skip to content
gigarouter gigarouter
models / object detection · coming soon

Anzhc's YOLOs

Anzhc/Anzhcs_YOLOs

published Feb 2024 · updated Feb 2026

Anzhc's YOLOs is a collection of object detection and instance segmentation models for face, eyes, head/hair, and breasts, trained on custom datasets for anime and real images.

status
coming soon
API providers
0
downloads / mo
75.5K
license
agpl-3.0

specs

TaskObject Detection & Instance Segmentation
ArchitectureUltralytics YOLOv8 / YOLO11 (nano, small, medium variants)
LicenseAGPL-3.0
Training DataCustom annotated datasets (face ~500–1030 images, eyes ~500, head/hair ~3180, breasts ~2000, breast size ~16100)

about this model

Anzhc/Anzhcs_YOLOs is a collection of YOLO-based object detection and instance segmentation models specialized in human-centric tasks such as face, eyes, head-hair, and breast segmentation and classification. All models are trained on custom-annotated datasets and are optimized for both illustration and real imagery.

Face Segmentation

The universal face segmentation models (v2, v3, v4) detect and segment faces with increasing accuracy. Version 4, trained at 640px on ~1,030 images, achieves mAP 50 of 0.835 (box) and 0.800 (mask). Gender-specific real-photo models are also available, with the ManFace model attaining mAP 50 of 0.883 (box, mask).

ModelmAP 50 (box)mAP 50 (mask)Training Res.
Anzhc Face seg 640 v4 y11n0.8350.800640
Anzhcs ManFace v02 1024 y8n0.8830.8831024
Benchmark comparison for face segmentation models

Eyes Segmentation

This model specializes in detecting anime eyes (sclera area) for inpainting workflows. At 1024px training resolution it achieves mAP 50 of 0.925 (box) and 0.868 (mask).

Eyes segmentation detection examples Eyes segmentation mask examples

Head+Hair Segmentation

One model each at y8n and y8m sizes. The y8m variant scores mAP 50 of 0.867 (box) and 0.862 (mask) at 640px, trained on ~3,180 images covering both illustration and real content.

Head+hair segmentation detection results

Breast Segmentation and Classification

The breast segmentation model (v1, 1024m) achieves mAP 50 of 0.782 (box) and 0.775 (mask) on illustration data. A separate breast size detection/classification model covers 15 size classes using a custom body-proportion scale; +-1 class accuracy is the recommended metric for evaluation.

best for

FAQ

What does this collection of models do?

It includes YOLO-based detectors/segmenters for faces, eyes, head/hair, and breasts, trained on custom datasets for both anime/illustration and real photos.

How accurate are the face segmentation models?

The v4 y11n model achieves mAP50 0.835 (box) and 0.800 (mask) on face detection. Gendered real-face models (ManFace, WomanFace) achieve mAP50 0.82–0.88.

What license applies to these models?

The models are released under the AGPL-3.0 license.

How do I call this model via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with your API key, specifying the model ID as Anzhc/Anzhcs_YOLOs.

Are there models for real photos or only anime?

Some models target only real photos (e.g., ManFace, WomanFace), while others (face v2–v4) are trained on both illustration and real faces. The breast size model also works on real images.

not yet live

We're benchmarking and onboarding Anzhc's YOLOs as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related object detection models

compare all →