awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
neilsonnn avatar

neilsonnn/image-blaster

0
View on GitHub↗

Image Blaster

Image Blaster turns a single input image into an explorable 3D world. It is packaged as a set of Claude skills that guide an AI assistant through a step-by-step workflow, pausing for the user's confirmation between stages. The output is a Gaussian splat of the static background, separate textured meshes for the movable objects, and matching audio, generated in minutes.

The project splits the source image into a static environment and individually extracted dynamic objects, so each is reconstructed in the way that suits it. The workflow starts by cleaning up the source image: it removes clutter, produces a clean background plate, and creates object reference images, with a choice of edit provider. Object meshes can be generated with adjustable face count, polygon type (textured, low-poly, or geometry-only), and physically based materials. The scene also gets a looping ambient soundtrack and object-specific physics sound effects. The generation work is delegated to external generative services, each authenticated with API keys read from environment variables.

Generated worlds can be viewed in a React browser app, where splats, meshes, and sounds are shown together and can be moved through. The viewer can be customized by removing its folder from the ignore list. Output is exported in formats intended for game engines, 3D content-creation software, and web or desktop apps.

The repository is a TypeScript monorepo with root-level scripts for development mode, production builds, build previews, and running tests and type checks.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Image-Conditioned 3D Generation - Turns a single picture into an explorable 3D world, with a Gaussian splat background and separate meshes for movable objects.
  • Image-to-3D World Generators - Convert a single input image into an explorable 3D environment using generative models, going from picture to fully meshed world in minutes.
  • Single-Image 3D Reconstructions - Converts a single input image into an explorable 3D environment captured as a Gaussian splat, ready in minutes.
  • Gaussian Splatting - Captures the static background of an image as a Gaussian splat that can be viewed and moved through in 3D.
  • World Simulation Generators - Turns a single source image into an explorable 3D environment using a world-generation model.
  • Gaussian Splatting Reconstruction - Turns the unmoving background of an image into a Gaussian splat file that can be explored in three dimensions.
  • Image-to-Mesh Generation - Turns object reference images into textured 3D meshes with configurable face count, polygon type, and physically based materials.
  • Static and Dynamic Scene Separation - Splits the source image into a static background and separately extracted movable objects, each reconstructed with the method that suits it.
  • 3D Asset Generators - Creates textured 3D meshes in standard formats for each dynamic object, with adjustable face count and polygon style.
  • Image Editing - Edits input images to remove clutter and produce clean background plates and object reference images, with a choice of edit provider.
  • Real-Time 3D Object Generators - Produces standard 3D model files for each movable object detected in the source image, ready for use in other tools.
  • Source Image Preparation for 3D Generation - Edits source images to remove clutter and produce clean background plates and object reference pictures before 3D generation begins.
  • Staged Approval Workflows - Breaks world generation into ordered stages where the assistant waits for user approval before starting the next one.
  • Claude Skills - Packages the whole workflow as Claude skills that guide an AI assistant step by step, pausing for user confirmation between stages.
  • 3D Mesh Generators - Produces 3D models in common mesh formats for each movable object, with adjustable face count, materials, and polygon type.
  • 3D Scene Web Viewers - Ships a React browser app that shows splats, meshes, and sounds together so users can move through the generated world.
  • Image-Based Object Model Generators - Converts object reference images into 3D models with adjustable face count, physically based materials, and textured, low-poly, or geometry-only output.
  • Multi-Modal Generative Service Integrations - Delegates image editing, world reconstruction, mesh creation, and sound synthesis to external generative APIs, each authenticated through environment-variable keys.
  • Sound Effects Generation - Generates ambient audio and object-specific sound effects with a sound-effects model so generated worlds have matching audio.
  • Assistant Skill Plugins - Packages the world-generation workflow as assistant skills that an AI model follows, coordinating tools and external services step by step.
12,383 stars·1,257 forks·TypeScript·MIT·4 views

Star history

Star history chart for neilsonnn/image-blasterStar history chart for neilsonnn/image-blaster

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Frequently asked questions

What does neilsonnn/image-blaster do?

Image Blaster turns a single input image into an explorable 3D world. It is packaged as a set of Claude skills that guide an AI assistant through a step-by-step workflow, pausing for the user's confirmation between stages. The output is a Gaussian splat of the static background, separate textured meshes for the movable objects, and matching audio, generated in minutes.

What are the main features of neilsonnn/image-blaster?

The main features of neilsonnn/image-blaster are: Image-Conditioned 3D Generation, Image-to-3D World Generators, Single-Image 3D Reconstructions, Gaussian Splatting, World Simulation Generators, Gaussian Splatting Reconstruction, Image-to-Mesh Generation, Static and Dynamic Scene Separation.

Which projects share features with neilsonnn/image-blaster?

Projects with overlapping indexed features include: tencent-hunyuan/hunyuan3d-2.1 — Hunyuan3D-2.1 is a generative 3D framework and image-to-3D pipeline that transforms single 2D images into textured 3D… mrforexample/comfyui-3d-pack — ComfyUI-3D-Pack is a suite of custom nodes for ComfyUI that enables 3D asset generation and rendering within a… scenario-labs/skills — This repository is a collection of installable agent skills that connect AI coding assistants to the Scenario… threestudio-project/threestudio — Threestudio is a 3D generative AI framework designed to create three-dimensional assets from text prompts and images.… tencentarc/instantmesh — InstantMesh is a neural 3D reconstruction tool and single-image 3D mesh generator. It utilizes a sparse-view large… vast-ai-research/triposr — TripoSR is a single-image 3D reconstruction system that generates a high-quality textured mesh from one photograph in…

Projects sharing features with Image Blaster

These projects share indexed features with Image Blaster. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • tencent-hunyuan/hunyuan3d-2.1Tencent-Hunyuan avatar

    Tencent-Hunyuan/Hunyuan3D-2.1

    2,910View on GitHub↗

    Hunyuan3D-2.1 is a generative 3D framework and image-to-3D pipeline that transforms single 2D images into textured 3D geometries. It functions as an asset generator that produces high-quality 3D meshes and textures using a flow-matching system. The project includes a specialized synthesizer for creating photorealistic textures with physically based rendering properties. These tools allow for the simulation of metallic reflections and light interactions on generated models. The system covers 3D asset pipeline automation through a sequence of shape generation and mesh refinement. It also provi

    Python3d3d-aigc3d-generation
    View on GitHub↗2,910
  • mrforexample/comfyui-3d-packMrForExample avatar

    MrForExample/ComfyUI-3D-Pack

    3,902View on GitHub↗

    ComfyUI-3D-Pack is a suite of custom nodes for ComfyUI that enables 3D asset generation and rendering within a node-based workflow. It provides a set of tools for reconstructing textured three-dimensional meshes and volumetric scenes from single images, multi-view images, or text prompts. The system includes a Gaussian splatting generator for creating high-fidelity volumetric 3D scene representations and a multi-view image generator to produce consistent image sets for reconstruction. It also features a single image 3D mesh tool to build geometry from a single 2D source. The toolset covers 3

    Pythoncomfycomfyuimachine-learning
    View on GitHub↗3,902
  • scenario-labs/skillsscenario-labs avatar

    scenario-labs/skills

    3,501View on GitHub↗

    This repository is a collection of installable agent skills that connect AI coding assistants to the Scenario generation server and to expert 3D and game-engine tools. The skills cover generating and editing images, video, audio, and 3D assets, and driving Blender, Maya, ZBrush, Unity, Unreal Engine, Godot, and Roblox through scripted workflows. Each skill is a self-contained instruction file with metadata, installed into many coding assistants through a shared open format. What defines the skills is how they run generation and tool work. Models are discovered through a standard tool protocol

    Python3d-modelsagent-skillsai-agents
    View on GitHub↗3,501
  • threestudio-project/threestudiothreestudio-project avatar

    threestudio-project/threestudio

    7,027View on GitHub↗

    Threestudio is a 3D generative AI framework designed to create three-dimensional assets from text prompts and images. It provides specialized pipelines for text-to-3D generation and image-to-3D reconstruction, utilizing a neural radiance field trainer to produce geometry and textures. The framework is distinguished by its support for hybrid geometry backends, including signed distance functions, tetrahedra grids, and volume grids. It employs score distillation sampling to guide the generation process and features a modular plugin system for loading custom modules and nodes. The system covers

    Jupyter Notebook
    View on GitHub↗7,027
Compare all 30 related projects→