HomeModelsImage To Text

Best Image To Text Models

396

396 image to text models on MLForge, ranked by downloads — including work from Salesforce, PaddlePaddle, numind, microsoft. Compare, download and run them locally on your own GPU. Free tier.

Start freeDesktop app

Top Image To Text models

B Salesforce/blip-image-captioning-base Image To Text 1.9M 863 🤗 HF B Salesforce/blip-image-captioning-large Image To Text ·469.7M params 737.4K 1.5K 🤗 HF P PaddlePaddle/PP-OCRv5_server_det Image To Text 587.3K 73 🤗 HF N numind/NuExtract3 Image To Text ·4.5B params 520.7K 270 🤗 HF U PaddlePaddle/UVDoc Image To Text 512.8K 11 🤗 HF T microsoft/trocr-small-handwritten Image To Text 448.6K 63 🤗 HF P PaddlePaddle/PP-LCNet_x1_0_doc_ori Image To Text 445.3K 16 🤗 HF M kha-white/manga-ocr-base Image To Text 389.4K 176 🤗 HF G ibm-granite/granite-vision-3.3-2b Image To Text ·3.0B params 343.3K 85 🤗 HF E PaddlePaddle/en_PP-OCRv5_mobile_rec Image To Text 288.9K 2 🤗 HF P PaddlePaddle/PP-LCNet_x1_0_textline_ori Image To Text 274.6K 6 🤗 HF T microsoft/trocr-base-printed Image To Text ·333.3M params 251.5K 209 🤗 HF L lightonai/LightOnOCR-1B-1025 Image To Text ·1.2B params 199.9K 254 🤗 HF P PaddlePaddle/PP-OCRv5_server_rec Image To Text 189.4K 29 🤗 HF T microsoft/trocr-large-handwritten Image To Text 182.4K 162 🤗 HF K microsoft/kosmos-2-patch14-224 Image To Text ·1.7B params 166.7K 185 🤗 HF D naver-clova-ix/donut-base Image To Text 166.0K 254 🤗 HF T microsoft/trocr-base-stage1 Image To Text ·384.3M params 149.0K 18 🤗 HF N facebook/nougat-base Image To Text ·348.7M params 145.4K 188 🤗 HF T microsoft/trocr-large-printed Image To Text ·608.1M params 133.0K 180 🤗 HF P PaddlePaddle/PP-OCRv5_mobile_det Image To Text 129.4K 28 🤗 HF T microsoft/trocr-base-handwritten Image To Text ·333.3M params 124.0K 498 🤗 HF M alibaba-damo/mgp-str-base Image To Text ·148.0M params 110.8K 65 🤗 HF P PaddlePaddle/PP-OCRv6_medium_det Image To Text 89.0K 23 🤗 HF P PaddlePaddle/PP-OCRv6_medium_rec Image To Text 79.9K 21 🤗 HF P PaddlePaddle/PP-OCRv5_mobile_rec Image To Text 74.5K 16 🤗 HF M rtr46/meiki.txt.recognition.v0 Image To Text 65.6K 6 🤗 HF V nlpconnect/vit-gpt2-image-captioning Image To Text 64.4K 931 🤗 HF M rtr46/meiki.text.detect.v0 Image To Text 48.2K 3 🤗 HF T optimum-intel-internal-testing/trocr-small-handwritten Image To Text 39.5K 🤗 HF L PaddlePaddle/latin_PP-OCRv5_mobile_rec Image To Text 37.5K 5 🤗 HF T microsoft/trocr-small-printed Image To Text ·61.4M params 36.3K 50 🤗 HF N facebook/nougat-small Image To Text ·247.4M params 29.5K 30 🤗 HF G unsloth/GLM-OCR Image To Text 28.0K 34 🤗 HF N numind/NuMarkdown-8B-Thinking Image To Text ·8.3B params 26.1K 477 🤗 HF E PaddlePaddle/en_PP-OCRv4_mobile_rec Image To Text 24.6K 6 🤗 HF P PaddlePaddle/PP-DocLayout_plus-L Image To Text 20.8K 16 🤗 HF P PaddlePaddle/PP-OCRv4_mobile_det Image To Text 19.6K 5 🤗 HF P PaddlePaddle/PP-DocBlockLayout Image To Text 18.4K 5 🤗 HF D naver-clova-ix/donut-base-finetuned-cord-v2 Image To Text 18.3K 120 🤗 HF R PaddlePaddle/RT-DETR-L_wired_table_cell_det Image To Text 18.3K 3 🤗 HF P PaddlePaddle/PP-LCNet_x1_0_table_cls Image To Text 17.9K 2 🤗 HF R PaddlePaddle/RT-DETR-L_wireless_table_cell_det Image To Text 17.6K 3 🤗 HF S PaddlePaddle/SLANeXt_wired Image To Text 17.4K 3 🤗 HF S PaddlePaddle/SLANet_plus Image To Text 15.7K 2 🤗 HF P PaddlePaddle/PP-FormulaNet_plus-L Image To Text 14.5K 5 🤗 HF N nvidia/nemotron-ocr-v2 Image To Text 13.2K 219 🤗 HF T OleehyO/TexTeller Image To Text ·298.1M params 13.1K 45 🤗 HF G microsoft/git-base Image To Text ·176.6M params 11.8K 111 🤗 HF T microsoft/trocr-small-stage1 Image To Text 11.4K 13 🤗 HF K PaddlePaddle/korean_PP-OCRv5_mobile_rec Image To Text 11.2K 15 🤗 HF T PaddlePaddle/th_PP-OCRv5_mobile_rec Image To Text 10.7K 2 🤗 HF D zhiyuanyou/DeQA-Score-Mix3 Image To Text ·8.2B params 9.2K 6 🤗 HF T Riksarkivet/trocr-base-handwritten-hist-swe-2 Image To Text ·384.9M params 9.0K 15 🤗 HF C nyu-visionx/Cambrian-S-7B Image To Text ·8.0B params 8.0K 5 🤗 HF B unography/blip-large-long-cap Image To Text ·469.7M params 7.8K 5 🤗 HF P PaddlePaddle/PP-LCNet_x0_25_textline_ori Image To Text 7.5K 3 🤗 HF Q mradermacher/Qwen2.5-VL-7B-Abliterated-Caption-it-GGUF Image To Text 6.8K 73 🤗 HF E PaddlePaddle/eslav_PP-OCRv5_mobile_rec Image To Text 6.5K 4 🤗 HF P PaddlePaddle/PP-OCRv4_mobile_rec Image To Text 6.4K 3 🤗 HF P PaddlePaddle/PP-Chart2Table Image To Text 6.1K 5 🤗 HF P google/pix2struct-textcaps-base Image To Text ·282.3M params 5.7K 29 🤗 HF Q zhangzicheng/q-sit-mini Image To Text ·893.7M params 5.6K 🤗 HF P PaddlePaddle/PP-OCRv3_mobile_det Image To Text 5.3K 1 🤗 HF F tiiuae/Falcon-OCR Image To Text ·269.9M params 5.1K 119 🤗 HF V ydshieh/vit-gpt2-coco-en Image To Text ·239.2M params 5.0K 39 🤗 HF V Xenova/vit-gpt2-image-captioning Image To Text 5.0K 29 🤗 HF B macpaw-research/blip-icon-captioning Image To Text ·247.4M params 4.9K 1 🤗 HF D PaddlePaddle/devanagari_PP-OCRv5_mobile_rec Image To Text 4.4K 🤗 HF K Darayut/khmer-text-recognition Image To Text ·17.6M params 4.2K 1 🤗 HF T microsoft/trocr-base-str Image To Text 4.0K 6 🤗 HF P breezedeus/pix2text-mfr Image To Text 4.0K 57 🤗 HF L noctrex/LightOnOCR-2-1B-ocr-soup-GGUF Image To Text 4.0K 10 🤗 HF G microsoft/git-base-coco Image To Text 3.9K 21 🤗 HF G microsoft/git-large-coco Image To Text ·394.2M params 3.9K 106 🤗 HF M opendatalab/MinerU-Diffusion-V1-0320-2.5B Image To Text ·2.7B params 3.8K 26 🤗 HF M Felldude/Ministral-3-8B-Uncensored-FP8 Image To Text ·8.9B params 3.7K 5 🤗 HF P PaddlePaddle/PP-OCRv6_medium_det_safetensors Image To Text ·22.0M params 3.4K 102 🤗 HF G mradermacher/Garnet-OCR-3B-0422-i1-GGUF Image To Text 3.2K 1 🤗 HF A PaddlePaddle/arabic_PP-OCRv5_mobile_rec Image To Text 3.2K 4 🤗 HF P google/pix2struct-base Image To Text ·282.3M params 3.0K 79 🤗 HF P PaddlePaddle/PP-OCRv6_small_det Image To Text 3.0K 17 🤗 HF F FireRedTeam/FireRed-OCR Image To Text ·2.1B params 3.0K 159 🤗 HF Q fairy322/Qwen2.5-VL-7B-Abliterated-Caption-it-i1-GGUF Image To Text 2.9K 🤗 HF P PaddlePaddle/PP-OCRv6_small_rec Image To Text 2.9K 14 🤗 HF L xtuner/llava-llama-3-8b-v1_1-gguf Image To Text 2.9K 225 🤗 HF C IAMJB/chexpert-mimic-cxr-findings-baseline Image To Text ·61.3M params 2.8K 2 🤗 HF P PaddlePaddle/PP-OCRv4_server_det Image To Text 2.8K 2 🤗 HF C IAMJB/chexpert-mimic-cxr-impression-baseline Image To Text ·67.8M params 2.7K 🤗 HF E PaddlePaddle/en_PP-OCRv3_mobile_rec Image To Text 2.6K 1 🤗 HF S PaddlePaddle/SLANeXt_wireless Image To Text 2.6K 1 🤗 HF P PaddlePaddle/PP-DocLayout-L Image To Text 2.6K 6 🤗 HF P mradermacher/PaddleOCR-VL-1.6-GGUF Image To Text 2.6K 10 🤗 HF G mlx-community/GLM-OCR-bf16 Image To Text ·1.1B params 2.5K 29 🤗 HF D naver-clova-ix/donut-base-finetuned-rvlcdip Image To Text 2.5K 20 🤗 HF P PaddlePaddle/PP-OCRv6_medium_rec_safetensors Image To Text ·19.2M params 2.4K 21 🤗 HF P PaddlePaddle/PP-OCRv6_tiny_det Image To Text 2.3K 17 🤗 HF T kazars24/trocr-base-handwritten-ru Image To Text ·333.9M params 2.3K 16 🤗 HF N numind/NuExtract3-FP8 Image To Text ·4.7B params 2.3K 5 🤗 HF P PaddlePaddle/PP-OCRv6_tiny_rec Image To Text 2.2K 11 🤗 HF T microsoft/trocr-large-str Image To Text 2.2K 17 🤗 HF P PaddlePaddle/PP-OCRv4_server_rec_doc Image To Text 2.1K 2 🤗 HF M mayocream/manga-ocr Image To Text 2.1K 4 🤗 HF K mrrtmob/kiri-ocr Image To Text 2.1K 9 🤗 HF P PaddlePaddle/PP-OCRv6_tiny_rec_safetensors Image To Text ·1.1M params 2.0K 19 🤗 HF N Norm/nougat-latex-base Image To Text ·348.7M params 2.0K 82 🤗 HF L xtuner/llava-phi-3-mini-hf Image To Text ·4.1B params 2.0K 53 🤗 HF P breezedeus/pix2text-mfr-1.5 Image To Text 2.0K 1 🤗 HF U LoJexLLM/Unlimited-OCR-MLX Image To Text ·3.3B params 2.0K 11 🤗 HF Q KuroTo4ka/Qwen3-VL-8B-Instruct-Unredacted-MAX-Quants-GGUF Image To Text 1.9K 6 🤗 HF H JustANormalTinkerer/hayai-ocr Image To Text ·133.1M params 1.8K 🤗 HF T microsoft/trocr-large-stage1 Image To Text ·608.1M params 1.8K 27 🤗 HF L PaddlePaddle/latin_PP-OCRv3_mobile_rec Image To Text 1.8K 1 🤗 HF P PaddlePaddle/PP-OCRv5_server_rec_safetensors Image To Text ·21.1M params 1.8K 2 🤗 HF P breezedeus/pix2text-mfd-1.5 Image To Text 1.7K 🤗 HF I logasanjeev/indian-id-validator Image To Text 1.7K 7 🤗 HF S sbintuitions/sarashina2.2-vision-3b Image To Text ·3.8B params 1.7K 19 🤗 HF P PaddlePaddle/PP-OCRv3_mobile_rec Image To Text 1.6K 1 🤗 HF H mradermacher/HunyuanOCR-GGUF Image To Text 1.6K 🤗 HF A PaddlePaddle/arabic_PP-OCRv3_mobile_rec Image To Text 1.5K 4 🤗 HF

Showing the top 120 of 396 by downloads. Browse all in MLForge →

Other tasks

Text Generation 872Image Text To Text 523Image Classification 499Time Series Forecasting 498Automatic Speech Recognition 494Video Classification 492Audio Classification 484Image Segmentation 480Text To Speech 475Translation 464Zero Shot Image Classification 463Text To Image 461Object Detection 447Other 423Depth Estimation 391Reinforcement Learning 390Question Answering 372Summarization 343Token Classification 316Sentence Similarity 147