You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When running the inference_tiktok_dataset.sh script, pose_control_model (i.e., ControlNet) is running unnecessarily (in line 1112 ~ 1114 in cldm.py) for computing model_uncod.
When uc==False, ControlNetReferenceOnly --> ControlNet (pose_control_model) --> ControlledUnetModelAttnPose (OK)
When uc==True, ContorlNet (pose_control_model) (???) --> ControlledUnetModelAttnPose
For computing unconditional model output (model_uncond), ControlledUnetModelPoseAttn doesn't use pose_control output from the pose_control_model, and I don't understand why pose_control_model is running in advance with no purpose.
The text was updated successfully, but these errors were encountered:
When running the inference_tiktok_dataset.sh script, pose_control_model (i.e., ControlNet) is running unnecessarily (in line 1112 ~ 1114 in cldm.py) for computing model_uncod.
When uc==False, ControlNetReferenceOnly --> ControlNet (pose_control_model) --> ControlledUnetModelAttnPose (OK)
When uc==True, ContorlNet (pose_control_model) (???) --> ControlledUnetModelAttnPose
For computing unconditional model output (model_uncond), ControlledUnetModelPoseAttn doesn't use pose_control output from the pose_control_model, and I don't understand why pose_control_model is running in advance with no purpose.
The text was updated successfully, but these errors were encountered: