image-to-text AI Models

🤖 Model 🖼️ → 📝

pku-yuangroup/llava-cot

Answer questions about images with step-by-step reasoning. Take an image and an optional text prompt and output text, in...

🖼️ → 📝 • image-to-text • image-captioning • image-analysis • 46 runs

🤖 Model 🖼️ → 📝

jimothyjohn/phi3-vision-instruct

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

🖼️ → 📝 • image-to-text • image-captioning • visual-understanding • 201 runs

🤖 Model 🖼️ → 📝

justmalhar/meta-llama-3.2-11b-vision

Answer questions about images and generate captions from an image and a text prompt, returning text. Perform visual ques...

🖼️ → 📝 • image-to-text • image-captioning • image-analysis • 261 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 🖼️ → 📝

openai/gpt-5-mini

Generates text responses based on prompts or multi-turn conversations, designed as a faster and more cost-effective vers...

🖼️ → 📝 • text-generation • image-to-text • code-generation • 2.2M runs

🤖 Model 🖼️ → 📝

yoadtew/arithmetic

Generates descriptive text captions from three input images using arithmetic operations on image features. The model com...

🖼️ → 📝 • image-to-text • image-captioning • visual-understanding • 94 runs

🤖 Model 🖼️ → 📝

replicate/resnet

Classify images into categories. Accepts a single image and returns top predicted classes with probabilities using a Res...

🖼️ → 📝 • image-to-text • image-classification • 8.8K runs

🤖 Model

lucataco/deepseek-ocr

Converts images containing documents, PDFs, charts, and handwritten text into structured markdown while preserving forma...

ocr • pdf-to-markdown • document-to-json • 93.6K runs

🤖 Model 🖼️

lhungting-ship-it/id-card-nationality

Classify the nationality of a national ID card from an image. Accepts a photo or scan of an ID document and returns the...

🖼️ • image-classification • document-classification • id-card • 11 runs

🤖 Model 🖼️ → 📝

rmokady/clip_prefix_caption

Generate image captions from a single image input. Select from COCO or Conceptual Captions modes and optionally use beam...

🖼️ → 📝 • image-to-text • image-captioning • 1.7M runs

🤖 Model 🖼️ → 📝

yoadtew/zero-shot-image-to-text

Caption images. Accepts an image input and generates a zero-shot natural-language description, optionally conditioned by...

🖼️ → 📝 • image-to-text • 6.7K runs

🤖 Model 🖼️ → 📝

google/gemini-2.5-flash

Generate text responses from text, image, video, and audio inputs with controllable reasoning depth. Supports up to 1 mi...

🖼️ → 📝 • text-generation • image-to-text • video-to-text • 6.8M runs

🤖 Model 🖼️

nateraw/vit-age-classifier

Classify age range from an input image. Accepts a single image and predicts a discrete age-range label with a confidence...

🖼️ • image-classification • age-estimation • 901 runs

🤖 Model 🖼️ → 📝

lucataco/internvl3_5-30b

Analyze images or video and generate text captions, answers, and summaries. Accepts single or multiple images or a video...

🖼️ → 📝 • image-to-text • video-to-text • 63 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 🖼️

lucataco/qwen3-vl-8b-instruct

Caption images and videos and answer visual questions. Accepts an optional image or video plus a text prompt and returns...

🖼️ • image-captioning • image-analysis • visual-understanding • 2.8K runs

🤖 Model 🖼️ → 📝

zsxkib/uform-gen

Caption images and answer visual questions from an input image, returning text. Accept an image and an optional instruct...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 2.3K runs

🤖 Model 🖼️ → 📝

kojott/content-moderation-vision

Moderate images for safety and policy compliance. Takes an image input (optionally a custom prompt) and outputs structur...

🖼️ → 📝 • image-nsfw-detection • image-to-text • content-moderation • 565 runs

🤖 Model 🖼️ → 📝

lucataco/joy-caption-pre-alpha

Caption images by generating detailed, paragraph-length natural-language descriptions from a single image input. Outputs...

🖼️ → 📝 • image-to-text • 430 runs

🤖 Model 🖼️ → 📝

ghostljj/deepseek-ocr

Extract text and convert documents to markdown format from images using optical character recognition. Supports multiple...

🖼️ → 📝 • ocr • pdf-to-markdown • document-to-json • 92 runs