SAVRN
Search Contact SAVRN

Open-weight model · Object detection

Ultralytics

by Midnight1111 MidnightRunner/Ultralytics

ComfyUI Ultralytics Integration – Midnight1111 Model Collection For ComfyUI, here’s how to load these models: 1. Locate your ComfyUI folder (e.g. ~/ComfyUI/ or C:\ComfyUI\). 2. Create directories: 3.

Parameters—
Context—
Weights956.9 MB
Licenseagpl-3.0
AccessOpen weights
Monthly Downloads7.1k

Model Card

By Midnight1111, published under agpl-3.0, revision b2121b71f619.

ComfyUI Ultralytics Integration – Midnight1111 Model Collection For ComfyUI, here’s how to load these models: 1. Locate your ComfyUI folder (e.g. ~/ComfyUI/ or C:\ComfyUI\). 2. Create directories: 3. Place your.pt files: • Segmentation → models/ultralytics/segm/ • Detection (bbox) → models/ultralytics/bbox/ 5. In the UI: Add Node → Model → Ultralytics → choose segm/… or bbox/…. Connect an Image Loader → Ultralytics node → Previewer Unsafe files 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 safe to use files downloaded from a trusted…

Read Midnight1111's full model card

ComfyUI Ultralytics Integration – Midnight1111 Model Collection

For ComfyUI, here’s how to load these models:

  1. Locate your ComfyUI folder (e.g. ~/ComfyUI/ or C:\ComfyUI\).
  2. Create directories: bash cd /path/to/ComfyUI/models mkdir -p ultralytics/segm ultralytics/bbox
  3. Place your .pt files: • Segmentation → models/ultralytics/segm/ • Detection (bbox) → models/ultralytics/bbox/
  4. Restart ComfyUI bash cd /path/to/ComfyUI
  5. In the UI: Add Node → Model → Ultralytics → choose segm/… or bbox/…. Connect an Image Loader → Ultralytics node → Previewer

Unsafe files

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 safe to use files downloaded from a trusted source.

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

Note on Loading Weights

If you encounter an error like: bash Weights-only load failed. Unsupported global: builtins.set

This happens because PyTorch (for safety) blocks loading some objects by default. To fix it safely, add this code before loading: bash python bash import torch torch.serialization.add_safe_globals([set]) This whitelists set and allows safe loading with weights_only=True.

Otherwise, never disable weights_only unless you 100% trust the file.

Check PyTorch's torch.load docs for more info.

Identity and Version

Repository
MidnightRunner/Ultralytics
Publisher
Midnight1111
Task
Object detection
Modality
Image
Library
ultralytics
Parameters
Not stated by the source
Languages
en
Revision
b2121b71f6199e5ec9dc70ab534010b1019ccd7e
First published
2025-04-26
Last updated
2026-06-11

Files and Weights

43 files, 956.9 MB in total. The weights are 41 files totalling 956.9 MB in pt.

Weights41 files · 956.9 MB
Documentation1 file · 1.9 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
bbox/Eyeful_v2-Individual.ptWeights22.5 MB 278fee230b1b
bbox/Eyeful_v2-Paired.ptWeights22.6 MB 0d574fd6b4f5
bbox/breasts_seg.ptWeights6.8 MB 87f314a908be
bbox/eyeful_v1.ptWeights22.6 MB 06bae812f2c8
bbox/face_yolov8m.ptWeights52.0 MB 717923c19b3f
bbox/face_yolov8n.ptWeights6.2 MB 30e7adcf03c1
bbox/face_yolov8n_v2.ptWeights6.2 MB 1e561e2edfcc
bbox/face_yolov8s.ptWeights22.5 MB 2e157766211d
bbox/hand_yolov8n.ptWeights6.2 MB f3f23b865741
bbox/hand_yolov8s.ptWeights22.5 MB 70b540063fbc
bbox/nsfw_watermarks_s_yolov8_v1.ptWeights22.5 MB 78d27f0f5ea3
bbox/pussy.ptWeights136.7 MB 2d19bce715d4
bbox/watermarks_s_yolov8_v1.ptWeights22.5 MB 234f6ab07701
segm/Anzhc Breasts Seg v1 1024m.ptWeights54.9 MB 53d15e82a830
segm/Anzhc Breasts Seg v1 1024n.ptWeights6.9 MB d469bd7abdcb
segm/Anzhc Breasts Seg v1 1024s.ptWeights24.0 MB 413a9b948a40
segm/Anzhc Eyes -seg-hd.ptWeights6.9 MB 6be1c13ca7a5
segm/Anzhc Face seg 1024 v2 y8n.ptWeights6.9 MB 1bbcfd7a9f40
segm/Anzhc Manga Panels -seg.ptWeights23.9 MB 915c85e044be
segm/Anzhcs ManFace v02 1024 y8n.ptWeights6.4 MB 184b9a680afb
segm/Anzhcs WomanFace v05 1024 y8n.ptWeights6.4 MB 84db37616e1c
segm/Eyeful_v2-Individual.ptWeights22.5 MB 278fee230b1b
segm/PitEyeDetailer-v2-seg.ptWeights23.9 MB 0485d0a88983
segm/PitGlassesDetailer-v1-seg.ptWeights23.9 MB 247354e884a4
segm/breasts_seg.ptWeights6.8 MB 87f314a908be
segm/deepfashion2_yolov8s-seg.ptWeights23.9 MB 6a707d8a3beb
segm/face_yolov8m-seg_60.ptWeights54.8 MB 4a63e08009bc
segm/face_yolov8n-seg2_60.ptWeights6.8 MB 5216e2aba6b4
segm/hair_yolov8n-seg_60.ptWeights6.8 MB 3112ced2bd21
segm/hand_yolov8n.ptWeights6.2 MB f3f23b865741
segm/nipples-yolov8s.ptWeights23.8 MB 32ada96a3aad
segm/person_yolov8m-seg.ptWeights54.8 MB c8ab26f51717
segm/person_yolov8n-seg.ptWeights6.8 MB 029e36039b53
segm/person_yolov8s-seg.ptWeights23.9 MB b5684835e79f
segm/piteyedetailer-v1-seg.ptWeights23.9 MB 55f1db15ceed
segm/pitglassesdetailer-v1-seg.ptWeights23.9 MB 247354e884a4
segm/pithanddetailer-v1-seg.ptWeights23.8 MB 0b88a8b43eff
segm/skin_yolov8m-seg_400.ptWeights54.9 MB 28917daf69ce
segm/skin_yolov8n-seg_400.ptWeights6.8 MB 0fdc28e11cfc
segm/skin_yolov8n-seg_800.ptWeights6.8 MB 0dc8136e6278
segm/wenaka_yolov8s-seg.ptWeights23.9 MB bc3d3b1eedab
README.mdDocumentation1.9 KB —
.gitattributesRepository1.5 KB —

License and Download

License
agpl-3.0
Access
Open weights, no gate
Download size
956.9 MB
Download from Midnight1111

Released by Midnight1111 through its official repository on Hugging Face. Read the license.

Built From

  • Derived from Ultralytics/YOLO11
  • Trained on (disclosed) skytnt/anime-segmentation
  • Trained on (disclosed) wider_face

Memory Requirements

PrecisionWeights in memory
As published956.9 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About Ultralytics

Can I use Ultralytics commercially?

Yes, with conditions. Ultralytics is released under GNU Affero General Public License 3.0. The AGPL 3.0 is a strong copyleft license. Commercial use is allowed, but a modified version made available to users over a network must be released with its source code under the same license.

Similar Models

Model · Object detection

locate-anything.cpp-gguf

Mudler

GGUF builds of nvidia/LocateAnything-3B for locate-anything.cpp - a C++/ggml inference engine for open-vocabulary detection / visual grounding, no Python at inference time. Brought to you by the LocalAI team. The detections are the same as the official PyTorch implementation (the engine is parity-gated against it), and it runs faster - on CPU and GPU. The full-precision f32 GGUF (~15 GB) is reproducible from the HF weights with scripts/convertlocateanythingtogguf.py in the repo. Same detections as the official model, faster. Full methodology, the warm/median setup, parity checks, and more images are in the repo's Slow-mode inference on the 448 fixture; vs official divides the official…

Open weights other gguf
View model

Model · Object detection

Anzhcs_YOLOs

Anzhc

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. 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. I've added some features to make Adetailer more usable and less manual - https://github.com/Anzhc/aadetailer-reforge Im open to commissions, hit me up in Discord - anzhc P.S. All model names in tables have download links attached:3 Series of models aiming at detecting and segmenting face…

Open weights agpl-3.0 ultralytics
View model

This is a fine-tuned version of YOLOv11 (n, s, m, l, x) specialized for License Plate Detection, using a public dataset from Roboflow Universe: The upstream Roboflow dataset (license-plate-recognition-rxg4e) contains train/test contamination — the same source images appear in both the training and test splits with only minor manual augmentation applied (see Discussion #2 for concrete examples). As a result: - The reported metrics below are likely overestimated, because the test set is not a true held-out evaluation. - Real-world generalization performance is expected to be lower than the numbers in the table. - Treat all evaluation figures with caution and validate the model on your own…

Open weights agpl-3.0 ultralytics
View model

Model · Object detection

surya_layout2

Datalab

A lightweight document layout detection model used by Surya. It detects layout regions (text, tables, figures, headers, captions, equations, etc.) on a page image and runs on CPU or GPU. This is the "fast" layout detector — a compact object detector that serves as a drop-in alternative to Surya's VLM-based layout model. Documentation, installation, and everything else lives in the Point the fast layout predictor at this checkpoint: Or make it the default so the CLI and library use it without an explicit path: Released under the AI Pubs OpenRAIL-M license (see LICENSE) — the same license as the surya-ocr-2 model weights.

Open weights openrail surya
View model

Model · Object detection

detr-resnet-50

Joshua

https://huggingface.co/facebook/detr-resnet-50 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Test it out here, or create your own object-detection demo with 1 click! Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Open weights 1,024 tokens transformers.js
View model