# img2threejs/img2threejs

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

Repository: https://github.com/img2threejs/img2threejs
Canonical: https://ross.abutalabs.com/products/img2threejs
Homepage: https://img2threejs.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: 3d, ai-agents, claude-code, computer-graphics, generative, image-to-3d, procedural-generation, threejs, typescript, webgl
Last push: 2026-08-26T11:20:20+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 3
- inputs: {"age_days": 49, "days_push": 7, "days_rel": 10, "gap_med": 6.5, "n_releases_24m": 5}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14018, forks 1126 (observed 2026-08-28T04:11:05.219301+00:00)

## What it is
A tool that reconstructs objects from reference images as code-only, procedural Three.js models rather than meshes or photogrammetry. It produces quality-gated, animation-ready, token-efficient 3D model code suitable for AI agent workflows like Claude Code.

## Use cases
- convert a reference image into a three.js 3d model
- generate procedural 3d objects from photos
- rebuild objects in code for webgl scenes
- create animation-ready 3d models without mesh files
- use with claude code to generate 3d assets
- token-efficient image to 3d reconstruction

## When to choose
- you want editable, code-based 3d models instead of downloaded meshes
- you work in Three.js/WebGL and need procedural, animation-ready assets
- you want an AI-agent-friendly, token-efficient image-to-3D pipeline

## When to avoid
- you need photorealistic reconstructions or accurate photogrammetry
- you need exported mesh formats like OBJ/GLTF from real-world scans
- you don't use Three.js or JavaScript for your 3D rendering

## Facets
- artifact type: library
- maturity: active
- function: image-processing, computer-vision, graphics, machine-learning, developer-tools
- domain: computer-vision, graphics, web-development, artificial-intelligence
- platform: python, cross-platform
- tags: threejs, image-to-3d, procedural-generation, claude-code, webgl, code-generation, 3d-models, token-efficient, game-development, web-server

## Member repositories
- img2threejs/img2threejs (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:05.219301+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:12:52.368216+00:00, confidence not recorded.
  - readme: https://github.com/img2threejs/img2threejs (fetched 2026-08-28T04:11:05.219301+00:00, sha bc6d94b1c5cc)
  - homepage: https://img2threejs.io (fetched 2026-08-29T08:06:49.823583+00:00, sha ca671edfcd26)
- Data as of 2026-08-30T08:39:29.467469+00:00.