[bug fix] fixes #6444 - checkpointing save issue in advanced dreambooth lora sdxl script #6464
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 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. |
|
cc @sayakpaul for review 😊 |
sayakpaul
reviewed
Jan 5, 2024
examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py
Outdated
Show resolved
Hide resolved
sayakpaul
approved these changes
Jan 5, 2024
…l_advanced.py Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
|
Feel free to merge once the CI is green! |
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
…ed dreambooth lora sdxl script (huggingface#6464) * unwrap text encoder when saving hook only for full text encoder tuning * unwrap text encoder when saving hook only for full text encoder tuning * save embeddings in each checkpoint as well * save embeddings in each checkpoint as well * save embeddings in each checkpoint as well * Update examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py Co-authored-by: Sayak Paul <spsayakpaul@gmail.com> --------- Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
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Outdated suggestions cannot be applied.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.
Fixes the bug described in #6444 that occurs when both
(
--checkpointing_steps < --max_train_steps) and--train_text_encoder_tiis enabled.When enabling pivotal tuning, since we optimize the embeddings but we don't modify the text encoder weights, we shouldn't be saving text encoder lora layers in each checkpoint (which is what cause the error). This PR modifies
save_model_hooksuch that they're saved only when full text encoder fine tuning is performed