Каталог
Обзор маркетплейса
CategoryAll Cybersecurity Coding Finance Agentic capability Marketing Orchestration Data & ETL Research Vision & Image Audio & Speech Language & NLP DevOps & Infra Robotics & Control Healthcare Legal & Compliance Gaming & Simulation
19 results
⬡Пайплайн
Diffusers
Hugging Face's state-of-the-art library for diffusion-based image, video, and audio generation models.
ai-supply
↓ 750k★ 4.9
◆Навык
Albumentations
Fast and flexible image augmentation library with 70+ transforms for computer vision model training.
ai-supply
↓ 560k★ 4.8
◆Навык
OpenCV Python
The world's most popular computer vision library with Python bindings — image processing, video, and ML pipelines.
ai-supply
↓ 500k★ 4.9
◐Модель
timm (PyTorch Image Models)
The largest collection of pretrained image models for PyTorch — ViT, ConvNeXt, EfficientNet, Swin, and 900+ more.
ai-supply
↓ 490k★ 4.9
◐Модель
SAM 2
Meta's Segment Anything Model 2 — real-time promptable segmentation for images and videos with streaming memory.
ai-supply
↓ 420k★ 4.8
⬡Пайплайн
PaddleOCR
Industrial-grade multilingual OCR toolkit supporting 80+ languages with text detection, recognition, and layout analysis.
ai-supply
↓ 390k★ 4.7
⬡Пайплайн
MediaPipe — Cross-Platform ML for Live & Streaming Media
Google's on-device ML framework for face, hand, pose, and object detection across mobile, desktop, web, and edge.
ai-supply
↓ 350k★ 4.7
◐Модель
InvokeAI
Production-grade Stable Diffusion studio with a node-based workflow editor, ControlNet, IP-Adapter, and full REST API.
ai-supply
↓ 340k★ 4.8
◐Модель
Segment Anything Model (SAM)
Meta AI's promptable image segmentation model that can segment any object from a single click or bounding box.
ai-supply
↓ 320k★ 4.9
◆Навык
EasyOCR — Ready-to-Use OCR for 80+ Languages
One-line OCR for 80+ languages including Latin, Chinese, Arabic, Devanagari, and Cyrillic — no training required.
ai-supply
↓ 295k★ 4.7
◐Модель
Detectron2
Meta AI's modular object detection platform supporting Mask R-CNN, Faster R-CNN, DETR, and panoptic segmentation.
ai-supply
↓ 210k★ 4.8
◆Навык
Supervision
Roboflow's reusable computer vision utilities for annotation, tracking, and visualising detection model outputs.
ai-supply
↓ 175k★ 4.8
⬡Пайплайн
Grounded SAM — Open-Vocabulary Detection + Segmentation
Combines Grounding DINO and Segment Anything for text-prompt-driven object detection and precise segmentation in one pipeline.
ai-supply
↓ 165k★ 4.7
⬡Пайплайн
MMDetection
OpenMMLab's comprehensive object detection toolbox with 40+ architectures and 300+ pretrained models.
ai-supply
↓ 165k★ 4.7
◐Модель
DINOv2 — Self-Supervised Vision Foundation Model
Meta's self-supervised ViT model producing universal visual features for classification, segmentation, depth estimation, and retrieval.
ai-supply
↓ 130k★ 4.8
◐Модель
MMSegmentation
OpenMMLab's unified semantic segmentation toolbox with 40+ architectures (DeepLab, SegFormer, Mask2Former) and 250+ pretrained models.
ai-supply
↓ 128k★ 4.6
◆Навык
Kornia — Geometric Computer Vision Library
Differentiable computer vision library built on PyTorch: geometry, augmentation, colour, filtering, feature extraction, and more.
ai-supply
↓ 110k★ 4.6
◐Модель
GroundingDINO
Open-set object detector that grabs any object by text description — no class list needed at inference time.
ai-supply
↓ 98k★ 4.8
◐Модель
Depth Anything
Foundation model for monocular depth estimation with state-of-the-art relative and metric depth from a single image.
ai-supply
↓ 82k★ 4.8