Models tagged "image-to-text"

🤖 Model 📝 → 🔊

lucataco/interactiveomni-8b

Hold multi-turn, multimodal conversations grounded in images, audio, video, and text, returning answers as text and opti...

📝 → 🔊 • image-to-text • video-to-text • text-to-speech • 11 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 🖼️ → 📝

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 🖼️ → 📝

openai/gpt-5.1

Generate and reason over text and images from prompts or multi-turn chat, with configurable reasoning effort. Accepts te...

🖼️ → 📝 • text-generation • image-to-text • image-captioning • 56 runs

🤖 Model 🖼️ → 📝

ell-hol/clip-interrogator

Generate descriptive prompts for text-to-image models from a single image. Outputs a CLIP Interrogator-style prompt stri...

🖼️ → 📝 • image-to-text • prompt-generation • 652 runs

🤖 Model 🖼️ → 📝

asppj/openclip

Caption images. Takes an image as input and outputs a short natural-language description (image-to-text) using OpenCLIP...

🖼️ → 📝 • image-to-text • 90 runs

🤖 Model 📝 → 📝

google/gemini-3-pro

Generate and reason over text from prompts, with optional image, audio, and video inputs. Produce answers, explanations,...

📝 → 📝 • text-generation • image-captioning • image-analysis • 5.5K runs

🤖 Model 🖼️ → 📝

zsxkib/molmo-7b

Caption images and answer visual questions from an input image and text prompt. Accept an image plus a question or instr...

🖼️ → 📝 • image-to-text • image-captioning • image-analysis • 594.3K runs

🤖 Model 🖼️ → 📝

openai/gpt-5.2

Generate and reason over text and images for coding, professional knowledge work, and agentic workflows. Accepts a singl...

🖼️ → 📝 • text-generation • image-to-text • visual-understanding • 1 runs

🤖 Model 🖼️ → 📝

cjwbw/unival

Caption images, videos, and audio; answer media-grounded questions; and localize referred objects via visual grounding....

🖼️ → 📝 • image-to-text • video-to-text • audio-to-text • 996 runs

🤖 Model 🖼️ → 📝

moonshotai/kimi-k2.5

Analyze images and text to generate answers, working code, and polished documents. Takes a text prompt with an optional...

🖼️ → 📝 • text-generation • image-to-text • image-analysis • 7 runs

🤖 Model 🖼️ → 📝

seeghost1019/google-medgemma-4b

Answer medical questions from text and optional medical images, returning explanatory text. Accept a prompt and optional...

🖼️ → 📝 • image-to-text • text-generation • medical • 4 runs

🤖 Model 🖼️ → 📝

google/gemini-3-flash

Generate and analyze text from prompts, images, audio, and video with fast, low-latency responses. Accept text plus up t...

🖼️ → 📝 • text-generation • image-to-text • video-to-text • 4 runs

🤖 Model 🖼️ → 📝

google/gemini-3.1-pro

Generate text from prompts with optional image, video, and audio context. Accepts multimodal inputs (up to 10 images, 10...

🖼️ → 📝 • text-generation • image-to-text • video-to-text • 1 runs

🤖 Model 🖼️ → 📝

openai/gpt-5.4

Generate text and analyze images for coding, reasoning, and professional workflows. Accept text prompts or chat messages...

🖼️ → 📝 • text-generation • image-to-text • image-analysis • 1 runs

🤖 Model 🖼️ → 📝

anthropic/claude-opus-4.6

Generate text and analyze images for complex, multi-step work. Accepts a text prompt (and an optional image) and returns...

🖼️ → 📝 • text-generation • image-to-text • image-analysis • 10 runs

🤖 Model 🖼️ → 📝

lucataco/idefics-9b

Answer questions about an input image from a text prompt, returning text. Generate image captions and short visual descr...

🖼️ → 📝 • image-to-text • visual-question-answering • image-captioning • 2.1K runs