[examples/advanced_diffusion_training] bug fixes and improvements for LoRA Dreambooth SDXL advanced training script #5935
Conversation
This file contains 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
…pivotal tuning) even if the rest of the model is loaded in fp16
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
linoytsaban
changed the title
patrickvonplaten
approved these changes
Nov 29, 2023
There was a problem hiding this comment.
Feel free to merge once you're happy with it (for everything under advanced_diffusion_training :-) Also cc @apolinario
…using pivotal tuning - added type to --num_new_tokens_per_abstraction
|
let's go! |
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
… LoRA Dreambooth SDXL advanced training script (huggingface#5935) * imports and readme bug fixes * bug fix - ensures text_encoder params are dtype==float32 (when using pivotal tuning) even if the rest of the model is loaded in fp16 * added pivotal tuning to readme * mapping token identifier to new inserted token in validation prompt (if used) * correct default value of --train_text_encoder_frac * change default value of --adam_weight_decay_text_encoder * validation prompt generations when using pivotal tuning bug fix * style fix * textual inversion embeddings name change * style fix * bug fix - stopping text encoder optimization halfway * readme - will include token abstraction and new inserted tokens when using pivotal tuning - added type to --num_new_tokens_per_abstraction * style fix --------- Co-authored-by: Linoy Tsaban <[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.
fixes some bugs in the advanced lora dreambooth sdxl training script
1 . type issue when training pivotal tuning using mixed precision - ensures text_encoder params are
dtype==float32even if the rest of the model is loaded in fp162. adds
text_encoder_lora_state_dictimplementation (now matchesexamples/train_dreambooth_lora_sdxl.py)+some cleaning and style fixing
cc for review and vis @apolinario