VisionSqueezer
CLI

Usage

Optimize a single image or a whole directory tree from the command line.

The CLI is the fastest way to squeeze images. The core command takes an input path and a target model.

Single image

Terminal
vision-squeezer screenshot.png --model claude

Squeezer runs the full pipeline — semantic crop → tile-aware resize → encode — and writes an optimized file next to the input. It also records the savings in the local stats database.

Choosing a target

Terminal
# Claude: preserve resolution, strip padding (area-based billing)
vision-squeezer image.png --model claude

# GPT-4o: snap under the 512px tile threshold
vision-squeezer image.png --model gpt4o

# Gemini: snap down to 768px tile boundaries
vision-squeezer image.png --model gemini

# Agnostic: no --model, optimize generally across providers
vision-squeezer image.png

See Providers for the math behind each target.

Custom output

Terminal
vision-squeezer image.png --model gpt4o --output optimized.avif --format avif

Batch a directory

Terminal
vision-squeezer ./screenshots --recursive --output-dir ./optimized

--recursive walks subdirectories; --output-dir mirrors the source tree structure into the destination.

Core commands

CommandDescription
vision-squeezer <image> [options]Optimize a single image
vision-squeezer <dir> --recursive [--output-dir DIR]Batch optimize a tree
vision-squeezer statsView cumulative savings analytics
vision-squeezer setup-hookPrint shell integration (eval) script for Zsh/Bash

Shell integration

Add a squeeze shortcut to your shell:

Terminal
eval "$(npx -y vision-squeezer setup-hook)"