Hunyuan Part

This documentation is valid for the following list of our models:

• tencent/hunyuan-part

Try in Playground

Model Overview

The model analyzes a 3D mesh and performs high-fidelity, structure-coherent shape decomposition, splitting the original mesh into multiple parts that can then be used independently in 3D editors, for example for texturing or animation.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

post

Body

application/json

modelstring · enumRequiredPossible values:

mesh_urlstring · uriRequired

URL of the 3D model file (.glb or .obj) to process for segmentation.

point_prompt_xnumber · min: -1 · max: 1Optional

X coordinate of the point prompt for segmentation.

point_prompt_ynumber · min: -1 · max: 1Optional

Y coordinate of the point prompt for segmentation.

point_prompt_znumber · min: -1 · max: 1Optional

Z coordinate of the point prompt for segmentation.

point_numintegerOptional

Number of points to sample from the mesh.

Default: 100000

use_normalbooleanOptional

Whether to use normal information for segmentation.

Default: true

noise_stdnumberOptional

Standard deviation of noise to add to sampled points.

seedinteger · min: 1Optional

The same seed and the same prompt given to the same version of the model will output the same image every time.

Responses

200Success

application/json

post

/v1/images/generations

cURLJavaScriptPython

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v1/images/generations' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
      "model": "tencent/hunyuan-part",
      "mesh_url": "https://storage.googleapis.com/falserverless/model_tests/video_models/base_basic_shaded.glb"
    }'

200Success

{
  "data": [
    {
      "url": "https://cdn.aimlapi.com/generations/hedgehog/1749730923700-29fe35d2-4aef-4bc5-a911-6c39884d16a8.png",
      "b64_json": null
    }
  ],
  "meta": {
    "usage": {
      "credits_used": 120000
    }
  }
}

Quick Example

Let's generate an image using a simple prompt.

Python

import requests
import json

def main():
    response = requests.post(
        "https://api.aimlapi.com/v1/images/generations",
        headers={
            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
            "Authorization": "Bearer d09bc3015a66486e9bd4e6d1942934e1",
            "Content-Type": "application/json",
        },
        json={
            "model": "tencent/hunyuan-part",
            "mesh_url": "https://storage.googleapis.com/falserverless/model_tests/video_models/base_basic_shaded.glb",
        },
    )

    response.raise_for_status()
    data = response.json()

    data = response.json()
    print(json.dumps(data, indent=2, ensure_ascii=False))


if __name__ == "__main__":
    main()

JS

Response

{
  "segmented_mesh": {
    "url": "https://cdn.aimlapi.com/flamingo/files/b/0a8a7d7b/gG3-a4ScI4yBswdMQ8CYQ_segmented.glb",
    "content_type": "application/octet-stream",
    "file_name": "segmented.glb",
    "file_size": 1600920
  },
  "mask_1_mesh": {
    "url": "https://cdn.aimlapi.com/flamingo/files/b/0a8a7d7b/Csp8ZOZQsxpaOtDrvbe2G_mask_1.glb",
    "content_type": "application/octet-stream",
    "file_name": "mask_1.glb",
    "file_size": 1600912
  },
  "mask_2_mesh": {
    "url": "https://cdn.aimlapi.com/flamingo/files/b/0a8a7d7b/fStkD-Pq6RZrlooYcZ34__mask_2.glb",
    "content_type": "application/octet-stream",
    "file_name": "mask_2.glb",
    "file_size": 1600920
  },
  "mask_3_mesh": {
    "url": "https://cdn.aimlapi.com/flamingo/files/b/0a8a7d7b/YVHy9A0XgUMehoLCA7z5o_mask_3.glb",
    "content_type": "application/octet-stream",
    "file_name": "mask_3.glb",
    "file_size": 1600920
  },
  "best_mask_index": 2,
  "iou_scores": [
    0.49007099866867065,
    0.5047933459281921,
    0.4866638779640198
  ],
  "seed": 3285486654,
  "requestId": "74e75e9a-7965-4348-a84d-d8663b0906dd",
  "meta": {
    "usage": {
      "credits_used": 84000
    }
  }
}