Extensions/ComfyUI-Hunyuan3D-v3
ComfyUI Extension

ComfyUI-Hunyuan3D-v3

Text-to-3D and Image-to-3D generation using Tencent Cloud Hunyuan 3D Global API. Supports PBR materials, face count control (40K-1.5M faces), and multiple generation…

By exedesign·Created 8 months ago·Updated 5 months ago· 10
exedesign/Hunyuan-3D-v3
Nodes6
On cloudLocal install
CategoryHunyuan3D/v3
Stars10
Updated5 months ago

Nodes (6)

Hunyuan 3D Model Preview

Hunyuan 3D Model Preview — ComfyUI Node Guide

Hunyuan3D/v3
Hunyuan Batch Image to 3D

Hunyuan Batch Image to 3D — ComfyUI Node Guide

Hunyuan3D/v3
Hunyuan Batch Model Preview

Hunyuan Batch Model Preview — ComfyUI Node Guide

Hunyuan3D/v3
Hunyuan Config

Hunyuan Config — ComfyUI Node Guide

Hunyuan3D/v3
Hunyuan Image to 3D

Hunyuan Image to 3D — ComfyUI Node Guide

Hunyuan3D/v3
Hunyuan Text to 3D

Hunyuan Text to 3D — ComfyUI Node Guide

Hunyuan3D/v3
Readme

ComfyUI-Hunyuan3D-v3

License: MIT GitHub release

ComfyUI custom node for Text-to-3D and Image-to-3D generation using Tencent Cloud Hunyuan 3D Global API v3.

Features

  • Text-to-3D: Create 3D models from text prompts
  • Image-to-3D: Convert images to 3D models
  • Advanced Options: PBR materials, face count control (40K-1.5M), generation types
  • GLB Output: Industry-standard format
  • Global API: ap-singapore region

Installation

Via ComfyUI Manager

  1. Open ComfyUI Manager
  2. Search "Hunyuan 3D"
  3. Install & Restart

Manual

cd ComfyUI/custom_nodes
git clone https://github.com/exedesign/Hunyuan-3D-v3.git
cd Hunyuan-3D-v3
pip install -r requirements.txt

Setup

  1. Get API keys: https://console.intl.cloud.tencent.com/ Access Management API Keys
  2. Activate Hunyuan 3D service (Console AI Services)
  3. Add billing info ( Paid API: ~$0.10-0.60 per request)

Quick Start

HunyuanConfig (SecretId, SecretKey)  HunyuanTextTo3D  Preview3D

Parameters

  • enable_pbr: PBR materials (default: False)
  • face_count: 40000-1500000 (default: 500000)
  • generate_type: Normal/LowPoly/Geometry/Sketch
  • polygon_type: triangle/quadrilateral

Output

  • Format: GLB
  • Location: ComfyUI/models/3d_models/

Batch Processing

⚡ Method 3: Automatic Batch Node (EASIEST!)

One-click batch processing for entire folders!

1. Load: examples/auto_batch_workflow.json
2. Put images in ComfyUI/input/
3. Set API credentials
4. Configure input/output folders
5. Click Queue Prompt once → ALL images processed!

Features:

  • ✅ Single click processes all images
  • ✅ Automatic file discovery with pattern matching
  • ✅ Custom output folder selection
  • ✅ Progress tracking per image
  • ✅ Detailed summary report with paths

Method 1: Python Script

# 1. Copy batch_hunyuan3d.py to ComfyUI root folder
# 2. Edit API credentials in the script
# 3. Place images in 'input_images' folder
# 4. Run:
python batch_hunyuan3d.py

Method 2: Manual Workflow

Use examples/batch_image_to_3d_workflow.json:

  1. Load workflow in ComfyUI
  2. Select image and Queue Prompt
  3. Repeat for each image

Troubleshooting

ResourceInsufficient Error:

  • Check account balance
  • Add credits ($10+ recommended)
  • Verify service activated

Batch Processing Tips:

  • Process 5-10 images at a time
  • Each image takes ~2-5 minutes
  • Monitor API credits

License

MIT - See LICENSE

Requires Tencent Cloud account with billing enabled