tencent-hunyuan3d

tencent-hunyuan3d is a skill for Claude Code, Codex from calesthio/generative-media-skills. It costs 203 tokens per session (5,824 once invoked), scanned A, original, MIT.

A guide to Tencent Hunyuan3D, a family of generative models that creates 3D objects or scenes from text and images. One stage creates the shape and another adds materials and textures; some versions run locally and others through hosted services.

In plain words
What is it for?
Use it to generate 3D objects from prompts or reference images, create 3D scenes, and prepare models for later production work.
Why use it?
It helps choose the right Hunyuan3D version and decide between running models yourself or using a hosted API. It also helps check licensing before using generated assets commercially.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to generate 3D objects from prompts or reference images, create 3D scenes, and prepare models for later production work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/calesthio/generative-media-skills/tencent-hunyuan3d
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 calesthio/generative-media-skills --skill tencent-hunyuan3d
Clone the repo
git clone --depth 1 https://github.com/calesthio/generative-media-skills

Made for: Claude Code, Codex.

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 tencent-hunyuan3d

README.md
[![agentmods](https://agentmods.dev/badge/skills/calesthio/generative-media-skills/tencent-hunyuan3d/github.svg)](https://agentmods.dev/skills/calesthio/generative-media-skills/tencent-hunyuan3d)
Your own site
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/tencent-hunyuan3d"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/tencent-hunyuan3d/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 tencent-hunyuan3d

Your own site · 80×15
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/tencent-hunyuan3d"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/tencent-hunyuan3d.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 203 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,824 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00203 $0.05824
Opus 5 $0.00102 $0.02912
Sonnet 5 $0.00041 $0.01165
Haiku 4.5 $0.00020 $0.00582

Measured 9d ago against content hash 2b853306d4ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tencent-hunyuan3d 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 9d ago.

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.

skills/providers/3d-generation/tencent-hunyuan3d/SKILL.md · 388 lines

How it starts

The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tencent Hunyuan3D

Hunyuan3D is Tencent's family of generative 3D models. Its defining trait is a two-stage, shape-then-texture pipeline: one model generates untextured geometry from an image (or text), a second model paints materials onto that geometry. The family spans open-weight releases you can self-host and closed tiers available only through a hosted API. Choosing correctly between those two tracks — and reading the license before you ship anything commercial — is the core production judgment this skill supports.

All version, license, hardware, and access facts below were verified 2026-07-10. These are volatile; re-verify against first-party repos before relying on them. Facts are labeled [fact] (documented in a primary source), [first-party claim] (Tencent's own benchmark/marketing, not independently reproduced), or [heuristic] (production judgment, not a documented guarantee).


When this skill applies

Use it when the request involves:

  • generating a 3D object/asset from an image or text prompt;
  • generating a 3D scene/world (panorama, explorable environment) — the HunyuanWorld / HY-World branch;
  • deciding self-host vs hosted API, or which Hunyuan3D tier fits;
  • license/compliance questions (commercial use, Territory, MAU, attribution);
  • GPU sizing for local inference or ComfyUI setup;
  • reviewing or post-processing Hunyuan3D output (topology, UVs, PBR maps).

Do not use it for 2D image generation (that is HunyuanImage), video (HunyuanVideo), or the Hunyuan text LLMs (Hunyuan/Hy3) — those are separate model families that happen to share the "Hunyuan" brand.


The version landscape (verified 2026-07-10)

Two tracks. Getting the track right is the first decision, because it determines cost model, control, and legal footing.

Track A — Open-weight, self-hostable (download from GitHub + Hugging Face)

Model Released Params (shape / paint) What it adds License
Hunyuan3D-2.0 Jan 2025 DiT-v2-0 ~1.1B / Paint-v2-0 ~1.3B (+ Delight) Original open two-stage object model Tencent Hunyuan 3D 2.0 Community License
Hunyuan3D-2mini Mar 18 2025 DiT-v2-mini 0.6B Low-VRAM shape (~5 GB) same 2.0 license
Hunyuan3D-2mv Mar 18 2025 DiT-v2-mv ~1.1B Multi-view shape input (front+back+sides) same 2.0 license
-Turbo / -Fast + FlashVDM Mar 19 2025 distilled variants of above Step/guidance distillation; fast decode same 2.0 license
Hunyuan3D-2.1 Jun 13–14 2025 DiT-v2-1 ~3.0B / Paint-v2-1 ~1.3–2B First fully open PBR + full training code Tencent Hunyuan 3D 2.1 Community License
HunyuanWorld-1.0 Jul 26 2025 Open scene/world gen: panorama proxy → layered mesh + 3DGS, 360° Tencent Hunyuan community license
HY-World 2.0 / WorldMirror 2.0 Apr 16 2026 Text/image/multiview/video → meshes + 3DGS + point clouds; editable, engine-ready open (GitHub + HF)

Read the full file on GitHub · 388 lines

Files

What ships with it

1 file 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. 9d ago First seen · 388 lines · 203 tokens per session scan A 2b853306d4ef

Subscribe to this mod's changes

tencent-hunyuan3d is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 203 tokens to every session and 5,824 once invoked, about $0.0010 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 2026-09-03.

Related

Other skills, from other repositories

threejs-animation

Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.

calesthio/OpenMontage · 40 tokens

threejs-geometry

Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.

calesthio/OpenMontage · 46 tokens

threejs-fundamentals

Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.

calesthio/OpenMontage · 51 tokens

threejs-world-generation

Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage.…

calesthio/OpenMontage · 100 tokens

3d-asset-generation

Generate, reconstruct, inspect, and route production 3D assets for OpenMontage worlds using Atlas Cloud, fal.ai, licensed catalogs, and Blender.

calesthio/OpenMontage · 37 tokens

sound-effects

Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.

calesthio/OpenMontage · 51 tokens