Anzhcs YOLOs

Description

YOLOs in this repo are trained with datasets that i have annotated myself, or with the help of my friends(They will be appropriately mentioned in those cases). YOLOs on open datasets will have their own pages.

Known Adetailer Issues

Ultralytics 8.3.217 updates mask handling, which breaks function in main Adetailer repo. Install Ultralytics==8.3.216 or lower. Alternatively - use forks that fix this. - Fixed in main repo.

My Adetailer fork

I've added some features to make Adetailer more usable and less manual - https://github.com/Anzhc/aadetailer-reforge

Want to request a model?

Im open to commissions, hit me up in Discord - anzhc

Table of Contents

• Face segmentation
  • Universal
  • Real Face, gendered
• Eyes segmentation
• Head+Hair segmentation
• Breasts
  • Breasts Segmentation
  • Breast size detection/classification
• Drone detection
• Anime Art Scoring
• Support

P.S. All model names in tables have download links attached :3

Available Models

Face segmentation:

Universal:

Series of models aiming at detecting and segmenting face accurately. Trained on closed dataset i annotated myself.

Model	Target	mAP 50	mAP 50-95	Classes	Dataset size	Training Resolution
Anzhc Face -seg.pt	Face: illustration, real	LOST DATA	LOST DATA	2(male, female)	LOST DATA	640
Anzhc Face seg 640 v2 y8n.pt	Face: illustration, real	0.464(box) 0.453(mask)	0.309(box) 0.207(mask)	1(face)	~500	640
Anzhc Face seg 768 v2 y8n.pt	Face: illustration, real	^	^	1(face)	~500	768
Anzhc Face seg 768MS v2 y8n.pt	Face: illustration, real	^	^	1(face)	~500	768
Anzhc Face seg 1024 v2 y8n.pt	Face: illustration, real	^	^	1(face)	~500	1024
Anzhc Face seg 640 v3 y11n.pt	Face: illustration	0.524(box) 0.516(mask)	0.387(box) 0.297(mask)	1(face)	~660	640
Anzhc Face seg 640 v4 y11n.pt	Face: illustration, real	0.835(box) 0.800(mask)	0.537(box) 0.467(mask)	1(face)	~1030	640

UPDATE: v3 model has a bit different face target compared to v2, so stats of v2 models suffer compared to v3 in newer benchmark, especially in mask, while box is +- same. Dataset for v3 and above is going to be targeting inclusion of eyebrows and full eyelashes, for better adetailer experience without large dillution parameter.

Also starting from v3, im moving to yolo11 models, as they seem to be direct upgrade over v8. v12 did not show significant improvement while requiring 50% more time to train, even with installed Flash Attention, so it's unlikely i will switch to it anytime soon.

UPDATE: V4 - Addition of high complexity data (over 100 instances per image), more simple realistic and AI-generated faces.

Benchmark was performed in 640px. V2 was condensed to single model, as their differences are marginal.
Benchmark results were recomputed on new val based on V4 dataset(images previously in val remained in val, so no contamination for previous versions), stats updated accordingly.

image

hjkhgjkghj

Real Face, gendered:

Trained only on real photos for the most part, so will perform poorly with illustrations, but is gendered, and can be used for male/female detection stack.

Model	Target	mAP 50	mAP 50-95	Classes	Dataset size	Training Resolution
Anzhcs ManFace v02 1024 y8n.pt	Face: real	0.883(box),0.883(mask)	0.778(box), 0.704(mask)	1(face)	~340	1024
Anzhcs WomanFace v05 1024 y8n.pt	Face: real	0.82(box),0.82(mask)	0.713(box), 0.659(mask)	1(face)	~600	1024

Benchmark was performed in 640px. image/png

image/png

Eyes segmentation:

Was trained for the purpose of inpainting eyes with Adetailer extension, and specializes on detecting anime eyes, particularly - sclera area, without adding eyelashes and outer eye area to detection. Current benchmark is likely inaccurate (but it is all i have), due to data being re-scrambled multi times (dataset expansion for future versions).

Model	Target	mAP 50	mAP 50-95	Classes	Dataset size	Training Resolution
Anzhc Eyes -seg-hd.pt	Eyes: illustration	0.925(box),0.868(mask)	0.721(box), 0.511(mask)	1(eye)	~500(?)	1024

image/png

image/png

Head+Hair segmentation:

An old model (one of my first). Detects head + hair. Can be useful in likeness inpaint pipelines that need to be automated.

Model	Target	mAP 50	mAP 50-95	Classes	Dataset size	Training Resolution
Anzhc HeadHair seg y8n.pt	Head: illustration, real	0.775(box),0.777(mask)	0.576(box), 0.552(mask)	1(head)	~3180	640
Anzhc HeadHair seg y8m.pt	Head: illustration, real	0.867(box),0.862(mask)	0.674(box), 0.626(mask)	1(head)	~3180	640

image/png

image/png

Breasts:

Breasts segmentation:

Model for segmenting breasts. Was trained on anime images only, therefore has very weak realistic performance, but still is possible.

Model	Target	mAP 50	mAP 50-95	Classes	Dataset size	Training Resolution
Anzhc Breasts Seg v1 1024n.pt	Breasts: illustration	0.742(box),0.73(mask)	0.563(box), 0.535(mask)	1(breasts)	~2000	1024
Anzhc Breasts Seg v1 1024s.pt	Breasts: illustration	0.768(box),0.763(mask)	0.596(box), 0.575(mask)	1(breasts)	~2000	1024
Anzhc Breasts Seg v1 1024m.pt	Breasts: illustration	0.782(box),0.775(mask)	0.644(box), 0.614(mask)	1(breasts)	~2000	1024

image/png

image/png

Breast size detection and classification:

Model for Detecting and classifying breast size. Can be used for tagging and moderating content. Utilizes custom scale, combining default Booru sizes with quite freeform upper range of scale from rule34, simplifying and standartizing it.

Size range is established relative to body proportion, instead of relative to scene, to not be confused in cases of gigantism and be disentangled from scene.
And of course it's subjective, since i was the only one annotating data.

Model	Target	Classes	Dataset size	Training Resolution
Anzhcs Breast Size det cls v8 y11m.pt	Breasts: illustration and real	15(size range)	~16100	640

mAPs are not displayed in table, because i think we need more complex stats for this model.

image/png

Accurate ratio - correct predictions, exactly matching val.
+1, -1, +-1 ratio - expanded range of acceptable predictions, by +,- and +-1 class. I suggest using this stat as main accuracy, because +-1 range is likely an acceptable margin of error.
At annotation, usual rate of error of original data according to this size scale was in range of +-2 to +-3 in some cases, so +-1 should be quite good.
Miscalss ratio - Correct detection, but classification goes beyond +-1 error.
Miss ratio - Not seen by model, completely missed.
False-Positive ratio - Detection of something that isn't there.
In case of this model i suspect that FPR is also including confusion rate. In some cases multiple detection will be made for single instance, and only 1 will be accepted.
That can be counted as false-positive, while it will be covered in +-1 acc. Actual FPR should be lower...