Image-to-3D
Upload one or multiple images and convert them into detailed 3D models. Automatic background removal ensures clean geometry generation from product photos or reference images.
Text-to-3D
Describe any object or scene in natural language and generate a corresponding 3D model. Hybrid mode combines text prompts with reference images for fine-grained control.
Quality Presets
Choose from 6 built-in quality presets that balance generation speed against mesh detail, texture resolution, and polygon count for your target use case.
3D Viewer
Inspect generated models instantly in a real-time preview powered by Three.js, @react-three/fiber, and @react-three/drei. Rotate, zoom, and pan directly in the browser.
Facial Enhancement
Access advanced AI options including facial enhancement for character models, expression refinement, and specialized optimization for portrait and avatar generation.
Analytics
Track all your generated models in a built-in analytics dashboard. View generation history, success rates, processing times, and model statistics at a glance.
Architecture
The application follows a modular component architecture orchestrated by a central Rodin component that manages state, API communication, and rendering:- Rodin Component: The main orchestrator that coordinates the entire application flow, manages global state, and connects UI components to the Rodin AI API.
- EnhancedForm: A comprehensive form with 80+ configuration options validated by Zod, covering quality, geometry, texture, and post-processing settings.
- SmartOptionsPanel: Dynamically renders parameter controls based on selected generation mode, showing only relevant options for image-to-3D, text-to-3D, or hybrid workflows.
- ModelViewer: Renders the generated 3D model using Three.js with @react-three/fiber and @react-three/drei, providing an interactive viewport inside the browser.
- api-service.ts: Handles all API interactions including job submission to
/api/rodin, status polling via/api/status, and file retrieval through/api/download.