Skip to content

[SD3 dreambooth lora] smol fix to checkpoint saving #9993

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Nov 24, 2024
Merged

[SD3 dreambooth lora] smol fix to checkpoint saving #9993

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b19a871
smol change to fix checkpoint saving & resuming (as done in train_dre…
linoytsaban Nov 22, 2024
6c1cef1
style
linoytsaban Nov 22, 2024
b1ece65
Merge branch 'main' into sd3-bug-fix
linoytsaban Nov 24, 2024
613a32d
modify comment to explain reasoning behind hidden size check
linoytsaban Nov 24, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 7 additions & 4 deletions examples/dreambooth/train_dreambooth_lora_sd3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1294,10 +1294,13 @@ def save_model_hook(models, weights, output_dir):
for model in models:
if isinstance(model, type(unwrap_model(transformer))):
transformer_lora_layers_to_save = get_peft_model_state_dict(model)
elif isinstance(model, type(unwrap_model(text_encoder_one))):
text_encoder_one_lora_layers_to_save = get_peft_model_state_dict(model)
elif isinstance(model, type(unwrap_model(text_encoder_two))):
text_encoder_two_lora_layers_to_save = get_peft_model_state_dict(model)
elif isinstance(model, type(unwrap_model(text_encoder_one))): # or text_encoder_two
# both text encoders are of the same class, so we check hidden size to distinguish between the two
hidden_size = unwrap_model(model).config.hidden_size
if hidden_size == 768:
text_encoder_one_lora_layers_to_save = get_peft_model_state_dict(model)
elif hidden_size == 1280:
text_encoder_two_lora_layers_to_save = get_peft_model_state_dict(model)
else:
raise ValueError(f"unexpected save model: {model.__class__}")

Expand Down
Loading