Make ControlNet SD Training Script torch.compile compatible
#6525
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
Signed-off-by: Suvaditya Mukherjee <[email protected]>
Signed-off-by: Suvaditya Mukherjee <[email protected]>
Signed-off-by: Suvaditya Mukherjee <[email protected]>
suvadityamuk
changed the title
torch.compile compatibletorch.compile compatible
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
sayakpaul
reviewed
Jan 12, 2024
| logger.info("Initializing controlnet weights from unet") | ||
| controlnet = ControlNetModel.from_unet(unet) | ||
|
|
||
| # Taken from [Sayak Paul's Diffusers PR #6511](https://github.com/huggingface/diffusers/pull/6511/files) |
Member
There was a problem hiding this comment.
Remove it. Not a problem. But I appreciate the thoughtfulness.
sayakpaul
reviewed
Jan 12, 2024
|
|
||
| # Get the text embedding for conditioning | ||
| encoder_hidden_states = text_encoder(batch["input_ids"])[0] | ||
| encoder_hidden_states = text_encoder(batch["input_ids"], return_dict=False)[0] |
Member
There was a problem hiding this comment.
Nit: For ControlNet training on SD, it won't matter (same for SDXL) as we never train the text encoder during ControlNet training. But keeping it this way doesn't hurt things. So, I am okay with it.
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
…gface#6525) * update: make controlnet script torch compile compatible Signed-off-by: Suvaditya Mukherjee <[email protected]> * update: correct earlier mistakes for compilation Signed-off-by: Suvaditya Mukherjee <[email protected]> * update: fix code style issues Signed-off-by: Suvaditya Mukherjee <[email protected]> --------- Signed-off-by: Suvaditya Mukherjee <[email protected]>
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.
What does this PR do?
Partially fixes #6503 concerning ControlNet's Training Script. Followed along with #6483 and #6511.
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.
@sayakpaul @patrickvonplaten