Smart low poly
All supported parameters for highpoly_to_lowpoly.
Rig data
Mesh editing and remeshing reconstruct model geometry and do not preserve skeletal (rig) data — including bones, skin weights, and animation bindings — even when the input model was previously rigged or retargeted.
| Task | Type | Description |
|---|---|---|
| Mesh Segmentation | mesh_segmentation | Splits the model into editable parts |
| Mesh Completion | mesh_completion | Applies segmentation results and completes selected parts |
| Smart LowPoly | highpoly_to_lowpoly | Remeshes the model to a lower polygon count, including quad output (quad=true) |
| Format Conversion (remesh) | convert_model | Remeshing via quad=true; skeleton data is not preserved regardless of the with_animation setting |
Complete all mesh editing and remeshing steps before running animate_prerigcheck → animate_rig → animate_retarget. If you process a rigged model with any of the tasks above, re-run the full animation pipeline on the resulting static mesh.
Endpoint
Parameters
Required parameters
type: This field must be set to highpoly_to_lowpoly.
original_model_task_id: The task_id of previous model, the model_version of previous task should be in (Turbo-v1.0-20250506 or over v2.0-20240919). Only the task IDs of the tasks which has model output can be used.
Note
1.x versions of text_to_model, image_to_model and multiview_to_model tasks are not supported.
quad: A bool value, set true to enable quad mesh output. If quad=true and face_limit is not set, face_limit will default to 10000. Recommended not to exceed 150,000. This will cost 5 additional credits when set to true.
TIP
Enabling this option will force the output to be an FBX model.
Optional parameters
model_version: Set to P-v2.0-20251225.
part_names: The list of part names referred from mesh-segmentation, the default value is empty list.
face_limit: A integer value which determines the target face count of the model during generation, range should be set from 500 to 20000. When quad is true, the range should be set from 500 to 10000.
bake: A bool value, when set to true, the model will be baked when generation. The default value is true.
Returns
task_id: The identifier for the successfully submitted task.