stochatic_karras_ve/pipeline_stochastic_karras_ve.py
Show resolved
Hide resolved
|
The documentation is not available anymore as the PR was closed or merged. |
|
|
||
| raise ValueError(f"`self.tensor_format`: {self.tensor_format} is not valid.") | ||
|
|
||
| def set_seed(self, seed): |
Contributor
Author
There was a problem hiding this comment.
We should not work with set_seed(...) here as it goes against the generator design. IMO passing generators around is the correct thing to do here because:
- We cannot really pass seeds around and globally set
manual_seed(...)every time:- It's not a great design to retrieve the current seed from a generator and then pass this -> better to pass generator directly
- Flax passes PNRG keys around that can be split -> we cannot split PyTorch seeds in the same way and we cannot pass a
seedinto atorch.randn(...)function -> so let's go for the generator here
patrickvonplaten
changed the title
Co-authored-by: Pedro Cuenca <[email protected]>
| for _ in range(self.scheduler.correct_steps): | ||
| model_output = self.unet(sample, sigma_t)["sample"] | ||
| sample = self.scheduler.step_correct(model_output, sample)["prev_sample"] | ||
| sample = self.scheduler.step_correct(model_output, sample, generator=generator)["prev_sample"] |
Contributor
Author
There was a problem hiding this comment.
let's pass the generator here
|
|
||
| # 2. compute previous image: x_t -> t_t-1 | ||
| image = self.scheduler.step(model_output, t, image)["prev_sample"] | ||
| image = self.scheduler.step(model_output, t, image, generator=generator)["prev_sample"] |
Contributor
Author
There was a problem hiding this comment.
DDPM scheduler is also stochastic
anton-l
approved these changes
Aug 31, 2022
Member
anton-l
left a comment
anton-l
left a comment
There was a problem hiding this comment.
Thanks for the updates! Let's see how the tests behave now
Co-authored-by: Anton Lozhkov <[email protected]>
natolambert
pushed a commit
that referenced
this pull request
Sep 7, 2022
* [Refactor] Remove set_seed and class attributes * apply anton's suggestiosn * fix * Apply suggestions from code review Co-authored-by: Pedro Cuenca <[email protected]> * up * update * make style * Apply suggestions from code review Co-authored-by: Anton Lozhkov <[email protected]> * make fix-copies * make style * make style and new copies Co-authored-by: Pedro Cuenca <[email protected]> Co-authored-by: Anton Lozhkov <[email protected]>
PhaneeshB
added a commit
to nod-ai/diffusers
that referenced
this pull request
Mar 1, 2023
yoonseokjin
pushed a commit
to yoonseokjin/diffusers
that referenced
this pull request
Dec 25, 2023
* [Refactor] Remove set_seed and class attributes * apply anton's suggestiosn * fix * Apply suggestions from code review Co-authored-by: Pedro Cuenca <[email protected]> * up * update * make style * Apply suggestions from code review Co-authored-by: Anton Lozhkov <[email protected]> * make fix-copies * make style * make style and new copies Co-authored-by: Pedro Cuenca <[email protected]> Co-authored-by: Anton Lozhkov <[email protected]>
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.
No description provided.