AI sprite sheet generator that turns a single character image into game-ready spritesheets in seconds
GPU-accelerated rigid-body dynamics solver for robot learning
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Freemium
Open source
Pricing
Free: Included daily credits with 15 free credits for new accounts plus 3 bonus credits daily. Starter: $12/month with 500 credits per month. Pro: $29/month with 1,500 credits per month. Enterprise: Contact for pricing with unlimited unlocks and custom volume. One-time credit packs also available at
Not given
Key features
Convert single character images to complete animation sets with idle, walk, run, jump, and attack animations
Custom animation with storyboard keyframes and reference image guidance
8-directional isometric animation generation
Generate game props, items, weapons, and pickups
Character outfit and skin variation editing
Motion transfer library to apply animations to different characters
REST API for programmatic generation and asset management
MCP server integration for AI coding agents
Batch processing and Advanced Mode for multiple animations
Export to multiple game engines including Unity, Godot, GameMaker, Phaser, and RPG Maker
3.8× PhysX throughput on 20 benchmarks geometric mean
13.0× performance on heterogeneous task mixtures
Per-environment work scheduling for efficiency
Reduced-coordinate articulation dynamics
Differentiable simulation
Rigid-deformable coupling support
Compliant and hydroelastic contact
62% less GPU memory than PhysX at matched batch size
3.90 million environment steps per second peak throughput
What makes it different
Automatic background removal and character consistency preservation across all animation frames
Eliminates manual frame slicing, padding, and renaming with engine-ready exports
Generates complete animations in minutes rather than days of manual work
Supports AI-generated characters from any source like Midjourney, DALL-E, and Stable Diffusion
Integration with AI coding agents through MCP for automated asset generation in development workflows
Designed for heterogeneous workloads with different robots and tasks simulated together efficiently
Integrated into open-source Newton for seamless adoption without separate physics stack
Supports diverse physical interactions beyond rigid bodies
Enables scaling of diverse robot experience for general-purpose learning
AutoSprite
Steel