AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity

config attribute not foud error for FluxImagetoImage Pipeline for multi controlnet solved (#9586)

Browse Source 
Co-authored-by: YiYi Xu <yixu310@gmail.com>
This commit is contained in:
Rachit Shah
2024-10-24 02:03:29 +05:30
committed by GitHub
parent bfa0aa4ff2
commit 24c7d578ba
1 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/diffusers/pipelines/flux/pipeline_flux_controlnet_image_to_image.py
View File

@@ -903,9 +903,12 @@ class FluxControlNetImg2ImgPipeline(DiffusionPipeline, FluxLoraLoaderMixin, From
timestep = t.expand(latents.shape[0]).to(latents.dtype)
guidance = (
torch.tensor([guidance_scale], device=device) if self.controlnet.config.guidance_embeds else None
)
if isinstance(self.controlnet, FluxMultiControlNetModel):
use_guidance = self.controlnet.nets[0].config.guidance_embeds
else:
use_guidance = self.controlnet.config.guidance_embeds
guidance = torch.tensor([guidance_scale], device=device) if use_guidance else None
guidance = guidance.expand(latents.shape[0]) if guidance is not None else None
if isinstance(controlnet_keep[i], list):