Models tagged "ocr"

🤖 Model

abiruyt/text-extract-ocr

Extract text from images with OCR. Takes a single image as input and outputs the detected text as a plain string for cop...

ocr • 90.0M runs

🤖 Model

bytedance/dolphin

Parse PDFs and document images into structured Markdown or JSON. Perform page-level layout analysis to recover reading o...

ocr • pdf-to-markdown • document-to-json • 926 runs

🤖 Model 🖼️ → 📝

lucataco/qwen2-vl-7b-instruct

Caption images and long videos and answer visual questions, returning text. Accepts an image or video plus an instructio...

🖼️ → 📝 • image-to-text • video-to-text • ocr • 259.0K runs

🤖 Model 🖼️

nomagick/qwen-vl-chat

Analyze images in conversational chat to answer questions, caption scenes, and localize objects with bounding boxes. Acc...

🖼️ • image-captioning • visual-understanding • image-analysis • 1.1K runs

🤖 Model 🖼️ → 📝

ibm-granite/granite-vision-3.2-2b

Extract text and answer questions about document images. Accepts an image and a text prompt and outputs text for OCR, ta...

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 118.0K runs

🤖 Model 🖼️ → 📝

cuuupid/glm-4v-9b

Answer questions about images, perform OCR, and caption visual content. Takes an image and a text prompt and outputs tex...

🖼️ → 📝 • image-to-text • ocr • image-analysis • 92.3K runs

🤖 Model 🖼️ → 📝

lucataco/moondream1

Answer questions about images from an image input and a text prompt, returning text. Support visual question answering (...

🖼️ → 📝 • image-to-text • ocr • 11.5K runs

🤖 Model 🖼️ → 📝

deepseek-ai/deepseek-vl2

Answer questions about images and produce text output. Handle image captioning, visual question answering (VQA), optical...

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 70.5K runs

🤖 Model 🎥

sai88uk/minicpm-v-45-v9

Answer questions about images and videos. Accepts an image or a video plus a question and returns text, enabling visual...

🎥 • video-to-text • image-captioning • image-analysis • 1.1K runs

🤖 Model 🖼️ → 📝

deepseek-ai/janus-pro-7b

Answer questions about images and return text. Accepts an image and a natural-language question, and outputs textual res...

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 13.3K runs

🤖 Model 🖼️ → 📝

lucataco/llama-3-vision-alpha

Caption images and answer visual questions from an image and a text prompt, returning text. Add visual understanding to...

🖼️ → 📝 • image-to-text • visual-question-answering • image-captioning • 5.8K runs

🤖 Model 🖼️ → 📝

lucataco/idefics-8b

Answer questions about an image from a text prompt and return text. Perform visual question answering, image captioning,...

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 1.1K runs

🤖 Model

cudanexus/nougat

Convert academic PDFs to text using OCR. Accepts a PDF document as input and returns formatted plain text suitable for s...

ocr • pdf-to-text • 241 runs

🤖 Model

cuuupid/marker

Convert PDFs and ebooks to Markdown. Accepts PDF, EPUB, MOBI, XPS, and FB2, including scanned documents; performs fast O...

pdf-to-markdown • ocr • 2.8K runs

🤖 Model

cudanexus/ocr-surya

Extract text from images and PDFs with multilingual OCR. Run line-level text detection or full OCR on selected pages and...

ocr • multilingual-ocr • 6.5K runs

🤖 Model

awilliamson10/meta-nougat

Extract text from academic PDF documents. Accepts a PDF input and returns a plain-text transcription using neural OCR op...

ocr • pdf-to-text • 4.8K runs

🤖 Model 🖼️ → 📝

mickeybeurskens/latex-ocr

Convert images of mathematical equations into LaTeX code. Accepts an image input and returns a LaTeX string, performing...

🖼️ → 📝 • ocr • image-to-text • latex • 867 runs

🤖 Model

willywongi/donut

Extract structured data from receipt images into JSON. Input a receipt image; output structured key–value fields and lin...

document-to-json • ocr • receipt-parsing • 2.2K runs

🤖 Model 🖼️ → 📝

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

Extract structured information and answer questions from documents, charts, tables, diagrams, and general images. Accept...

🖼️ → 📝 • image-to-text • ocr • image-analysis • 38.7K runs

🤖 Model 🖼️ → 📝

deepseek-ai/janus-pro-1b

Answer questions about images. Takes an image and a natural-language question as input and returns a text answer. Suppor...

🖼️ → 📝 • image-to-text • vqa • visual-understanding • 6.7K runs