[AudioLDM 2] Pipeline fixes #4738
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
sanchit-gandhi
commented
Aug 23, 2023
sanchit-gandhi
changed the title
|
The documentation is not available anymore as the PR was closed or merged. |
sanchit-gandhi
commented
Aug 23, 2023
| @@ -469,29 +469,6 @@ def test_save_load_optional_components(self): | |||
| # increase tolerance from 1e-4 -> 2e-4 to account for large composite model | |||
| super().test_save_load_optional_components(expected_max_difference=2e-4) | |||
|
|
|||
| def test_to_dtype(self): | |||
There was a problem hiding this comment.
Now that huggingface/transformers#25682 is merged, overriding this test won't be necessary - CLAP will always have the default dtype of float32
|
Ready for review @sayakpaul! |
patrickvonplaten
approved these changes
Aug 23, 2023
5 tasks
yoonseokjin
pushed a commit
to yoonseokjin/diffusers
that referenced
this pull request
Dec 25, 2023
* fix docs * fix unet docs * use image output for latents * fix hub checkpoints * fix pipeline example * update example * return_dict = False * revert image pipeline output * revert doc changes * remove dtype test * make style * remove docstring updates * remove unet docstring update * Empty commit to re-trigger CI * fix cpu offload * fix dtype test * add offload test
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
* fix docs * fix unet docs * use image output for latents * fix hub checkpoints * fix pipeline example * update example * return_dict = False * revert image pipeline output * revert doc changes * remove dtype test * make style * remove docstring updates * remove unet docstring update * Empty commit to re-trigger CI * fix cpu offload * fix dtype test * add offload test
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.
What does this PR do?
Pipeline fixes:
return_dict=Falsein the UNet to allow fortorch.compileUse theImagePipelineOutputwhen we return latents (not theAudioPipelineOutput)Test fixes: