NEWVectors or files. Pick a path.Start →

    Image Segmentation Models

    Browse AI models for multimodal decomposition and recomposition pipelines — plug any model into your extractors.

    447 models available

    Get startedSchedule DemoRead Documentation

    Showing 1–24 of 447 models

    Image Segmentation

    CIDAS/clipseg-rd64-refined

    1.3M
    140
    transformers
    View Details
    Image Segmentation

    ZhengPeng7/BiRefNet

    711K
    601
    birefnet
    View Details
    Image Segmentation

    briaai/RMBG-2.0

    596K
    1,283
    transformers
    View Details
    Image Segmentation

    facebook/mask2former-swin-large-ade-semantic

    569K
    21
    transformers
    View Details
    Image Segmentation

    briaai/RMBG-1.4

    326K
    1,993
    transformers
    View Details
    Image Segmentation

    nvidia/segformer-b0-finetuned-ade-512-512

    301K
    190
    transformers
    View Details
    Image Segmentation

    jonathandinu/face-parsing

    203K
    223
    transformers
    View Details
    Image Segmentation

    Xenova/segformer-b0-finetuned-ade-512-512

    198K
    2
    transformers.js
    View Details
    Image Segmentation

    nvidia/segformer-b2-finetuned-ade-512-512

    198K
    7
    transformers
    View Details
    Image Segmentation

    facebook/mask2former-swin-large-cityscapes-semantic

    172K
    38
    transformers
    View Details
    Image Segmentation

    mattmdjaga/segformer_b2_clothes

    149K
    501
    transformers
    View Details
    Image Segmentation

    nvidia/segformer-b5-finetuned-cityscapes-1024-1024

    128K
    43
    transformers
    View Details
    Image Segmentation

    nvidia/segformer-b1-finetuned-ade-512-512

    106K
    16
    transformers
    View Details
    Image Segmentation

    shi-labs/oneformer_ade20k_swin_large

    99K
    35
    transformers
    View Details
    Image Segmentation

    nvidia/segformer-b5-finetuned-ade-640-640

    90K
    45
    transformers
    View Details
    Image Segmentation

    facebook/mask2former-swin-tiny-coco-instance

    61K
    16
    transformers
    View Details
    Image Segmentation

    shi-labs/oneformer_coco_swin_large

    59K
    8
    transformers
    View Details
    Image Segmentation

    Xenova/modnet

    57K
    83
    transformers.js
    View Details
    Image Segmentation

    facebook/mask2former-swin-large-mapillary-vistas-panoptic

    49K
    3
    transformers
    View Details
    Image Segmentation

    chendelong/DirectSAM-1800px-0424

    45K
    3
    transformers
    View Details
    Image Segmentation

    shi-labs/oneformer_cityscapes_swin_large

    44K
    2
    transformers
    View Details
    Image Segmentation

    PaddlePaddle/PP-DocLayoutV3

    41K
    92
    PaddleOCR
    View Details
    Image Segmentation

    fashn-ai/fashn-human-parser

    41K
    28
    transformers
    View Details
    Image Segmentation

    tue-mps/coco_panoptic_eomt_large_640

    37K
    13
    transformers
    View Details
    1 / 19

    Previous

    Connectors

    Next

    Retrievers

    What's new in models

    Full changelog