# vinhhien112/img2obj

Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.

Repository: https://github.com/vinhhien112/img2obj
Canonical: https://ross.abutalabs.com/products/img2obj
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-06T07:54:18+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 35, longevity 3
- inputs: {"age_days": 55, "days_push": 27, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1615, forks 165 (observed 2026-08-28T04:05:11.564104+00:00)

## What it is
img2obj is a Codex plugin that turns an attached object image into a code-only, animation-ready procedural Three.js model. It guides the AI through a quality-gated workflow of validating the reference, planning an ObjectSculptSpec, building geometry in phases, and reviewing browser renders against the source image.

## Use cases
- generate a procedural three.js model from a reference image
- turn a screenshot of an object into code-based 3d geometry
- create animation-ready 3d props for web scenes without downloading meshes
- rebuild stylized plants or mechanical objects as procedural three.js assets
- plan and refine 3d object structure with an ai coding agent
- make interactive browser 3d demos from photos

## When to choose
- you want code-only procedural Three.js assets rather than downloaded meshes or art packs
- you work with stylized props, mechanical objects, plants, or scene assets
- you use Codex or a similar AI agent and want a structured, quality-gated reconstruction workflow
- you need animation-ready hierarchies with pivots and sockets

## When to avoid
- you need photogrammetry or exact mesh extraction from images
- you require guaranteed production-ready geometry from a single image
- you want a standalone tool rather than an AI-agent plugin
- you need high-poly scans or CAD-accurate models

## Facets
- artifact type: plugin
- maturity: active
- function: machine-learning, graphics, agent-framework, prompt-engineering, developer-tools
- domain: graphics, artificial-intelligence, web-development, developer-tools
- platform: browser, cli
- tags: threejs, procedural-geometry, codex-plugin, image-to-3d, 3d-modeling, animation-ready, objectsculptspec, ai-workflow, game-development, web-server

## Member repositories
- vinhhien112/img2obj (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:11.564104+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 2026-08-30T03:50:18.063877+00:00, confidence not recorded.
  - readme: https://github.com/vinhhien112/img2obj (fetched 2026-08-28T04:05:11.564104+00:00, sha 16ca0477b616)
- Data as of 2026-08-30T08:39:29.467469+00:00.