HY 3D 2.0

Generate 3D models from single images using Hunyuan3D 2.0.

About

The HY 3D 2.0 workflow is designed to transform single 2D images into detailed 3D models using the Hunyuan3D 2.0 model. This workflow leverages advanced AI techniques to interpret and reconstruct depth and form from flat images, making it an invaluable tool for artists, designers, and developers looking to create 3D assets quickly. At the heart of this process are nodes like the CLIPVisionEncode, which extracts visual features from the input image, and the VAEDecodeHunyuan3D, which decodes these features into a 3D representation.

The workflow also includes the VoxelToMesh node, which converts voxel data into a mesh format, ready for use in 3D applications.

Technically, this workflow begins by loading the Hunyuan3D model using the ImageOnlyCheckpointLoader node. Users then upload their image via the LoadImage node, which is processed through a series of conditioning and sampling steps, including the Hunyuan3Dv2Conditioning and ModelSamplingAuraFlow nodes. The final 3D model is saved in GLB format using the SaveGLB node, making it compatible with most 3D software. This workflow is particularly useful for creating 3D models from photos or concept art, providing a bridge between 2D creativity and 3D application.

What you provide

Reading the workflow

Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.

Try in Cloud

Output

Use this workflow from code

Generated from the workflow graph and inputs when possible; stored examples are shown otherwise. Review credentials and endpoints before running code, which may incur charges.

Get API key

What you need

Runs on: Comfy Cloud
Key: COMFY_API_KEY

Needs a paid Cloud plan and credits.

Download API JSON

# Python 3.10+: pip install comfy-sdk==0.4.0
import os

from comfy_sdk import Comfy

api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
    "3": {
        "class_type": "KSampler",
        "inputs": {
            "cfg": 8,
            "denoise": 1,
            "latent_image": [
                "66",
                0
            ],
            "model": [
                "70",
                0
            ],
            "negative": [
                "80",
                1
            ],
            "positive": [
                "80",
                0
            ],
            "sampler_name": "euler",
            "scheduler": "normal",
            "seed": 242832339647017,
            "steps": 20
        },
        "_meta": {
            "title": "KSampler"
        }
    },
    "51": {
        "class_type": "CLIPVisionEncode",
        "inputs": {
            "clip_vision": [
                "54",
                1
            ],
            "crop": "none",
            "image": [
                "56",
                0
            ]
        },
        "_meta": {
            "title": "CLIP Vision Encode"
        }
    },
    "54": {
        "class_type": "ImageOnlyCheckpointLoader",
        "inputs": {
            "ckpt_name": "hunyuan3d-dit-v2_fp16.safetensors"
        },
        "_meta": {
            "title": "Load Checkpoint Image Only (img2vid model)"
        }
    },
    "56": {
        "class_type": "LoadImage",
        "inputs": {
            "image": "3d_hunyuan3d_image_to_model_input_image.png"
        },
        "_meta": {
            "title": "Load Image"
        }
    },
    "61": {
        "class_type": "VAEDecodeHunyuan3D",
        "inputs": {
            "num_chunks": 8000,
            "octree_resolution": 256,
            "samples": [
                "3",
                0
            ],
            "vae": [
                "54",
                2
            ]
        },
        "_meta": {
            "title": "Hunyuan 3D VAE Decode"
        }
    },
    "66": {
        "class_type": "EmptyLatentHunyuan3Dv2",
        "inputs": {
            "batch_size": 1,
            "resolution": 3072
        },
        "_meta": {
            "title": "Empty Hunyuan 3D v2 Latent"
        }
    },
    "70": {
        "class_type": "ModelSamplingAuraFlow",
        "inputs": {
            "model": [
                "54",
                0
            ],
            "sampling": "flow",
            "shift": 1.0000000000000002
        },
        "_meta": {
            "title": "ModelSamplingAuraFlow"
        }
    },
    "80": {
        "class_type": "Hunyuan3Dv2Conditioning",
        "inputs": {
            "clip_vision_output": [
                "51",
                0
            ]
        },
        "_meta": {
            "title": "Hunyuan3Dv2Conditioning"
        }
    },
    "81": {
        "class_type": "VoxelToMesh",
        "inputs": {
            "algorithm": "surface net",
            "threshold": 0.6,
            "voxel": [
                "61",
                0
            ]
        },
        "_meta": {
            "title": "Voxel to Mesh"
        }
    },
    "82": {
        "class_type": "SaveGLB",
        "inputs": {
            "filename_prefix": "mesh/ComfyUI",
            "mesh": [
                "81",
                0
            ]
        },
        "_meta": {
            "title": "Save 3D Model"
        }
    }
})

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)

API documentation

HY 3D 2.0

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

What types of images work best with this workflow?

Can I use this workflow for commercial projects?

What file format is the 3D model saved in?

How can I improve the accuracy of the 3D model?