Pre rig check
All supported parameters for animate_prerigcheck.
riggable: true means it can be rigged, false means it cannot be rigged.
rig_type: Available values are biped, quadruped, hexapod, octopod, avian, serpentine, aquatic.
The animation flow rigs a previous generation (draft or refine) and then adds animation. These guidelines help when the subject is not clearly humanoid:
- Preferred subjects: humans, robots, or anime characters with a clear depiction of four limbs, and simpler attire, ideally one layer of clothing.
- Subjects to avoid: non-human-like figures such as animals, large structures, or food; human-like models with unnatural connections such as fused legs; excessive accessories such as multiple glasses or necklaces.
There is no strict limitation. If you are unsure about the pose, specify an A-pose or T-pose in the text prompt before rigging.
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 animate_prerigcheck.
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.
Returns
task_id: The identifier for the successfully submitted task.