AI game art workspace for creating and animating 2D game characters and scenes
GPU-accelerated rigid-body dynamics solver for robot learning
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Open source
Pricing
Free: 50 one-time Credits (never expire), 3 lifetime runs. Starter: $19/month with 1,500 Credits each month. Creator: $39/month with 3,600 Credits each month. Pro: $79/month with 8,500 Credits each month. Studio: $159/month with 20,000 Credits each month. Annual plans save 25% compared with 12 month
Not given
Key features
Generate game characters from briefs or references across six art styles
AI character motion generation with continuous video output
Select and extract 8 to 64 frames from generated motion
Edit frame timing, position and order after generation
Recolor animations across all frames in a sequence
Export as PNG frames, sprite sheets, GIFs or ZIP files
Sprite sheet editing, splitting and resizing tools
Motion quality check with automatic retry on failure
Idle animation generator with procedural breathing
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
Motion-first workflow: generate full video, then choose frames, rather than commit to frame count upfront
Keep character identity across multiple outfits, expressions and motions
Exact credit cost shown before generation approval
One eligible motion or image replacement at no extra cost when quality check fails
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