Models tagged "ocr"

🤖 Model 🖼️ → 📝

chenxwh/deepseek-vl2

Answer questions about images and documents. Accepts 1–3 images plus an instruction and returns text for tasks like visu...

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

🤖 Model 🖼️ → 📝

lucataco/minicpm-v-4

Analyze images and videos to generate captions, answer visual questions, and summarize scenes. Accepts an image or a vid...

🖼️ → 📝 • image-to-text • video-to-text • ocr • 229 runs

🤖 Model 🖼️ → 📝

lucataco/florence-2-base

Caption images, detect objects, and extract text from an input image, returning text outputs. Accepts an image plus a ta...

🖼️ → 📝 • image-to-text • ocr • image-object-detection • 124.3K runs

🤖 Model 🖼️ → 📝

lucataco/ollama-llama3.2-vision-90b

Analyze images and generate text responses to prompts. Accepts an image and a text prompt, and outputs text for visual q...

🖼️ → 📝 • image-to-text • image-captioning • image-analysis • 3.4K runs

🤖 Model 🖼️ → 📝

lucataco/florence-2-large

Analyze images to generate captions, detect objects, and extract text (OCR). Accepts an image plus a task selector and o...

🖼️ → 📝 • image-to-text • image-object-detection • ocr • 471.5K runs

🤖 Model 🖼️ → 📝

deepseek-ai/deepseek-vl2-small

Answer questions about images, documents, charts, and tables. Takes an image and a text prompt and returns text. Support...

🖼️ → 📝 • image-to-text • ocr • visual-understanding • 1.4K runs

🤖 Model 🖼️ → 📝

lucataco/ollama-llama3.2-vision-11b

Analyze images and answer questions from an input image and text instruction, returning text. Support visual question an...

🖼️ → 📝 • image-to-text • image-captioning • image-analysis • 2.7K runs

🤖 Model 🖼️ → 📝

microsoft/omniparser-v2

Parse GUI screenshots into structured UI elements with bounding boxes and captions. Accepts an image of a desktop or mob...

🖼️ → 📝 • image-to-text • image-object-detection • ui-parsing • 185.5K runs

🤖 Model

sulthonmb/ocr-receipt

Extract structured purchase data from receipt images as JSON. Input a receipt image and output JSON with line items, qua...

ocr • document-to-json • receipt-parsing • 675 runs

🤖 Model

datalab-to/ocr

Extract text from images and documents in 90+ languages with OCR, returning plain text plus optional structured layout....

ocr • layout-analysis • table-recognition • 426 runs

🤖 Model

datalab-to/marker

Convert documents to Markdown and structured JSON. Accept PDF, DOC/DOCX, PPT/PPTX, and image files (PNG/JPG/WEBP) as inp...

pdf-to-markdown • document-to-json • ocr • 361 runs

🤖 Model

lucataco/deepseek-ocr

Extract text and document structure from an input image into Markdown or plain text. Handle PDFs, scans, screenshots, re...

ocr • document-parsing • document-to-markdown • 25.0K runs

🤖 Model 🖼️ → 📝

lucataco/qwen-vl-chat

Answer questions about images. Accept an image and a text prompt and return text outputs for visual question answering,...

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 825.5K runs

🤖 Model 🖼️ → 📝

nvidia/nemotron-nano-v2-12b-vl

Extract structured data, answer visual questions, and summarize videos from images and videos. Accepts 1–4 images or a v...

🖼️ → 📝 • image-to-text • video-to-text • ocr • 9 runs

🤖 Model 🖼️ → 📝

ghostljj/deepseek-ocr

Extract text and document structure from images into plain text or Markdown. Accept an image and a task type (markdown,...

🖼️ → 📝 • ocr • image-to-text • image-object-detection • 19 runs

🤖 Model 🖼️ → 📝

eiby777/olmocr-2-7b-1025-fp8

Extract text and tables from document images or PDFs. Accepts an image or a selected PDF page and returns structured tex...

🖼️ → 📝 • ocr • image-to-text • 10 runs

🤖 Model 🖼️ → 📝

lucataco/blip3-phi3-mini-instruct-r-v1

Answer questions about images and generate captions from an image input and a natural-language question, returning text....

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 399 runs

🤖 Model 🖼️ → 📝

perceptron-ai-inc/isaac-0.1

Answer questions about images with grounded visual references. Takes an image and a natural-language prompt and returns...

🖼️ → 📝 • image-to-text • image-object-detection • ocr • 7 runs

🤖 Model 🖼️ → 📝

jyoung105/honeybee

Answer questions about images from a text prompt and an image input, returning a text response. Perform visual question...

🖼️ → 📝 • image-to-text • vqa • ocr • 29 runs

🤖 Model 🖼️ → 📝

chenxwh/cogvlm2

Caption images and answer visual questions from an image plus an optional text prompt, returning text. Handle OCR-style...

🖼️ → 📝 • image-to-text • ocr • visual-question-answering • 6.6K runs