Chewy is a beautiful TUI for generating images locally with Stable Diffusion and FLUX. Private. Fast. Free. No cloud, no API keys, no limits.
Generate images entirely on your machine. No accounts, no subscriptions, no data leaving your computer.
Everything runs on your hardware. Your prompts and images never leave your machine. No cloud, no API keys, no tracking.
Powered by stable-diffusion.cpp with Metal support. Generate images in seconds on Apple Silicon, not minutes.
Supports Stable Diffusion 1.x, 2.x, SDXL, SD3, and FLUX. Use .gguf, .safetensors, or .ckpt models. Auto-detects model type.
Browse and download models directly from HuggingFace without leaving the terminal. Search, preview, and install in seconds.
Use an existing image as a starting point. Browse for files or paste directly from your clipboard with Ctrl+V.
Apply LoRA weights, save parameter presets for quick switching, and browse your full generation history with metadata.
Watch your image take shape in real-time as it generates. Accurate ETA and progress tracking with step-by-step updates.
Automatically finds models from DiffusionBee and Draw Things. Validates compatibility and remembers your last selection.
Real outputs from chewy running locally. No cloud processing, no watermarks.
Every action is a keystroke away. No mouse needed.
Chewy installs everything you need, including the sd inference engine with GPU acceleration.
Installs chewy + stable-diffusion.cpp with Metal GPU support.
Requires Ruby 4.0+ and stable-diffusion.cpp on your PATH.
Customize paths and defaults with environment variables.
No sign-ups. No API keys. No cloud. Just your machine and your imagination.