Models tagged "ocr"

🤖 Model

sljeff/dots.ocr

Extract document layout and text from an image into structured JSON. Accepts a scanned page or document image and return...

ocr • document-to-json • document-layout • 4.2K runs

🤖 Model 🖼️

lucataco/smolvlm-instruct

Answer questions about images and documents from an image and a text prompt, returning text. Handle visual question answ...

🖼️ • image-captioning • image-analysis • visual-understanding • 3.3K runs

🤖 Model 🖼️ → 📝

cjwbw/cogagent-chat

Answer questions about images and GUI screenshots, returning text responses or, for UI tasks, a step-by-step plan with n...

🖼️ → 📝 • image-to-text • ocr • gui-agent • 2.3K runs

🤖 Model 🖼️ → 📝

lucataco/paligemma-3b-pt-224

Caption images and answer visual questions from an image plus a text prompt, returning text. Support multilingual prompt...

🖼️ → 📝 • image-to-text • visual-question-answering • ocr • 1.5K runs

🤖 Model

cuuupid/markitdown

Convert PDFs, Office documents, images, audio, HTML, and other files to clean Markdown text. Accepts PDF, DOCX, PPTX, XL...

pdf-to-markdown • ocr • speech-to-text • 72.1K runs

🤖 Model

aodianyun/ad-pdf-extract

Convert PDFs to Markdown text. Accepts a PDF input and extracts content using the embedded text layer (txt) or optical c...

pdf-to-markdown • ocr • 235 runs

🤖 Model 🖼️ → 📝

jyoung105/imp

Answer questions about images. Accept an image and a natural-language prompt and return text, enabling visual question a...

🖼️ → 📝 • image-to-text • visual-question-answering • ocr • 71 runs

🤖 Model 🖼️ → 📝

jyoung105/moondream

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

🖼️ → 📝 • image-to-text • visual-question-answering • ocr • 309 runs

🤖 Model

vwtyler/ocr-pdf

Extract text from PDF documents using OCR, returning plain text. Accepts a PDF as input, converts each page to an image,...

ocr • pdf-to-text • 2.5K runs

🤖 Model

lucataco/olmocr-7b

Extract text and layout metadata from PDF pages. Takes a PDF and page number as input and returns a structured JSON stri...

ocr • document-to-json • 4.0K runs

🤖 Model 🖼️ → 📝

jigsawstack/vocr

Extract text and structured data from images and multi-page PDFs. Provide an image or PDF plus a prompt string for scene...

🖼️ → 📝 • ocr • image-to-text • document-to-json • 20 runs

🤖 Model

qr2ai/img2txt

Extract text from images and PDFs using OCR. Accepts an image or PDF input and returns the recognized text as plain text...

ocr • arabic-ocr • 34 runs

🤖 Model 🖼️ → 📝

hiscodesmells/florence-2-base

Analyze images to caption content, detect objects, segment regions, and extract text (OCR). Accepts an image and an opti...

🖼️ → 📝 • image-to-text • image-object-detection • ocr • 286 runs

🤖 Model

jichengdu/got-ocr-2

Extract text from images with OCR. Accepts a single image input and returns the recognized text; when the format option...

ocr • 302 runs

🤖 Model

hexiaochun/pp-ocr-v4

Extract text from images (OCR). Accepts an image and an optional language code (default Chinese) and returns recognized...

ocr • 419.7K runs

🤖 Model

charlesfrye/text-recognizer-gpu

Recognizes and extracts text from images of handwritten text, outputting the detected text as a string.

text-recognition • optical-character-recognition • ocr • 19.9K runs

🤖 Model 🖼️ → 📝

jd7h/texify

Extract LaTeX-formatted math from images or PDFs and return Markdown text. Takes an image (or PDF) containing equations...

🖼️ → 📝 • ocr • image-to-text • pdf-to-markdown • 72 runs

🤖 Model 🖼️ → 📝

zsxkib/easyocr

Extract on-screen text with pixel coordinates from images and screenshots. Takes an image as input and returns readable...

🖼️ → 📝 • ocr • image-to-text • 96 runs

🤖 Model 🖼️ → 📝

cjwbw/pix2struct

Answer questions about images and documents and generate captions from an image plus a text prompt, returning text. Sele...

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 6.1K runs

🤖 Model 🖼️ → 📝

lucataco/moondream2

Caption images and answer visual questions from an input image and text prompt. Accepts an image and a natural-language...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 4.2M runs