NEWWhy single embeddings fail for video.Read the post →

    AI Model Hub

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

    9,588 models available

    Showing 70577080 of 9,588 models

    Image Feature Extraction

    timm/vit_pe_core_tiny_patch16_384.fb

    201
    1
    timm
    Image Feature Extraction

    ibm-nasa-geospatial/Prithvi-WxC-1.0-2300M

    201
    82
    terratorch
    Text To Video

    LiseTY/my_first_lora_v9-lora

    201
    1
    diffusers
    Audio Classification

    amiriparian/ExHuBERT

    201
    19
    transformers
    Question Answering

    elgeish/cs224n-squad2.0-albert-base-v2

    201
    transformers
    Zero Shot Image Classification

    timm/eva02_enormous_patch14_clip_224.laion2b

    201
    open_clip
    Object Detection

    aipluxtechnology/insurance-DocLayout-YOLO

    200
    ultralytics
    Object Detection

    melihuzunoglu/ppe-detection

    200
    1
    ultralytics
    Image To Text

    mradermacher/Gliese-OCR-7B-Post2.0-final-GGUF

    200
    1
    transformers
    Image To Text

    Kansallisarkisto/estonian-large-handwritten

    200
    2
    Audio Classification

    DBD-research-group/Bird-MAE-Huge

    200
    transformers
    Audio Classification

    sanchit-gandhi/distilhubert-finetuned-gtzan

    200
    3
    transformers
    Question Answering

    gauravgupta81/Llama-Open-Finance-8B-Q4_K_M-GGUF

    200
    transformers
    Image Segmentation

    lorebianchi98/Talk2DINOv3-ViTL

    199
    Pytorch
    Image To Text

    EasyDeL/Qwen3.5-9B

    199
    easydel
    Question Answering

    DenBond2002/albert-base-finetuned-adcm-v6data

    199
    transformers
    Image To Text

    mradermacher/Lh41-1042-Magellanic-7B-0711-i1-GGUF

    199
    transformers
    Audio To Audio

    LocalAI-io/LocalVQE

    199
    4
    pytorch
    Question Answering

    dccuchile/roberta-large-bne-finetuned-qa-sqac

    199
    transformers
    Depth Estimation

    prs-eth/marigold-depth-hr-v1-1

    198
    10
    diffusers
    Object Detection

    nsugianto/detr-resnet50_finetuned_lstabledetv1s9_lsdocelementdetv1type3_session8

    198
    transformers
    Object Detection

    humellad/yolo_finetuned_fruits

    198
    transformers
    Object Detection

    AXERA-TECH/yolo26-obb

    198
    Depth Estimation

    WEO-SAS/chm-meta-v2

    197
    transformers
    295 / 400