NEWVectors or files. Pick a path.Start →

    Image To Text Models

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

    478 models available

    Showing 124 of 478 models

    Image To Text

    Salesforce/blip-image-captioning-base

    1.6M
    867
    transformers
    Image To Text

    numind/NuExtract3

    1.2M
    294
    transformers
    Image To Text

    Salesforce/blip-image-captioning-large

    765K
    1,477
    transformers
    Image To Text

    PaddlePaddle/PP-OCRv5_server_det

    640K
    73
    PaddleOCR
    Image To Text

    ibm-granite/granite-vision-3.3-2b

    458K
    85
    Image To Text

    PaddlePaddle/UVDoc

    450K
    11
    PaddleOCR
    Image To Text

    kha-white/manga-ocr-base

    434K
    176
    transformers
    Image To Text

    microsoft/trocr-small-handwritten

    426K
    63
    transformers
    Image To Text

    PaddlePaddle/PP-LCNet_x1_0_doc_ori

    385K
    16
    PaddleOCR
    Image To Text

    PaddlePaddle/en_PP-OCRv5_mobile_rec

    374K
    2
    PaddleOCR
    Image To Text

    microsoft/trocr-base-printed

    331K
    215
    transformers
    Image To Text

    microsoft/trocr-large-handwritten

    204K
    162
    transformers
    Image To Text

    PaddlePaddle/PP-LCNet_x1_0_textline_ori

    197K
    6
    PaddleOCR
    Image To Text

    microsoft/kosmos-2-patch14-224

    172K
    184
    transformers
    Image To Text

    microsoft/trocr-base-handwritten

    164K
    502
    transformers
    Image To Text

    PaddlePaddle/PP-OCRv5_server_rec

    153K
    29
    PaddleOCR
    Image To Text

    lightonai/LightOnOCR-1B-1025

    142K
    254
    transformers
    Image To Text

    microsoft/trocr-large-printed

    117K
    180
    transformers
    Image To Text

    optimum-intel-internal-testing/pix2struct-tiny-random

    109K
    Image To Text

    PaddlePaddle/PP-OCRv6_medium_det

    105K
    25
    PaddleOCR
    Image To Text

    PaddlePaddle/PP-OCRv5_mobile_det

    97K
    28
    PaddleOCR
    Image To Text

    facebook/nougat-base

    96K
    188
    transformers
    Image To Text

    PaddlePaddle/PP-OCRv6_medium_rec

    92K
    21
    PaddleOCR
    Image To Text

    alibaba-damo/mgp-str-base

    85K
    65
    transformers
    1 / 20