Models tagged "image-to-text"

🤖 Model 🖼️ → 📝

aodianyun/minicpm-v-26

Caption images and videos. Accepts an image or video plus an optional prompt and returns text descriptions or summaries...

🖼️ → 📝 • image-to-text • video-to-text • 15 runs

🤖 Model 🖼️ → 📝

hexiaochun/minicpm_v26

Generate captions, answers, and summaries from an input image or video. Accept an image or video plus an optional prompt...

🖼️ → 📝 • image-to-text • video-to-text • 518 runs

🤖 Model 🖼️ → 📝

aodianyun/minicpm-v-26-int4

Generate text descriptions for images and videos. Accepts a single image or video plus an optional instruction prompt, a...

🖼️ → 📝 • image-to-text • video-to-text • 12 runs

🤖 Model 🖼️ → 📝

nelsonjchen/minigpt-4_vicuna-13b

Answer questions about images and generate captions from an input image and text prompt. Accepts an image plus a message...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 52.0K runs

🤖 Model 📝 → 📝

openai/gpt-5

Generate and reason over text for chat, coding, and complex problem solving. Accept prompts or multi-turn messages and o...

📝 → 📝 • text-generation • image-captioning • image-analysis • 361.3K runs

🤖 Model 🖼️ → 📝

openai/gpt-5-pro

Generate text from prompts or chat messages, with optional image inputs for multimodal reasoning and captioning. Accept...

🖼️ → 📝 • text-generation • image-to-text • image-captioning • 343 runs

🤖 Model 🖼️ → 📝

anthropic/claude-4-sonnet

Generate text from prompts with optional image analysis and captioning. Takes a text prompt (and optionally an image) an...

🖼️ → 📝 • text-generation • image-to-text • visual-understanding • 946.9K runs

🤖 Model 🖼️

anthropic/claude-3.7-sonnet

Generate and reason over text from a prompt and optional image. Support code generation, code understanding, front-end w...

🖼️ • image-captioning • image-analysis • visual-understanding • 2.9M runs

🤖 Model 📝 → 📝

openai/gpt-5-structured

Generate structured JSON or free-form text from prompts. Accept text and image inputs to analyze visuals and return capt...

📝 → 📝 • text-generation • structured-output • image-captioning • 126.9K runs

🤖 Model 🖼️ → 📝

nelsonjchen/minigpt-4_vicuna-7b

Caption images and answer visual questions from an image and a text prompt. Accepts an image and a message (question or...

🖼️ → 📝 • image-to-text • image-captioning • visual-question-answering • 9.9K runs

🤖 Model 🖼️ → 📝

yimi81/yi-vl-6b

Answer questions about images and generate captions from an image and a natural-language query. Takes an image plus a te...

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

🤖 Model 📝 → 📝

openai/o1

Solve complex reasoning tasks and generate text from prompts or chat messages. Accept text or messages and optional imag...

📝 → 📝 • text-generation • image-captioning • image-analysis • 15.9K runs

🤖 Model 🖼️

google-deepmind/gemma-3-4b-it

Generate text and understand images from text and optional image inputs. Handle chat, question answering, document summa...

🖼️ • image-captioning • image-analysis • visual-understanding • 5.1K runs

🤖 Model 🖼️

google-deepmind/gemma-3-12b-it

Generate text and analyze images from text and image inputs. Handle question answering, long‑context reasoning (128K tok...

🖼️ • image-captioning • image-analysis • visual-understanding • 13.9K runs

🤖 Model 🖼️ → 📝

google-deepmind/gemma-3-27b-it

Generate text from prompts and optionally analyze images to produce text outputs. Accepts text and optional image inputs...

🖼️ → 📝 • text-generation • image-to-text • 20.0K runs

🤖 Model 🖼️ → 📝

paragekbote/gemma3-torchao-quant-sparse

Generate text and answer questions about images from a text prompt, returning text outputs for chat, captioning, and vis...

🖼️ → 📝 • text-generation • image-to-text • image-analysis • 32 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 🖼️ → 📝

lucataco/moondream-0.5b

Caption images and answer questions about images. Accepts an image and a natural-language prompt (e.g., “Describe this i...

🖼️ → 📝 • image-to-text • visual-question-answering • 62 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 🖼️ → 📝

webnizam/image-caption

Caption images from a single image input, returning a natural-language description of the scene. Accepts one image and o...

🖼️ → 📝 • image-to-text • image-captioning • 2.8K runs