HY 3D 2.0
Generate a textured-ready 3D mesh from a single image using Hunyuan3D 2.0's shape diffusion pipeline, which aligns geometry to the given image and outputs an untextured white mesh. Ideal for 3D asset prototyping, game and AR content prep, and as a base for later texture painting or handcrafted detailing.
Minimum ComfyUI version: 0.3.28
Models and weights
- hunyuan3d-dit-v2_fp16.safetensors ·
models/checkpoints/
ComfyUI nodes
- CLIPVisionEncode
- Empty Hunyuan 3D v2 Latent
- Hunyuan 3D VAE Decode
- Hunyuan3Dv2Conditioning
- ImageOnlyCheckpointLoader
- KSampler
- LoadImage
- ModelSamplingAuraFlow
- Save 3D Model
- Voxel to Mesh
ORIGINAL REPOSITORY
Comfy-Org/workflow_templates ↗GitHub activity
- Stars
- 1,445
- Forks
- 270
- Open issues and PRs
- 98
- Repository size
- ~4,915,364 KB
- Default branch
- main
- Created
- Feb 28, 2025
- Repository updated
- Nov 5, 2026
- Last push
- Nov 5, 2026
- Language
- TypeScript
- License
- MIT
Repository-wide figures from GitHub, checked Nov 5, 2026. Stars are endorsements, not a Mega AI Hub quality rating. Repository size is GitHub’s estimate; a ZIP download may differ.
Resource information
- Deployment
- Local
- Publisher
- Comfy Org
- License
- MIT
- Last record update
- Nov 5, 2026