Yolov8x segmentation model trained on images of penises. This model was only designed to detect realistic images so it won't work for 2d or anime penises.
You can find the 2D version here https://civarchive.com/models/310687
How to use in ComfyUI
Install Impact Pack and Subpack
Install ComfyUI-Manager from https://github.com/ltdrdata/ComfyUI-Manager
Open the Manger window
Open Install Custom Nodes
Search for and install ComfyUI Impact Pack
Search for and install ComfyUI Impact Subpack
Save the model to ~\ComfyUI\models\ultralytics\segm\
Node setup
Add a FaceDetailer node from the Impact Pack
Add a UltralyticsDetectorProvider node and Select the ADetailer model, connect BBOX_DETECTOR to bbox_detector, and SEGM_DETECTOR to segm_detector_opt
Description
Trained on 700 examples
FAQ
Comments (3)
Thank you for this. It has the same file name as v0.5 which can be a bit confusing.
did i set it wrong? caz i got image of a man from hving a va*** to hving a rod of flesh.... only
This seems to no longer work? Getting this error:
UltralyticsDetectorProvider
Weights only load failed. This file can still be loaded, to do so you have two options, [1mdo those steps only if you trust the source of the checkpoint[0m. (1) In PyTorch 2.6, we changed the default value of the weights_only argument in torch.load from False to True. Re-running torch.load with weights_only set to False will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source. (2) Alternatively, to load with weights_only=True please check the recommended steps in the following error message. WeightsUnpickler error: Unsupported global: GLOBAL getattr was not an allowed global by default. Please use torch.serialization.add_safe_globals([getattr]) or the torch.serialization.safe_globals([getattr]) context manager to allowlist this global if you trust this class/function. Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.