Skip to content

【Fix】Nachaku Dit Api Arg Error #231

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
Glaceon-Hyy merged 1 commit into from
Jan 29, 2026
Merged

【Fix】Nachaku Dit Api Arg Error #231

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
1 change: 1 addition & 0 deletions diffsynth_engine/models/qwen_image/qwen_image_dit_nunchaku.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,6 +179,7 @@ def forward(
rotary_emb: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
attn_mask: Optional[torch.Tensor] = None,
attn_kwargs: Optional[Dict[str, Any]] = None,
modulate_index: Optional[List[int]] = None,
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot Jan 29, 2026

Choose a reason for hiding this comment

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

high

While adding modulate_index fixes the API signature mismatch, it is currently unused within the forward method. This parameter is crucial for features like zero_cond_t, and ignoring it can lead to incorrect behavior.

To properly fix this, modulate_index should be passed to the _modulate calls within this method. This will also require updating _modulate to accept and handle this new parameter, likely by adapting the logic from the base QwenImageTransformerBlock's _modulate method.

) -> Tuple[torch.Tensor, torch.Tensor]:
if self.use_nunchaku_awq:
img_mod_params = self.img_mod(temb) # [B, 6*dim]
Expand Down