NEWVectors or files. Pick a path.Start →

    AI Model Hub

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

    14,077 models available

    Showing 1125711280 of 14,077 models

    Visual Question Answering

    openbmb/OmniLMM-12B

    68
    73
    transformers
    Image Segmentation

    canvit/probe-ade20k-40k-s1024-c64-in21k

    68
    canvit-pytorch
    Video Classification

    archit11/videomae-base-finetuned-fight-nofight

    68
    transformers
    Audio Classification

    7wolf/wav2ast-gender-classification

    68
    2
    transformers
    Visual Question Answering

    BUAADreamer/Yi-VL-34B-hf

    68
    5
    transformers
    Object Detection

    Perception365/VehicleNet-Y26s

    68
    6
    ultralytics
    Object Detection

    HLouy/yolov26m-sportsmot-football

    68
    1
    ultralytics
    Image Segmentation

    yuxindu/segvol

    68
    transformers
    Audio Classification

    xiaomi-research/TTS-PRISM-7B

    68
    Text To Audio

    michjosh/speecht5-hausa-tts

    68
    transformers
    Object Detection

    NMFS-OSI/yolo11m-esa-coral-icra-detector

    68
    ultralytics
    Image Feature Extraction

    nvidia/PS3-4K-SigLIP2

    68
    2
    Audio Classification

    Vladimirlv/ast-finetuned-audioset-10-10-0.4593-heart-sounds

    68
    2
    transformers
    Object Detection

    samu2117/detr-finetuned-chess

    68
    transformers
    Object Detection

    AnnaZhang/lwdetr_xlarge_60e_coco

    68
    transformers
    Object Detection

    Manas-Maahir/violence-detection-yolov26

    68
    ultralytics
    Video Classification

    Shawon16/VideoMAE_fold__0__20_epoch_p5_bdslw60_kinetics_check_longtail__

    68
    transformers
    Audio Classification

    eoinedge/hey-android-kws

    68
    Table Question Answering

    neulab/omnitab-large-16shot

    67
    3
    transformers
    Image Feature Extraction

    StreamFormer/OmniStream

    67
    3
    transformers
    Video Classification

    adeelhasan/videomae-base-finetuned-kinetics-finetuned-RTFeed

    67
    transformers
    Audio Classification

    Adam-ousse/ast-esc50-finetuned-fold1

    67
    2
    transformers
    Text To Audio

    piyazon/TTS-CV-Unique-Ug-2

    67
    4
    transformers
    Audio Classification

    xbgoose/wavlm-base-speech-emotion-recognition-russian-dusha-finetuned

    67
    1
    transformers
    470 / 587