Models tagged "ocr" - AI Models Search

Answer questions and caption images from one to three input images, returning text. Handle visual question answering (VQ...

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

Generate captions and answer visual questions for images and videos from a text prompt. Accepts a single image or a vide...

🖼️ → 📝 • image-to-text • video-to-text • 219 runs

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

Answer questions about images from an image and text prompt, returning text. Perform visual question answering (VQA), im...

🖼️ → 📝 • image-to-text • ocr • visual-understanding • 3.4K runs

Analyze images to generate captions, detect objects with bounding boxes, and extract text (OCR). Accepts an image plus a...

🖼️ → 📝 • image-to-text • image-object-detection • ocr • 454.2K runs

Answer questions about images and extract information, returning text. Accepts an image plus a text prompt and outputs t...

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

Answer questions about images and caption them from an image plus text prompt, returning text. Perform visual recognitio...

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

Parse UI screenshots into structured UI elements for agentic automation. Accepts an image of a desktop, mobile, or web i...

🖼️ → 📝 • image-object-detection • ocr • image-to-text • 180.3K runs

Extract structured receipt data from an image and return JSON. Takes a receipt photo or scan as input and outputs a JSON...

ocr • document-to-json • receipt-parsing • 673 runs