API docs / 3D models

hunyuan3d-2 API

Converts 2D images into 3D mesh objects with texture mapping. Takes a single input image and generates a 3D model that can be exported as GLB or OBJ files. Features speed optimization modes including 'Juiced' for fast processing and 'Unsqueezed' for highest quality output. Allows customization of mesh complexity through face count control, octree resolution settings, and inference steps. Optimized with the Pruna toolkit for enhanced performance.

Model id
prunaai/hunyuan3d-2
Provider
prunaai
Output
3D
Price
From 77 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "prunaai/hunyuan3d-2". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "prunaai/hunyuan3d-2",
  "input": {},
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
reference_imagesarray of URLs

Input image for hunyuan3d control

Up to 1 files · Accepts image/*

seednumber

Seed for random generator

Default: 12345

stepsnumber

Number of inference steps

Default: 50

output_formatstring

Default: glb

One of: glb, obj

face_countnumber

Target number of faces for simplification

Default: 40000

num_chunksnumber

Number of chunks

Default: 20000

octree_resolutionnumber

Octree resolution

Default: 200

speed_modestring

Default: Juiced 🔥 (fast)

One of: Unsqueezed 🍋 (highest quality), Juiced 🔥 (fast)