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.

    9,002 models available

    Showing 31213144 of 9,002 models

    Image Feature Extraction

    timm/samvit_base_patch16.sa1b

    13K
    1
    timm
    Sentence Similarity

    NeuML/glove-6B-quantized

    13K
    3
    staticvectors
    Image Segmentation

    ZhengPeng7/BiRefNet_dynamic

    13K
    9
    birefnet
    Text To Speech

    Xenova/mms-tts-eng

    13K
    2
    transformers.js
    Text Classification

    TakoData/en_tako_query_analyzer

    13K
    spacy
    Image Classification

    timm/vit_base_r50_s16_384.orig_in21k_ft_in1k

    13K
    4
    timm
    Depth Estimation

    LiheYoung/depth_anything_vitb14

    13K
    3
    transformers
    Audio Classification

    3loi/SER-Odyssey-Baseline-WavLM-Categorical

    13K
    10
    transformers
    Depth Estimation

    depth-anything/DA3MONO-LARGE

    13K
    13
    depth-anything-3
    Fill Mask

    DeepChem/ChemBERTa-100M-MLM

    13K
    5
    transformers
    Image To Image

    XLabs-AI/flux-ip-adapter-v2

    13K
    315
    diffusers
    Image Classification

    CaicedoLab/MorphEm

    13K
    1
    Fill Mask

    nghuyong/ernie-3.0-xbase-zh

    13K
    23
    transformers
    Zero Shot Image Classification

    timm/PE-Core-B-16

    13K
    open_clip
    Image Classification

    timm/pvt_v2_b2.in1k

    13K
    1
    timm
    Sentence Similarity

    bclavie/JaColBERTv2

    13K
    16
    RAGatouille
    Any To Any

    mradermacher/DarkIdol-Gemma-4-31B-it-i1-GGUF

    13K
    1
    transformers
    Fill Mask

    ai-forever/ruBert-base

    13K
    43
    transformers
    Sentence Similarity

    ENOSYS/Octen-Embedding-8B-750-v1-GGUF

    13K
    2
    sentence-transformers
    Feature Extraction

    allenai/specter

    13K
    65
    transformers
    Zero Shot Image Classification

    timm/vit_base_patch32_clip_224.laion400m_e32

    13K
    open_clip
    Zero Shot Classification

    cointegrated/rubert-base-cased-nli-threeway

    13K
    37
    transformers
    Image To Image

    lilylilith/AnyPose

    13K
    455
    diffusers
    Image Feature Extraction

    timm/convnext_base.dinov3_lvd1689m

    13K
    1
    timm
    131 / 376