Skip to content

Force min length 1 when tokenizing for text generation. #12538

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
comfyanonymous merged 1 commit into from
Feb 20, 2026
Merged

Force min length 1 when tokenizing for text generation. #12538

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 2 additions & 0 deletions comfy/sd1_clip.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -573,6 +573,8 @@ def tokenize_with_weights(self, text:str, return_word_ids=False, tokenizer_optio
min_length = tokenizer_options.get("{}_min_length".format(self.embedding_key), self.min_length)
min_padding = tokenizer_options.get("{}_min_padding".format(self.embedding_key), self.min_padding)

min_length = kwargs.get("min_length", min_length)

text = escape_important(text)
if kwargs.get("disable_weights", self.disable_weights):
parsed_weights = [(text, 1.0)]
Expand Down
2 changes: 1 addition & 1 deletion comfy_extras/nodes_textgen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ def define_schema(cls):
@classmethod
def execute(cls, clip, prompt, max_length, sampling_mode, image=None) -> io.NodeOutput:

tokens = clip.tokenize(prompt, image=image, skip_template=False)
tokens = clip.tokenize(prompt, image=image, skip_template=False, min_length=1)

# Get sampling parameters from dynamic combo
do_sample = sampling_mode.get("sampling_mode") == "on"
Expand Down