image-to-3d

image-to-3d is a skill for Claude Code from guinacio/claude-image-gen. It costs 112 tokens per session (3,317 once invoked), scanned A, original, MIT.

A tool that turns one image of an isolated object into a downloadable GLB 3D model through the Tripo service. A GLB is a 3D file that can be opened by tools such as Blender, Unity, or Unreal.

In plain words
What is it for?
It is for reconstructing products, clothing, props, or hardware from photographs or generated images. It uploads the image, creates the model, and downloads the resulting GLB, with optional extra views and textures.
Why use it?
It avoids manually building a basic 3D mesh from a product photo or other single-object image. A required confirmation step helps prevent an unintended paid generation job.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the media-pipeline plugin — 3 skills, 1 MCP server shipped together

Good fit It is for reconstructing products, clothing, props, or hardware from photographs or generated images. It uploads the image, creates the model, and downloads the resulting GLB, with optional extra views and textures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guinacio/claude-image-gen/image-to-3d
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add guinacio/claude-image-gen --skill image-to-3d
Clone the repo
git clone --depth 1 https://github.com/guinacio/claude-image-gen

Made for: Claude Code.

Or install media-pipeline, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for image-to-3d

README.md
[![agentmods](https://agentmods.dev/badge/skills/guinacio/claude-image-gen/image-to-3d/github.svg)](https://agentmods.dev/skills/guinacio/claude-image-gen/image-to-3d)
Your own site
<a href="https://agentmods.dev/skills/guinacio/claude-image-gen/image-to-3d"><img src="https://agentmods.dev/badge/skills/guinacio/claude-image-gen/image-to-3d/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for image-to-3d

Your own site · 80×15
<a href="https://agentmods.dev/skills/guinacio/claude-image-gen/image-to-3d"><img src="https://agentmods.dev/badge/skills/guinacio/claude-image-gen/image-to-3d.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,317 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.03317
Opus 5 $0.00056 $0.01658
Sonnet 5 $0.00022 $0.00663
Haiku 4.5 $0.00011 $0.00332

Measured 2d ago against content hash 749064ae67db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

image-to-3d scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/normalize_views.py, scripts/tripo.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

optional-workflows/image-to-3d/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image to 3D with Tripo

One image of one isolated object goes in, a GLB comes out. The script in scripts/tripo.py handles upload, submission, polling and download.

Cost rule, before anything else

Never submit a Tripo job without asking first. Every run spends the user's credits. The script enforces this: without --yes it prints the plan, the cost and the account balance, and stops. Show that dry run, then wait for an explicit go-ahead before adding --yes.

Usage

python scripts/tripo.py piece.png --name sneaker --output-dir ./models
python scripts/tripo.py piece.png --name sneaker --output-dir ./models --yes

Needs TRIPO_API_KEY in the environment. Standard library only, no install.

Flag Effect
--yes actually submit and spend
--left, --back, --right supply your own views instead of letting Tripo invent them
--direct single-image path, skips multiview: cheaper, least accurate geometry
--model-version v3.1-20260211 (default) or v3.0-20250812
--name, --output-dir naming and destination

Texture — all inert unless --texture is passed:

Flag Effect
--texture also generate texture maps, 10 more credits (default: geometry only)
--texture-quality detailed +10 credits
--texture-alignment original_image (default) favours visual fidelity, geometry favours structure
--texture-seed N repeatable texture

Mesh:

Flag Effect
--face-limit N cap the polygon count
--geometry-quality detailed Tripo's Ultra mode, +20 credits
--smart-low-poly the Smart Mesh of the web UI: built topology instead of a collapsed dense mesh, +10 credits
--quad quads instead of triangles, +5 credits
--generate-parts model split into parts, +20 credits; refuses to combine with textures or --quad
--no-export-uv faster, but the mesh arrives with no UVs
--compress geometry geometry compression instead of the default meshopt

Read the full file on GitHub · 281 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 281 lines · 112 tokens per session scan A 749064ae67db

Subscribe to this mod's changes

image-to-3d is a skill published in the GitHub repository guinacio/claude-image-gen (63 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 3,317 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.

Related

Other skills, from other repositories

image-to-3d-pipeline

Transformez une image 2D en modèle 3D animé prêt pour le web ou le jeu en moins de 30 minutes, en utilisant le workflow Dilum Sanjaya (Hunyuan3D + Mixamo). Use when: Créer un personnage 3D pour un site web - Mascotte, avatar, illustration interactive; Prototyper un asset de jeu - Character design, props…

guia-matthieu/clawfu-skills · 140 tokens

screenshot-isolated

Render a target GameObject from a chosen camera angle with optional layer-based isolation, configurable background (solid/skybox/transparent), multi-light setup via JSON, and Composite (2x2 Front/Right/Back/Top) mode. Returns a PNG image. When isolated=true, inactive children may briefly fire OnEnable — see the body…

IvanMurzak/Unity-MCP · 78 tokens

screenshot-camera

Capture a screenshot from a Unity Camera and return it as a PNG image for direct LLM inspection. Falls back to Camera.main (then any active camera) when cameraRef is null. Width and height are capped to keep response size manageable.

IvanMurzak/Unity-MCP · 58 tokens

screenshot-game-view

Capture a screenshot of the Unity Editor's Game View by reading its internal render texture directly. Image size matches the current Game View resolution; the tool corrects Y-flip on DirectX / Metal so the output is always upright. Requires an open Game View window.

IvanMurzak/Unity-MCP · 58 tokens

screenshot-scene-view

Capture a screenshot from the Unity Editor Scene View at the requested size. Renders via the Scene View's active camera onto a temporary RenderTexture. Requires an open Scene View.

IvanMurzak/Unity-MCP · 42 tokens

sound-cues

Create and modify SoundCue assets — add/connect nodes (mixer, random, delay, attenuation, modulator, etc.) and set audio properties (SoundCueService). Use when the user asks to create a Sound Cue, build a SoundCue node graph, or wire audio playback logic.

kevinpbuckley/VibeUE · 62 tokens