diff --git a/src/diffusers/pipelines/flux/pipeline_flux_controlnet_image_to_image.py b/src/diffusers/pipelines/flux/pipeline_flux_controlnet_image_to_image.py
index a7f7c66a2cad..4b48518127d8 100644
--- a/src/diffusers/pipelines/flux/pipeline_flux_controlnet_image_to_image.py
+++ b/src/diffusers/pipelines/flux/pipeline_flux_controlnet_image_to_image.py
@@ -897,9 +897,12 @@ def __call__(
 
                 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):