NEWAgents can now see video via MCP.Try it now →

    AI Model Hub

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

    9,588 models available

    Schedule DemoRead Documentation

    Showing 5377–5400 of 9,588 models

    Feature Extraction

    mesolitica/mistral-embedding-191m-8k-contrastive

    2K
    transformers
    View Details
    Question Answering

    deepset/gelectra-base-germanquad

    2K
    26
    transformers
    View Details
    Audio Classification

    davethaler/whale-call-detector

    2K
    transformers
    View Details
    Text To Speech

    kakao-enterprise/vits-vctk

    2K
    15
    transformers
    View Details
    Image Segmentation

    Acly/BiRefNet-GGUF

    2K
    11
    View Details
    Feature Extraction

    mlx-community/bge-m3-mlx-8bit

    2K
    mlx
    View Details
    Feature Extraction

    LSX-UniWue/ModernGBERT_1B

    2K
    10
    transformers
    View Details
    Feature Extraction

    MERaLiON/MERaLiON-SER-v1

    2K
    7
    transformers
    View Details
    Text To Video

    yaleiyaleichiling/NSFW-Anime-wan-5B

    2K
    47
    diffusers
    View Details
    Feature Extraction

    cstr/jina-v5-nano-GGUF

    2K
    View Details
    Feature Extraction

    OpenSearch-AI/Ops-MM-embedding-v1-2B

    2K
    17
    View Details
    Robotics

    ar0s/groot_libero

    2K
    lerobot
    View Details
    Feature Extraction

    n24q02m/Qwen3-Embedding-0.6B-ONNX

    2K
    1
    View Details
    Table Question Answering

    google/tapas-small-finetuned-wtq

    2K
    6
    transformers
    View Details
    Image To Image

    black-forest-labs/FLUX.2-klein-4b-nvfp4

    2K
    34
    diffusion-single-file
    View Details
    Any To Any

    prithivMLmods/gemma-4-E4B-it-NVFP4

    2K
    3
    transformers
    View Details
    Image Feature Extraction

    xtxx/Digepath

    2K
    6
    timm
    View Details
    Image To Text

    PaddlePaddle/th_PP-OCRv5_mobile_rec

    2K
    2
    PaddleOCR
    View Details
    Image To Image

    1038lab/SDMatte

    2K
    diffusers
    View Details
    Feature Extraction

    shtoshni/longformer_coreference_ontonotes

    2K
    1
    transformers
    View Details
    Feature Extraction

    Xenova/GIST-small-Embedding-v0

    2K
    2
    transformers.js
    View Details
    Image To Image

    huggingworld/onnx-image-models

    2K
    1
    ml-agents
    View Details
    Feature Extraction

    tanganke/clip-vit-base-patch32_rendered-sst2

    2K
    transformers
    View Details
    Text To Video

    tencent/HunyuanVideo-1.5

    2K
    981
    HunyuanVideo-1.5
    View Details
    225 / 400

    Previous

    Connectors

    Next

    Retrievers