Appearance

Hunyuan3D

POST/v1/run

Hunyuan3d V2 Turbo by Tencent - convert 2D images into 3D models with AI. Generate textured 3D assets from single photos for games, AR/VR, e-commerce, and digital content creation.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to tencent/hunyuan3d/v2/turbo.

Default: tencent/hunyuan3d/v2/turbo

stringimagerequired

URL of image to use while generating the 3D model.

Optional<integer>octree_resolution

Octree resolution for the model.

Range: 1 to 1024

Default: 256

Optional<boolean>textured_mesh

If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh.

Default: false

Optional<integer>seed

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

Optional<integer>num_inference_steps

Number of denoising or inference steps to run when supported.

Range: 1 to 50

Default: 50

Optional<number>guidance_scale

Request parameter supported by this model.

Range: 0 to 20

Default: 7.5

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-3d

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async