neilsonnn/image-blasterPublic

An image-to-world skillset for Claude.

AI summary: A high-performance command-line tool for bulk processing, converting, and resizing images efficiently.

Stars: 4.8K; +3 today
Forks: 492
Watchers: 50
Open issues: 3
Open PRs: 6
Contributors: ~1
Commits: 72
Branches: 1

TypeScriptMITCreated Apr 21, 2026Last push 2mo ago+18 stars this week+24 this month

Star history

since May 10, 2026

4.8K stars as of Aug 7, 2026, tracked back to May 10, 2026. Historical curve reconstructed from public GitHub event archives, calibrated to the current total.

Contribution activity

commits per day, last 52 weeks

72 commits in the last yearLessMore

Signals and awards

derived from tracked data

Breakout launch
4,790 stars in 109 days
Permissive license
MIT

What image-blaster does

Image-blaster is built for speed and simplicity when dealing with large directories of images. It provides a streamlined CLI interface to concurrently resize, format, and compress images in bulk. By leveraging modern underlying graphics libraries, it maximizes multi-core CPU usage to process thousands of files drastically faster than traditional script-based tools. It handles complex operations like format conversion, intelligent cropping, and metadata stripping, making it an ideal utility for preparing massive datasets or optimizing web assets.

Image-blaster is built for data scientists, web developers, and system administrators who require a fast, scriptable way to manipulate large volumes of images from the command line.

Concurrent execution: Utilizes multi-threading to process large batches of images simultaneously, drastically reducing overall execution time.
Format conversion: Seamlessly converts between popular formats (JPEG, PNG, WebP, AVIF) with customizable compression parameters.
Smart resizing: Offers various resizing algorithms including precise dimensions, percentage scaling, and intelligent cropping.
Metadata management: Can automatically strip EXIF data and other embedded metadata to reduce file sizes and protect privacy.
CLI-first design: Highly scriptable interface designed to be easily integrated into CI/CD pipelines and automated workflows.

Where teams use it

Machine learning dataset preparation

Data scientists can rapidly standardize the resolution and format of massive image datasets prior to training computer vision models.

Web asset optimization

Web developers can automate the generation of responsive image variants and next-gen formats (like WebP) for entire content libraries.

Automated photography workflows

Photographers can use it as a rapid first-pass tool to generate low-resolution proofs from massive directories of high-res originals.

Getting started: npm install -g image-blaster

README

main branch

`image-blaster`

Creates 3D environments, SFX, and meshes from a single image using Claude skills, World Labs, and FAL.

Can take you from an image to a fully meshed 3D environment in < 5 minutes, great for jumpstarting 3D work. Go full blast.

Quickstart

Open a Terminal, enter git clone https://github.com/neilsonnn/image-blaster
Enter the directory with cd image-blaster
Run claude (install with curl -fsSL https://claude.ai/install.sh | bash)
Say hello to Claude, and give them your API key for World Labs and FAL.
Put an image into input/ directory and ask Claude to blast it and confirm each step with me.

Description

By default image-blaster will use your input image to create:

3D models (.glb, .obj) of all dynamic objects
Gaussian splat (.spz) of the static environment,
Ambient looping sound and object specific physics SFX (.mp3)

Extensions

You can embed image-blaster under the assets of any game engine, DCC software, or web app.

Unity, Unreal, or Godot game engine
Blender, 3DS Max, or Maya or other DCC software
Three.js web app or Electron app

Advanced

IMAGE-BLASTER uses a few generation models:

marble-1.1 - World Labs Marble model creates the explorable environment.
nano-banana - default image edit preference for source cleanup, clean plates, and object reference images.
gpt-image-2 - alternate image edit provider when the edit skill is asked to prefer it.
hunyuan-3d - Hunyuan 3D model creates 3D object models through FAL.
elevenlabs-sfx - ElevenLabs sound effects model creates ambient and object-specific sounds.

3D model creation supports these Hunyuan parameters:

--face-count <40000-1500000>: target face count. IMAGE-BLASTER defaults to 50000; Hunyuan's API default is 500000.
--enable-pbr true|false: enable PBR material generation. Defaults to true.
--generate-type Normal|LowPoly|Geometry: Normal creates a textured model, LowPoly applies polygon reduction, and Geometry creates a white geometry-only model. Defaults to Normal.
--polygon-type triangle|quadrilateral: polygon type for LowPoly. Defaults to triangle.

Examples

Video game level concepts? IMAGE-BLAST it.
Your childhood bedroom? IMAGE-BLAST it.
Need an environment for a robot? IMAGE-BLAST it.
A film location scout? IMAGE-BLAST it.
An architectural rendering? IMAGE-BLAST it.

Development

remove /app from the .claudeignore file to give Claude the ability to change the React viewer.

View on GitHub

Recent activity

commits and pull requests

Fix CLI entrypoint detection on Windows (all scripts exit silently)Open
#12 by GOODMAN-PRO · updated 1mo ago
feat: add CADBuildr Prototype MCP bridgeClosed
#10 by clement91190 · updated 1mo ago
fix(scripts): use pathToFileURL for ESM entrypoint check on WindowsOpen
#7 by yugao-gaos · updated 2mo ago
Test env example instead of local secretsClosed
#6 by grp06 · updated 2mo ago
Trigger object SFX on physical impact with force-scaled volumeOpen
#5 by dalision · updated 2mo ago
Add image-blast-character skill: auto-rigged humanoid characters from one imageOpen
#4 by gnoblin · updated 2mo ago
feat: add tripo3d as third 3d providerOpen
#2 by mvanhorn · updated 2mo ago
feat: add image-blast-export skill (usdz, stl, fbx)Open
#3 by mvanhorn · updated 2mo ago
license
neilsonnn committed 4acb43b · 2mo ago
Update README.md
neilsonnn committed d13c7c1 · 2mo ago
tweaks, show loading states, spawn pos, no hot reload in editor, better hover state
neilsonnn committed 68955e5 · 2mo ago
cleanup, loading items and world, object gen prompt, show url
neilsonnn committed aa8c667 · 2mo ago

Recent open issues

view all

Showing API key error
#11 · 1mo ago · by aniket-professional2025
Question about the possible usage of other agents
#9 · 2mo ago · by pigwu
Question: Single gen cost
#8 · 2mo ago · by javimosch

Commits per week

last 52 weeks

72 commits in the last 52 weeks.

When work happens

weekday and hour

Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Who is committing