Open-source video generation models and world simulators
AI image generator and editor on an infinite canvas for creating, editing, and expanding images
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
NO
Pricing model
Freemium
Free trial
Pricing
Free plan: $0/month with 250 lifetime credits. Lite plan: 1,200 credits per month. Standard plan: 5,000 credits per month. Mochi video generation costs 100 credits; replay video costs 50 credits.
Free trial for 7 days. Starter plan $20/mo with 1,000 tokens monthly. Pro plan $60/mo with 3,000 tokens monthly. Studio plan $200/mo with 10,000 tokens monthly. Unlimited plan available at custom pricing. 50% discount when paying annually.
Key features
Text-to-video generation from written descriptions
Local execution and customization via open-source repository
ComfyUI integration for tailored experience
Interactive playground for testing capabilities
Commercial usage rights on paid plans
MP4 video format with H.264 encoding
Videos up to 5.4 seconds at 30fps
Video download for 30 days after generation
Watermark removal on paid plans
High queue priority for paid users
Inpainting to mask and regenerate image regions
Outpainting to extend images in any direction without boundaries
Instruction edits to describe changes in plain words
Multi-image input and compositing from reference images
AI agent for bulk creation and autonomous asset generation
Non-destructive editing with layers and reversible changes
Drawing, text, and shape tools on canvas
Runs in browser and installs as app on mobile and desktop
Remove background in a single step
What makes it different
Apache 2.0 licensed open-source model for individual and commercial use
World simulator technology for embodied AI breakthroughs
Team with 55,000+ citations across foundational AI research
Run locally without vendor lock-in
State-of-the-art open text-to-video model
Non-destructive infinite canvas with full professional editing capabilities
Integrated AI agent that works autonomously on the canvas to generate and compose full layouts
Works across all devices without installation directly in browser
Multiple reference images as context for precise AI-guided edits
10+ integrated high-performance AI models in one workspace