vision-capability

LocalEyes gives text-only LLMs in Claude Code (e.g., DeepSeek, CodeLlama) local vision via Ollama, enabling image description without cloud uploads. Setup takes two commands.

展示了Claude Fable 5强大的视觉能力，仅用一个提示词配合three.js就能复刻出《我的世界》风格的游戏场景，画面感和3D效果令人惊叹。