2024-06-14 – Sent yolo to cuda device if available (credits: kilroythethird, thanks for the suggestion!)
2024-06-14 – Dropped the requirement from insightface completely.
2024-05-22 – Updated GenderFaceFilter node.
2024-05-19 – Added BiSeNetMask and JonathandinuMask nodes. Careful about JonathandinuMask, it’s more accurate than BiSeNet, but it takes more memory; you can get out of memory more easily with it.
2024-03-10 – Added nodes to detect faces using face_yolov8m instead of insightface.
Example Workflows
Full inpainting workflow with two controlnets which allows to get as high as 1.0 denoise strength without messing things up.
warps: 2×3 warp matrix to paste the cropped face back into the original image
WarpFacesBack
input:
images: this is the original image
face
crop: cropped face images
mask: masks for the cropped faces
warp: 2×3 warp matrix
OrderedFaceFilter
works similarly to ImpactSEGSOrderedfilter
GenderFaceFilter
needs more work, as InsightFace gender classifier isn’t very accurate.
MergeWarps
I made some changes in FaceDetailer and WarpFacesBack since I’ve created this one, so it probably doesn’t work anymore. Needs more testing and more work.
(Only if you want to use occlusion aware masks) Download BiSeNet model into ComfyUI/models/bisenet
DEPRECATED:
You need ComfyUI-Impact-Pack for Load InsightFace node and comfyui_controlnet_aux for MediaPipe library (which is required for convex_hull masks) and MediaPipe Face Mesh node if you want to use that controlnet.