🤖 AI Models
Trending AI models from Hugging Face — sorted by most downloads.
All Categories✍️ Text Generation🎨 Text to Image🖼️ Image Classification🏷️ Text Classification🌐 Translation📝 Summarization🎙️ Speech Recognition🔍 Object Detection
🤖 image-to-text
blip-image-captioning-base
Salesforce/blip-image-captioning-base
⬇ 2.2M❤️ 849
transformerspytorchtfblip
blip-image-captioning-large
Salesforce/blip-image-captioning-large
⬇ 1.4M❤️ 1.5K
transformerspytorchtfsafetensors
trocr-base-printed
microsoft/trocr-base-printed
⬇ 763.3K❤️ 205
transformerspytorchsafetensorsvision-encoder-decoder
pix2text-mfr
breezedeus/pix2text-mfr
⬇ 676.7K❤️ 53
transformersonnxvision-encoder-decoderimage-text-to-text
Nanonets-OCR2-3B
nanonets/Nanonets-OCR2-3B
⬇ 662.2K❤️ 500
transformerssafetensorsqwen2_5_vlimage-text-to-text
blip2-opt-2.7b-coco
Salesforce/blip2-opt-2.7b-coco
⬇ 555.5K❤️ 11
transformerspytorchsafetensorsblip-2
PP-OCRv5_server_det
PaddlePaddle/PP-OCRv5_server_det
⬇ 517.4K❤️ 59
PaddleOCROCRPaddlePaddletextline_detection
blip2-opt-2.7b
Salesforce/blip2-opt-2.7b
⬇ 433.2K❤️ 439
transformerspytorchsafetensorsblip-2
PaddleOCR-VL-1.5
PaddlePaddle/PaddleOCR-VL-1.5
⬇ 375.3K❤️ 574
PaddleOCRsafetensorspaddleocr_vlERNIE4.5
PP-LCNet_x1_0_doc_ori
PaddlePaddle/PP-LCNet_x1_0_doc_ori
⬇ 374.2K❤️ 10
PaddleOCROCRPaddlePaddledoc_img_orientation_classification
nougat-base
facebook/nougat-base
⬇ 340.0K❤️ 189
transformerspytorchsafetensorsvision-encoder-decoder
manga-ocr-base
kha-white/manga-ocr-base
⬇ 307.7K❤️ 170
transformerspytorchvision-encoder-decoderimage-text-to-text
en_PP-OCRv5_mobile_rec
PaddlePaddle/en_PP-OCRv5_mobile_rec
⬇ 297.5K❤️ 1
PaddleOCROCRPaddlePaddletextline_recognition
trocr-large-printed
microsoft/trocr-large-printed
⬇ 291.5K❤️ 179
transformerspytorchsafetensorsvision-encoder-decoder
trocr-large-handwritten
microsoft/trocr-large-handwritten
⬇ 241.8K❤️ 158
transformerspytorchvision-encoder-decoderimage-text-to-text
vit-gpt2-image-captioning
nlpconnect/vit-gpt2-image-captioning
⬇ 215.9K❤️ 927
transformerspytorchvision-encoder-decoderimage-text-to-text
PP-LCNet_x1_0_textline_ori
PaddlePaddle/PP-LCNet_x1_0_textline_ori
⬇ 179.7K❤️ 2
PaddleOCROCRPaddlePaddletextline_orientation_classification
HunyuanOCR
tencent/HunyuanOCR
⬇ 173.6K❤️ 567
transformerssafetensorshunyuan_vltext-generation
donut-base
naver-clova-ix/donut-base
⬇ 167.0K❤️ 252
transformerspytorchvision-encoder-decoderimage-text-to-text
dots.ocr
rednote-hilab/dots.ocr
⬇ 166.5K❤️ 1.3K
dots_ocrsafetensorstext-generationimage-to-text
kosmos-2-patch14-224
microsoft/kosmos-2-patch14-224
⬇ 159.8K❤️ 184
transformerspytorchsafetensorskosmos-2
trocr-base-handwritten
microsoft/trocr-base-handwritten
⬇ 159.1K❤️ 490
transformerspytorchsafetensorsvision-encoder-decoder