Conversation
This may be a temporary solution until #567 is addressed.
The denoising loop always computes the next step in float32, so this would fail when using `bfloat16`.
|
The documentation is not available anymore as the PR was closed or merged. |
pcuenca
commented
Sep 21, 2022
| ) | ||
| if latents is None: | ||
| latents = jax.random.normal(prng_seed, shape=latents_shape, dtype=self.dtype) | ||
| latents = jax.random.normal(prng_seed, shape=latents_shape, dtype=jnp.float32) |
Member
Author
There was a problem hiding this comment.
The alternative to this, I think, would be to prepare the scheduler parameters using the same dtype as the model. We can do that in a follow-up PR.
Contributor
There was a problem hiding this comment.
Sounds good, and agree we should check model dtype here.
patil-suraj
approved these changes
Sep 21, 2022
| ) | ||
| if latents is None: | ||
| latents = jax.random.normal(prng_seed, shape=latents_shape, dtype=self.dtype) | ||
| latents = jax.random.normal(prng_seed, shape=latents_shape, dtype=jnp.float32) |
Contributor
There was a problem hiding this comment.
Sounds good, and agree we should check model dtype here.
yoonseokjin
pushed a commit
to yoonseokjin/diffusers
that referenced
this pull request
Dec 25, 2023
* Fix typo in docstring. * Allow dtype to be overridden on model load. This may be a temporary solution until huggingface#567 is addressed. * Create latents in float32 The denoising loop always computes the next step in float32, so this would fail when using `bfloat16`.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 replaces #581, which was reviewed by @patil-suraj.