Local-first visual media plugin for DeepSeek Harness: local video preprocessing, native vision, copyable image history, and video playback.
This project is a Streamlit web application that leverages OpenAI's GPT-4o to generate descriptions for uploaded images
AI Image Description Generator accurately extracts the key elements from images and interprets the creative purposes behind them, which can be applied in fields such as scientific research, artistic creation, and the mutual search between images and texts.
为 DeepSeek V4.0 等单模态大模型装上眼睛和耳朵 —— 本地视觉+音频 MCP 服务器，基于 Ollama + MiniCPM-V 4.6 + faster-whisper，图片描述·视频分析·语音转文字
Image identification with Kosmos2 model, drawing and cutting bbox with object detection
多账号 Google Gemini 提供商（DSH 插件）：订阅额度即用即扣，账号池自动调度；主模型没有视觉也能贴图看图（池内 Gemini 自动转述），另有生图工具与中英双语设置页
Experimenting with mastodon.social client alt-text usage dataset.
VisionMate: fast, fully offline image descriptions for the NVDA screen reader
Describes the screen, the active window, the focused item or a picture, with Windows' on-device AI. Built for JAWS, NVDA and Narrator.
Windows desktop app that describes images with ChatGPT Plus, SuperGrok or an API key and saves a clean PNG with the description in metadata (Eagle-friendly). Tauri 2, Rust, React.
DeepSeek Harness 识图插件：为不具备原生识图能力的模型提供识图能力（阿里云百炼 qwen3.5-omni-plus，失败自动切换智谱 glm-4.6v-flash）。由 claude-vision-skill 移植适配。 | Vision tool for DeepSeek Harness
Give vision to non-vision models in OpenCode using Google's free Gemini API. Transparently replaces image parts with detailed text descriptions — vision models stay untouched.
279K image alt-text pairs from 489 Bluesky accounts — curated for quality, validated at 90%+ alt-text rate
A lightweight console utility that uses an LLM to generate descriptions and keywords for images.
A new package that processes user-submitted text descriptions of images or videos containing watermarks and returns structured, watermark-free descriptions. It uses an LLM to reinterpret the content w
给 DeepSeek Harness 纯文本模型装上原生视觉（Windows）：粘贴即看图——预注入描述，模型首轮就看见，不用选模型、不用调工具；see_image 精查；自定义视觉后端（任意 OpenAI 兼容模型）+ 四后端容灾；换主模型视觉自动跟随。| Give text-only DeepSeek Harness models native-feeling vision on Windows: paste and the model just sees it — pre-injected descriptions, see_image tool, custom backends, 4-backend failover.
A see_image vision tool plugin for DeepSeek Harness — describe images through any OpenAI-compatible vision model (GitHub Copilot, OpenAI, Ollama, vLLM, LM Studio).
📊 Multi-Modal RAG 2.0 — An enterprise-grade RAG system that processes PDFs, tables, charts/images, and audio files together. Uses Unstructured.io, Camelot, Gemini Vision, Whisper, ChromaDB, FastAPI, and Streamlit. Increases information retrieval accuracy by 35% over text-only RAG.
An intelligent assistant powered by the ReAct framework, leveraging LangChain for tool-based reasoning and Gradio for a user-friendly interface. Supports tasks like weather queries, PDF summarization, image descriptions, and more.
CLI tool for generating image metadata in bulk — powered by Gemini for smarter, more context-aware descriptions.
To associate your repository with the image-description topic, visit your repo's landing page and select "manage topics."