image-blaster: Generating 3D Worlds and Audio from a Single Image with Claude Skills

Repositoryneilsonnn/image-blasterTool

image-blaster is an open-source TypeScript skillset for Claude that turns a single 2D image into complete 3D environments, including meshes, Gaussian splats, and audio effects.

Key points

  1. Converts a reference image into static environment Gaussian splats (.spz), dynamic 3D meshes (.glb, .obj), and ambient or physics SFX (.mp3).
  2. Orchestrates specialized models via external APIs: Marble 1.1 (World Labs) for environments, Hunyuan 3D (via FAL) for meshes, ElevenLabs for audio, and nano-banana or gpt-image-2 for image cleanup.
  3. Operates interactively through the Claude CLI and can be embedded directly into game engines (Unity, Unreal, Godot), DCC tools (Blender, Maya), or web applications (Three.js).
  4. Supports detailed mesh generation settings such as PBR materials, target face counts, and low-poly decimation.

Why it matters

Manual creation of 3D assets, scene backgrounds, and matched audio is time-consuming and expensive. image-blaster bridges multiple specialized generative 3D and audio services into a unified conversational CLI workflow, yielding interactive prototypes in under five minutes.

Analysis

The project addresses the fragmentation in generative 3D workflows by using Claude as an orchestration agent across external model providers. Separating static scene backdrops (Gaussian splatting) from interactive dynamic models (polygonal meshes with PBR) aligns well with modern real-time rendering pipelines. With over 8,500 GitHub stars and active maintenance as of October 2026, the MIT-licensed tool demonstrates strong community traction. Its operational reliability depends primarily on external API keys (World Labs, FAL), but it already provides a built-in React viewer for local inspection.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 5 October 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:img2threejs/img2threejs

    img2threejs: Procedural Code-Only Image-to-3D for Three.js

    img2threejs turns reference images into procedural, animation-ready Three.js models generated purely as code, avoiding traditional mesh extraction or photogrammetry.

    15.1kstarsPython

    AI & LLMs· Tool

  • Video

    Video:Sean Kochel

    Creating Scrollable 3D Websites with scroll-world and Claude

    Sean Kochel demonstrates how to build interactive, scrollable 3D-style websites using the open-source scroll-world skill and Claude. The workflow relies on the Higgsfield API to generate images and transition videos stitched into a smooth journey.

    AI & LLMs· Tutorial

  • Repository:achimala/dream-loop

    dream-loop: Agent Skill for 3D Visuals via Iterative Critic Feedback

    dream-loop is an open-source agent skill by Anshu Sharma (@anshuc) designed to build high-quality 3D scenes, games, and web apps through a closed feedback loop. Image generation creates a reference target, after which an AI critic visually inspects live output and directs iterative refinements.

    1.5kstarsJavaScript

    AI & LLMs· Tool

  • Repository:mshumer/Claude-of-Duty

    Claude of Duty: Fully Procedural Browser FPS Built by AI Agents Using Three.js

    Claude of Duty is an open-source first-person shooter running in the browser on Three.js r180 and WebGL2. Spanning roughly 55,000 lines of code across 11 subsystems, it was constructed by an orchestrated fleet of AI agents. The game contains zero pre-baked art assets: every texture, 3D mesh, animation, and sound effect is generated procedurally from code at runtime.

    3.4kstarsJavaScript

    AI & LLMs· Demo

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.