v0.2.4 — Now with FLUX support

AI image generation
in your terminal.

Chewy is a beautiful TUI for generating images locally with Stable Diffusion and FLUX. Private. Fast. Free. No cloud, no API keys, no limits.

$ brew install Holy-Coders/chewy/chewy
chewy
chewy | dreamshaper-v8 SD 1.x [^n] models
Models
dreamshaper-v8
sd15-q8_0
flux1-schnell-F16
flux1-dev-Q2_K
realisticVision-v5
Prompt
a sunset over the ocean, vibrant colors, photorealistic
steps 20   cfg 7.0   512x512   seed -1   euler_a
Generated sunset image
output: outputs/20260313_012424.png | 25.4s | seed 42 ^e open | ^f fullscreen

Everything you need.
Nothing you don't.

Generate images entirely on your machine. No accounts, no subscriptions, no data leaving your computer.

🔒

100% Local & Private

Everything runs on your hardware. Your prompts and images never leave your machine. No cloud, no API keys, no tracking.

Metal GPU Acceleration

Powered by stable-diffusion.cpp with Metal support. Generate images in seconds on Apple Silicon, not minutes.

🎨

SD & FLUX Models

Supports Stable Diffusion 1.x, 2.x, SDXL, SD3, and FLUX. Use .gguf, .safetensors, or .ckpt models. Auto-detects model type.

📥

Built-in Model Browser

Browse and download models directly from HuggingFace without leaving the terminal. Search, preview, and install in seconds.

🖼

img2img & Clipboard

Use an existing image as a starting point. Browse for files or paste directly from your clipboard with Ctrl+V.

LoRA, Presets & History

Apply LoRA weights, save parameter presets for quick switching, and browse your full generation history with metadata.

🖥

Live Preview

Watch your image take shape in real-time as it generates. Accurate ETA and progress tracking with step-by-step updates.

📁

Auto Model Discovery

Automatically finds models from DiffusionBee and Draw Things. Validates compatibility and remembers your last selection.

Designed for speed.

Every action is a keystroke away. No mouse needed.

tab Cycle focus
enter Generate image
^n Model picker
^d Download models
^b Browse init image
^v Paste from clipboard
^a Gallery
^g Generation history
^l LoRA selection
^p Presets
^e Open in viewer
^f Fullscreen preview
^x Cancel generation
^r Randomize seed
^u Clear init image
^q Quit

Up and running in one command.

Chewy installs everything you need, including the sd inference engine with GPU acceleration.

Homebrew (recommended)

Installs chewy + stable-diffusion.cpp with Metal GPU support.

$ brew install Holy-Coders/chewy/chewy
$ chewy

From source

Requires Ruby 4.0+ and stable-diffusion.cpp on your PATH.

$ git clone https://github.com/Holy-Coders/chewy.git
$ cd chewy && bundle install
$ ruby chewy.rb

Configuration

Customize paths and defaults with environment variables.

# Set custom model directory
$ export CHEWY_MODELS_DIR=~/my-models

# Set custom output directory
$ export CHEWY_OUTPUT_DIR=~/Pictures/ai

# Point to a custom sd binary
$ export SD_BIN=/path/to/sd

Start generating locally.

No sign-ups. No API keys. No cloud. Just your machine and your imagination.