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

    Showing 66736696 of 9,588 models

    Audio Classification

    KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru

    306
    1
    transformers
    Summarization

    mradermacher/DrMedra4B-i1-GGUF

    306
    transformers
    Zero Shot Classification

    startificial/nli-implementation

    305
    Depth Estimation

    xingyang1/Distill-Any-Depth-Small-hf

    304
    7
    transformers
    Depth Estimation

    jingheya/lotus-depth-d-v1-0

    304
    5
    diffusers
    Text To Video

    vrgamedevgirl84/LTX_2.3_Wild_West_Style_LoRa

    303
    4
    diffusers
    Zero Shot Classification

    alexandrainst/scandi-nli-large-v2

    302
    2
    Zero Shot Classification

    valhalla/distilbart-mnli-12-9

    302
    12
    transformers
    Text To Video

    alibaba-pai/Wan2.1-Fun-V1.1-1.3B-Control-Camera

    302
    14
    videox_fun
    Summarization

    panggi/t5-base-indonesian-summarization-cased

    301
    7
    transformers
    Zero Shot Classification

    hivetrace/gliner-guard-biencoder

    301
    3
    gliner2
    Object Detection

    Jesse020202/detr_finetuned_cppe5

    301
    transformers
    Text To Video

    gajesh/LTX-2.3-mlx-fp16

    301
    2
    mlx
    Question Answering

    mradermacher/Mistral-7B-Instruct-Uz-GGUF

    301
    2
    transformers
    Table Question Answering

    google/tapas-small-finetuned-sqa

    300
    1
    transformers
    Image Feature Extraction

    UCSC-VLAA/openvision-vit-large-patch14-224

    300
    5
    open_clip
    Summarization

    IMISLab/GreekT5-umt5-small-greeksum

    299
    1
    transformers
    Object Detection

    mradermacher/Polaris-VGA-0.8B-Post1.0-i1-GGUF

    298
    transformers
    Text To Audio

    KandirResearch/CiSiMi-v0.1

    298
    9
    transformers
    Text To Audio

    Marvis-AI/marvis-tts-250m-v0.2-MLX-8bit

    297
    4
    transformers
    Text To Audio

    forkjoin-ai/qwen3-tts-12hz-0.6b-customvoice

    297
    llama-cpp
    Image To Text

    StanfordAIMI/CheXagent-2-3b-srrg-impression

    297
    transformers
    Text To Audio

    ACE-Step/acestep-v15-xl-turbo-diffusers

    297
    13
    diffusers
    Robotics

    nvidia/GR00T-N1-2B

    297
    351
    279 / 400