Hyper3d
/v1/runRodin V2 by hyper3d - 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.
Model identifier. Set to hyper3d/rodin/v2.
Default: hyper3d/rodin/v2
A textual prompt to guide model generation. Optional for Image-to-3D mode - if empty, AI will generate a prompt based on your images.
Default:
Seed value for randomization, ranging from 0 to 65535. Optional.
Range: 0 to 65535
Combined quality and mesh type selection. Quad = smooth surfaces, Triangle = detailed geometry. These corresponds to `mesh_mode` (if the option contains 'Triangle', mesh_mode is 'Raw', otherwise 'Quad') and `quality_override` (the numeric part of the option) parameters in Hyper3D API.
Allowed values: 4K Quad, 8K Quad, 18K Quad, 50K Quad, 2K Triangle, 20K Triangle, 150K Triangle, 500K Triangle
Default: 500K Triangle
URL of images to use while generating the 3D model. Required for Image-to-3D mode. Up to 5 images allowed.
Generate characters in T-pose or A-pose format, making them easier to rig and animate in 3D software.
Default: false
The HighPack option will provide 4K resolution textures instead of the default 1K, as well as models with high-poly. It will cost **triple the billable units**.
Generate a preview render image of the 3D model along with the model files.
Default: false
Format of the geometry file. Possible values: glb, usdz, fbx, obj, stl. Default is glb.
Allowed values: glb, usdz, fbx, obj, stl
Default: glb
Material type. PBR: Physically-based materials with realistic lighting. Shaded: Simple materials with baked lighting. All: Both types included.
Allowed values: PBR, Shaded, All
Default: All
When enabled, preserves the transparency channel from input images during 3D generation.
Default: false
An array that specifies the bounding box dimensions [width, height, length].
Response Schema
The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.
Error message if the task failed. Empty on success.
Unique identifier for the generation task.
Model ID used for the prediction.
Array of generated content. Empty when status is not completed.
Status of the task: pending, running, completed, failed, or timeout.
Allowed values: pending, running, completed, failed, timeout
Model capabilities
Capabilities declared by the model registry.
Default: image-to-3d
Execution mode declared by the model registry.
Default: async

