--- title: "img2threejs by Nick (Hoài Nhớ) — AI video generator workflow for 3D scenes" description: "Rebuilds the object in one reference image as a code-only, animation-ready Three.js model, gated pass by pass. Install in Claude Code, Codex and Grok with one command." url: https://varg.ai/how-to/skills/img2threejs updated: 2026-11-01 --- # img2threejs by Nick (Hoài Nhớ) — workflow skill for 3D scenes > **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q="` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page. From a terminal: `curl -fsSL https://varg.ai/install | sh` installs the vargai CLI (https://varg.ai/how-to/cli.md): `vargai search` and `vargai install ` with no key, every varg model after `vargai login`. Rebuilds the object in one reference image as a code-only, animation-ready Three.js model, gated pass by pass. - **Type:** [Workflow](https://varg.ai/how-to/workflows.md) · [3D scenes](https://varg.ai/how-to/browse/skills/3d-scenes.md) - **Slug:** `img2threejs` - **Status:** live - **Publisher:** Nick (Hoài Nhớ) (community) - **License:** Apache-2.0 - **Source:** https://github.com/img2threejs/img2threejs - **Works in:** Claude Code, Codex - **Requires:** Node.js 18+, Git, Python 3.10+ - **Cost:** Free, Apache-2.0: runs on your own agent plan - **Adoption:** 19,931 GitHub stars (GitHub, 2026-10-31) ## What it does Give it one reference image of an object or character and it writes a TypeScript `THREE.Group` factory that rebuilds it from primitives, procedural shaders and generated geometry, with pivots, sockets and colliders so the result is ready to animate. A staged pipeline (blockout, structure, form, material, surface, lighting, interaction, optimization) is vision-reviewed against the reference after every pass, while stdlib Python scripts handle validation and gates so model tokens go only to visual judgment and code. Runs in Claude Code, Codex, OpenCode and Hermes; optional plugins add rigging, interiors and 2D PixiJS. About 19.9k GitHub stars; on @AmirMushich's Oct 23, 2026 list of agent skills. ## Use when - a 3D model of a product or object for a three.js scene or video - a character or prop rebuilt from one picture - an animation-ready model with real pivots instead of an inert mesh ## Not for - Photogrammetry or exact scans: it reconstructs by code, and unseen sides are marked low-confidence - Exact likeness of a real person from one photo: the pipeline reports per-region confidence and asks for more views ## Install - Claude Code: `npx --yes img2threejs@latest install` - Codex: `npx --yes img2threejs@latest install --host codex` - Any agent, with the vargai CLI: `vargai install img2threejs` ## Example output https://s3.varg.ai/files/4325c578-378d-4c43-ae53-3cc3218df1ea/file_30b06de7e03e.webp — A code-only Warhauler vehicle rebuilt from one reference image, from the project's showcase repo. (credit: img2threejs showcase, https://img2threejs.io/) ## More 3D scenes skills - [Three.js Skills](https://varg.ai/how-to/skills/threejs-skills.md): 13 Three.js skills: scenes, geometry, materials, lighting, GLSL and TSL shaders, animation, post-processing, R3F. - [Three.js Scene Composition](https://varg.ai/how-to/skills/calesthio-threejs-scene-composition.md): Plan, build and capture Three.js scenes for video: absolute-time frames, seeded motion, color-safe glTF, render QA. - [R3F Skills](https://varg.ai/how-to/skills/enzed-r3f-skills.md): 11 React Three Fiber skills checked against Fiber 9.7 and three r185: Canvas, demand loops, loaders, shaders, post. - [Procedural 3D Story](https://varg.ai/how-to/skills/karpathy-3d-story.md): Turn a myth or book into a seeded, multi-chapter procedural three.js film in one scene.html, audited frame by frame. - [Three.js Architecture Effects](https://varg.ai/how-to/skills/threejs-architecture-effects.md): Self-assembling 3D buildings in three.js: bricks, timber, eaves and PBR, driven by one seekable progress value. - [Teardown by Elvar](https://varg.ai/how-to/skills/elvar-teardown.md): One reference picture in, a 3D machine you can take apart out: three.js simulator, live gauges, 60 fps film. ## Run the generation on varg varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs. - Any agent with a terminal: `curl -fsSL https://varg.ai/install | sh` (Windows: `irm https://varg.ai/install.ps1 | iex`), then `vargai login` and every model is a command — `vargai generate_video …`, `vargai estimate_cost …` (https://varg.ai/how-to/cli/) - Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a -y` - Grok and any agent that reads SKILL.md: `npx skills add vargHQ/skills --skill varg-ai`, or point it at the skill's SKILL.md - Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp` - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt