Skip to content
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

[Fix] remove setting lr for T5 text encoder when using prodigy in flux dreambooth lora script #9473

Merged
merged 7 commits into from
Oct 28, 2024
Merged

[Fix] remove setting lr for T5 text encoder when using prodigy in flux dreambooth lora script #9473

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
288a311
fix: removed setting of text encoder lr for T5 as it's not being tuned
biswaroop1547 Sep 19, 2024
6c6724f
fix: removed setting of text encoder lr for T5 as it's not being tuned
biswaroop1547 Sep 19, 2024
8aa965c
Merge branch 'main' into main
sayakpaul Sep 20, 2024
416021d
Merge branch 'main' into main
biswaroop1547 Sep 23, 2024
e0a3db7
Merge branch 'main' into main
sayakpaul Oct 2, 2024
349da9a
Merge branch 'main' into main
sayakpaul Oct 26, 2024
bba88e3
Merge branch 'main' into main
linoytsaban Oct 28, 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
1 change: 0 additions & 1 deletion examples/dreambooth/train_dreambooth_flux.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1288,7 +1288,6 @@ def load_model_hook(models, input_dir):
# changes the learning rate of text_encoder_parameters_one and text_encoder_parameters_two to be
# --learning_rate
params_to_optimize[1]["lr"] = args.learning_rate
params_to_optimize[2]["lr"] = args.learning_rate

optimizer = optimizer_class(
params_to_optimize,
Expand Down
1 change: 0 additions & 1 deletion examples/dreambooth/train_dreambooth_lora_flux.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1370,7 +1370,6 @@ def load_model_hook(models, input_dir):
# changes the learning rate of text_encoder_parameters_one and text_encoder_parameters_two to be
# --learning_rate
params_to_optimize[1]["lr"] = args.learning_rate
params_to_optimize[2]["lr"] = args.learning_rate
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am not sure if this is the right fix because what happens when we train the text encoder, too? Cc @linoytsaban

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

when we enable the option for training text encoders too, we only target the clip model and not the T5 for flux, hence this line was unnecessary from what I noticed

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hence also the reason for the indexerror^

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

indeed for now we support full fine-tuning of the CLIP encoder only when --train_text_encoder is enabled, so simply removing this line for now should be good!


optimizer = optimizer_class(
params_to_optimize,
Expand Down
Loading