Generate 3D models from images or text prompts entirely in your browser
AI agent for content creators
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Freemium
Freemium
Pricing
Basic: $9.99/month or $6.99/month (save 30% yearly); Pro: $29/month or $18.99/month (save 35% yearly); Enterprise: $49/month or $35/month (save 29% yearly). Plans include credits for images and videos monthly.
Free: 20 credits per day, no card required. Lite: $9/month with 1,000 credits per month. Starter: $19/month with 2,000 credits per month. Pro: $49/month with 6,000 credits per month. All prices in USD.
Key features
Image-to-3D generation from JPG, PNG, or WebP uploads
Text-to-3D generation from natural language descriptions
Multiple AI models: Microsoft Trellis 2, Hunyuan 3D, and Seed 3D
Export in GLB, OBJ, FBX, and USDZ formats
Interactive 3D preview in browser before download
No GPU or local installation required
Generation typically completes in 2-6 minutes
Support for complex geometry and non-manifold shapes with Trellis 2
Export rotating GIF preview for sharing
Direct import compatibility with Unity and Unreal Engine
Video editing by natural language description
Automatic subtitle generation in multiple languages
Thumbnail creation from footage or text description
Audio transcription with word-level timing
Text-to-speech voiceover generation
Motion graphics and animated sequences
Document analysis and PDF processing
Live progress visibility
Video generation from text descriptions
Multi-platform access via web, iOS, and Android
What makes it different
Access to Microsoft Trellis 2, a 4-billion-parameter model for complex topology
Entirely browser-based with no GPU, setup, or 3D experience needed
Choice of three leading AI models optimized for different object types
Fast generation with interactive preview in minutes
Commercial usage rights and compatibility with professional workflows
Natural conversation interface instead of complex editing timelines
No watermarks on exported files
Privacy-first processing with no model training on user content