Hunyuan 3D v3.1 Pro for Image to 3D

ABOUT THE WORKFLOW

Generate a 3D Model from a Photo
Upload a single image and the model generates a textured 3D mesh from it. Add photos from other angles to improve accuracy. You get a downloadable GLB file with optional PBR materials.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• Hunyuan 3D v3.1 Pro by Tencent AI Lab. A production-grade image-to-3D model with high-fidelity geometry, clean mesh topology, and support for up to 1.5 million polygon faces.

HOW IT WORKS

Step 1. Upload your image
The photo of the object or scene you want to turn into a 3D model. A clean, well-lit shot with the subject clearly visible works best.
Works great with: products · characters · furniture · vehicles · props

Step 2. Add extra angles (optional)
Supply up to seven more photos from different views: back, left, right, top, bottom, left-front, right-front. More angles mean more accurate geometry.

Step 3. Hit run and preview
The model generates a textured 3D mesh and shows a thumbnail preview plus an interactive 3D viewer in the workflow. Download the GLB file when you are happy with it.
Ready for: Blender · Unity · Unreal · any GLB-compatible viewer

First time? Leave every setting as-is. The defaults (Normal mode, PBR off, 500K faces) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard 3D model (most people) — Normal mode, PBR off, 500K faces. The right starting point for almost everyone.

• Need game-ready or print-ready detail — Raise face count to 1M or 1.5M. Higher poly count captures finer surface detail, but the file size grows with it.

• Want realistic materials for rendering — Turn PBR on. The model outputs physically-based rendering textures so materials respond to lighting in Blender, Unity, or Unreal.

• Have photos from multiple angles — Connect images to the back, left, right, top, bottom, left-front, and right-front inputs. The more views you supply, the more accurate the geometry.

• Quick test before a full run — Keep face count at 500K and PBR off. Fastest way to check if the model reads the subject correctly before committing to a high-poly run.

• The mesh has soft or missing detail on the back — Add a back-view photo. A single front image means the model has to guess what the far side looks like.

Prompt: This workflow has no text prompt. The model works entirely from the images you upload. To control the result, supply better photos: clean backgrounds, even lighting, and more angles all improve the output.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🎮 Game Developers
Turn concept art or reference photos into 3D game assets. Export as GLB and drop straight into Unity or Unreal with PBR materials ready for in-engine lighting.

🖨️ 3D Printing
Generate a watertight mesh from a product photo or character design and send it to a slicer. Raise the face count for fine surface detail.

🛍️ E-commerce & Product Visualization
Photograph a product once and generate a 3D model for interactive product pages, AR try-on, or catalog rendering.

🎬 Pre-visualization & Concept Art
Block out 3D scenes from reference photos during early production. Get a placeable asset in minutes instead of hours of manual modeling.

🏗️ Architecture & Interior Design
Convert photos of furniture, fixtures, or decorative objects into 3D assets for walkthroughs and client presentations.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Clean, well-lit photos with a single subject

• Solid or simple backgrounds

• Multiple angle photos of the same object

• Rigid objects with clear geometry (products, furniture, vehicles)

⚠️ May produce softer results

• Thin or transparent objects (glass, wire, hair)

• Complex multi-part scenes from a single view

• Heavy motion blur or low-light photos

• Flat textures with no depth cues (logos, posters)

FAQ

What is Hunyuan 3D v3.1 Pro?
Hunyuan 3D v3.1 Pro is a production-grade 3D generation model from Tencent AI Lab. It takes a single photo, or up to eight photos from different angles, and generates a textured 3D mesh with configurable polygon count up to 1.5 million faces. It supports optional PBR materials and outputs in GLB format.

How does multi-view input improve the 3D model?
A single photo gives the model one perspective, so it has to infer the geometry of every unseen surface. When you supply additional angles (back, left, right, top, bottom, left-front, right-front), the model reconstructs surfaces it can see directly instead of guessing. The result is more accurate geometry and fewer artifacts on the far side of the object.

What is PBR and when should I turn it on?
PBR stands for physically-based rendering. When enabled, the model outputs material maps (albedo, roughness, metallic, normal) alongside the mesh. This means the 3D model reacts to lighting realistically in engines like Blender, Unity, and Unreal. Leave PBR off for quick previews or when you plan to texture the model yourself.

Can I use Hunyuan 3D v3.1 Pro output in Unity, Unreal, or Blender?
Yes. The output is a standard GLB file, which all three applications import natively. In Unity, drag it into the project assets. In Unreal, use the Datasmith or GLTF importer. In Blender, use File > Import > glTF 2.0. With PBR enabled, the material maps come embedded in the file.

Is Hunyuan 3D v3.1 Pro open source?
No. Earlier versions of Hunyuan 3D (2.0, 2.1) are open source, but the 3.x line is API-only. The model weights have not been publicly released. This workflow connects to the API through a partner node, so you do not need your own API key.

Can I use the output for commercial projects?
Hunyuan 3D v3.1 Pro is a proprietary Tencent model, so commercial use is governed by Tencent's terms rather than an open license. Commercial use is generally allowed, but review Tencent's current terms and make sure you have the rights to any image you upload.

How to run Hunyuan 3D v3.1 Pro online?
You can run Hunyuan 3D v3.1 Pro online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload your image, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A designer runs an edit and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it?
Upload a photo of the object you want in 3D and hit run. The settings are already set.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.