Skip to content

flux controlnet inpaint config bug #1

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 1 commit into from
Dec 16, 2024
Merged

flux controlnet inpaint config bug #1

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
12 changes: 7 additions & 5 deletions src/diffusers/pipelines/flux/pipeline_flux_controlnet_inpainting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1095,11 +1095,13 @@ def __call__(
timestep = t.expand(latents.shape[0]).to(latents.dtype)

# predict the noise residual
if self.controlnet.config.guidance_embeds:
guidance = torch.full([1], guidance_scale, device=device, dtype=torch.float32)
guidance = guidance.expand(latents.shape[0])
else:
guidance = None
if isinstance(self.controlnet, FluxMultiControlNetModel):
use_guidance = self.controlnet.nets[0].config.guidance_embeds
guidance = torch.tensor([guidance_scale], device=device) if use_guidance else None
else :
use_guidance = self.controlnet.config.guidance_embeds
guidance = torch.full([1], guidance_scale, device=device, dtype=torch.float32) if use_guidance else None
guidance = guidance.expand(latents.shape[0]) if use_guidance else None

if isinstance(controlnet_keep[i], list):
cond_scale = [c * s for c, s in zip(controlnet_conditioning_scale, controlnet_keep[i])]
Expand Down