Media
3 items
Description
Turn any image into a ready-to-use prompt for Stable Diffusion, FLUX and Midjourney. ImgPrompt AI turns any image on the web into a detailed text prompt for AI image generators. HOW IT WORKS: • Hover over any image on any webpage — a "Prompt" button appears • Click it — the extension analyzes the image using a vision AI model • Get a ready-to-use prompt optimized for Midjourney, Stable Diffusion, DALL-E, or Flux • Works with video too — captures and analyzes the current frame KEY FEATURES: • One-click image analysis with overlay button • Video frame capture (YouTube, Vimeo, any HTML5 video) • Right-click context menu integration • Side panel with full prompt history • Image compression for faster processing • Configurable request timeouts with cancel option • Custom system prompts — tailor the output to your needs • Multilingual output: English, Russian, Chinese SUPPORTED PROVIDERS: • OpenRouter (100+ models, free options available) • Groq (fast inference) • Ollama (local, free, fully offline) • LM Studio (local, GUI-based) • Jan (local, desktop app) PRIVACY: • No backend server — requests go directly from your browser • API keys stored locally in encrypted browser storage • No data collection, no telemetry • Fully open source (MIT license) GETTING STARTED: Install the extension Get a free API key at openrouter.ai Paste the key and select a model Hover over any image and click "Prompt" Works on all Chromium-based browsers and Firefox (separate build).