// image · GoogleChromeLabs/squoosh

squoosh

squoosh est un projet de image open source, créé par GoogleChromeLabs (GoogleChromeLabs/squoosh sur GitHub). Il compte 25 984 étoiles sur GitHub et 2 178 forks, il est publié sous la licence Apache-2.0 et a été mis à jour pour la dernière fois sur GitHub le 23 septembre 2026.

Make images smaller using best-in-class codecs, right in the browser.

★ 26,0 k étoiles⑂ 2,2 k forksApache-2.0mis à jour sept. 2026

Voir sur GitHub ↗Official site ↗

▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.

// détails du projet

Détails du projet

Dépôt: GoogleChromeLabs/squoosh
Étoiles GitHub: 25 984
Forks: 2 178
Licence: Apache-2.0
Dernière mise à jour sur GitHub: 23 septembre 2026
Catégorie: Image
Type de fiche: Guide d'installation complet
Site officiel: Official site

// fonctionnement

Comment ça marche

Choose the right tool
Generation studio, upscaler, background remover, or photo library — match the tool to the task.
Install it your way
Desktop apps, Docker images, and portable builds cover most platforms; pick the simplest for your OS.
Add models if needed
Generation tools need checkpoint files; utilities like upscalers usually bundle everything.
Create or organize
Generate, enhance, or import — then export, share, or keep building your library.

// fonctionnalités

Pourquoi on l'adore

Purpose-built utilities

Single-job tools (upscale, de-background, restore) that do one thing excellently.

Model freedom

Bring any compatible open checkpoint; you are never locked to one vendor's style.

Runs locally

Your images stay on your machine — important for client work and privacy.

No subscriptions

The defining trait of this whole category: professional results without monthly fees.

Non-destructive

Edits stay reversible; originals are never touched.

Batch processing

Run whole folders through upscalers and converters unattended.

// lancez-le

Lancez-le vous-même

Step 1 — Clone the repo
Download the source and move into the project folder.
```
git clone https://github.com/GoogleChromeLabs/squoosh.git
cd squoosh
```
Step 2 — Check the README
Every project documents its own setup; start with install requirements.
```
cat README.md | head -60
```
Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
```
# see README for the exact launch command
```

// cas d'usage

Ce que vous pouvez créer

Generate concept art and illustrations.
Upscale and restore old photos.
Remove backgrounds in bulk for product shots.
Self-host a Google-Photos-style library.

// faq

Questions fréquentes

Who maintains squoosh?

It is an open-source project at GoogleChromeLabs/squoosh with 2,178 forks. Check the repo's contributors and recent commits to see how active maintenance is.

Is squoosh free for commercial use?

Apache 2.0 licensed — commercial use allowed with attribution.

Which should I start with?

For generation: a polished studio interface. For enhancement: a dedicated upscaler. For libraries: a photo manager.

Can they match Midjourney quality?

With the right open checkpoints, absolutely — the interface matters less than the model you load.

Are they free for commercial work?

Les autres projets de la catégorie Image avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si squoosh ne vous convient pas.

Stable Diffusion Webui★ 165,2 k
Stable Diffusion web UI
ComfyUI★ 136,0 k
The node-graph powerhouse for precise, professional AI image and video generation.
Immich★ 115,5 k
High performance self-hosted photo and video management solution
PhotoCraft★ 73,2 k
PhotoCraft — a clean-room Photoshop reimplementation in pure Rust: layers, masks, adjustment layers, type, vectors, brushes and real PSD files, offline, MIT / Apache-2.0
Fooocus★ 53,3 k
Focus on prompting and generating

// plus en image

Plus en Image

Projets de la catégorie Image proches dans le catalogue, les plus proches en étoiles de squoosh — continuez à explorer de part et d'autre.

flux★ 26,0 k
Black Forest Labs' official inference repo for the FLUX.1 image generation models
pytorch-CycleGAN-and-pix2pix★ 25,3 k
The classic PyTorch implementation of CycleGAN and pix2pix for image-to-image translation
Generative Models★ 27,3 k
Generative Models — Stability AI reference code for Stable Diffusion, SV3D and SV4D video-to-4D models, MIT
rembg★ 25,0 k
Rembg is a tool to remove images background
InvokeAI★ 28,3 k
A polished creative studio for professionals who want power without the node spaghetti.
pydantic-ai★ 20,4 k
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.

Obtenir squoosh

Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.

Voir sur GitHub ↗← Plus d'outils image