Skip to content

Fix prior preservation encoding in DreamBooth SD3(&its LoRA version) training scripts #12411

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

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
+19 −13
Open

Fix prior preservation encoding in DreamBooth SD3(&its LoRA version) training scripts #12411

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4313003
fix: train_dreambooth_sd3.py line1605: 1. pass prompts to the prompt …
Barque-S Sep 30, 2025
5505cdb
fix: train_dreambooth_lora_sd3.py line 1751: prompts instead of args.…
Barque-S Sep 30, 2025
ef90e69
Merge branch 'main' into fix-traindreambooth-sd3-in-examples
linoytsaban Oct 6, 2025
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
4 changes: 2 additions & 2 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 @@ -1750,8 +1750,8 @@ def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
if args.train_text_encoder:
prompt_embeds, pooled_prompt_embeds = encode_prompt(
text_encoders=[text_encoder_one, text_encoder_two, text_encoder_three],
tokenizers=[None, None, tokenizer_three],
prompt=args.instance_prompt,
tokenizers=[None, None, None],
prompt=prompts,
max_sequence_length=args.max_sequence_length,
text_input_ids_list=[tokens_one, tokens_two, tokens_three],
)
Expand Down
28 changes: 17 additions & 11 deletions examples/dreambooth/train_dreambooth_sd3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -875,15 +875,20 @@ def _encode_prompt_with_t5(
prompt = [prompt] if isinstance(prompt, str) else prompt
batch_size = len(prompt)

text_inputs = tokenizer(
prompt,
padding="max_length",
max_length=max_sequence_length,
truncation=True,
add_special_tokens=True,
return_tensors="pt",
)
text_input_ids = text_inputs.input_ids
if tokenizer is not None:
text_inputs = tokenizer(
prompt,
padding="max_length",
max_length=max_sequence_length,
truncation=True,
add_special_tokens=True,
return_tensors="pt",
)
text_input_ids = text_inputs.input_ids
else:
if text_input_ids is None:
raise ValueError("text_input_ids must be provided when the tokenizer is not specified")

prompt_embeds = text_encoder(text_input_ids.to(device))[0]

dtype = text_encoder.dtype
Expand Down Expand Up @@ -1604,8 +1609,9 @@ def get_sigmas(timesteps, n_dim=4, dtype=torch.float32):
else:
prompt_embeds, pooled_prompt_embeds = encode_prompt(
text_encoders=[text_encoder_one, text_encoder_two, text_encoder_three],
tokenizers=None,
prompt=None,
tokenizers=[None, None, None],
prompt=prompts,
max_sequence_length=args.max_sequence_length,
text_input_ids_list=[tokens_one, tokens_two, tokens_three],
)
model_pred = transformer(
Expand Down
Loading