Bingsu/adetailer

ultralyticsultralyticspytorchdataset:wider_facedataset:skytnt/anime-segmentationdoi:10.57967/hf/3633license:apache-2.0apache-2.0
13.1M

YOLOv8 Detection Model

Datasets

Face

Hand

Person

deepfashion2

idlabel
0short_sleeved_shirt
1long_sleeved_shirt
2short_sleeved_outwear
3long_sleeved_outwear
4vest
5sling
6shorts
7trousers
8skirt
9short_sleeved_dress
10long_sleeved_dress
11vest_dress
12sling_dress

Info

ModelTargetmAP 50mAP 50-95
face_yolov8n.pt2D / realistic face0.6600.366
face_yolov8n_v2.pt2D / realistic face0.6690.372
face_yolov8s.pt2D / realistic face0.7130.404
face_yolov8m.pt2D / realistic face0.7370.424
face_yolov9c.pt2D / realistic face0.7480.433
hand_yolov8n.pt2D / realistic hand0.7670.505
hand_yolov8s.pt2D / realistic hand0.7940.527
hand_yolov9c.pt2D / realistic hand0.8100.550
person_yolov8n-seg.pt2D / realistic person0.782 (bbox)
0.761 (mask)
0.555 (bbox)
0.460 (mask)
person_yolov8s-seg.pt2D / realistic person0.824 (bbox)
0.809 (mask)
0.605 (bbox)
0.508 (mask)
person_yolov8m-seg.pt2D / realistic person0.849 (bbox)
0.831 (mask)
0.636 (bbox)
0.533 (mask)
deepfashion2_yolov8s-seg.ptrealistic clothes0.849 (bbox)
0.840 (mask)
0.763 (bbox)
0.675 (mask)

Usage

from huggingface_hub import hf_hub_download
from ultralytics import YOLO

path = hf_hub_download("Bingsu/adetailer", "face_yolov8n.pt")
model = YOLO(path)
import cv2
from PIL import Image

img = "https://farm5.staticflickr.com/4139/4887614566_6b57ec4422_z.jpg"
output = model(img)
pred = output[0].plot()
pred = cv2.cvtColor(pred, cv2.COLOR_BGR2RGB)
pred = Image.fromarray(pred)
pred

image

Unsafe files

image

Since getattr is classified as a dangerous pickle function, any segmentation model that uses it is classified as unsafe.

All models were created and saved using the official ultralytics library, so it's okay to use files downloaded from a trusted source.

See also: https://huggingface.co/docs/hub/security-pickle

DEPLOY IN 60 SECONDS

Run adetailer on Runcrate

Deploy on H100, A100, or RTX GPUs. Pay only for what you use. No setup required.