Open-source video generation models and world simulators
PDF and image translator that preserves layout
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Freemium
Paid
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.
Pay-as-you-go credit system. New accounts receive 5 cleanup pages + 5 translation pages automatically. Larger top-ups add more credits per dollar. Custom top-ups are billed in USD. Credit packs currently unavailable; visit billing to add credits.
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
Translates PDFs, JPEG, PNG, and WebP formats
Supports 100+ languages
Layout preservation with OCR
Built-in editor for corrections
Style reference pinning across pages
Page-to-page context for consistency
Web and desktop app availability
Local project storage by default
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
Preserves original layout and design while translating
Maintains character names and voice across consecutive pages
Review and edit each translated page before exporting
Pay-as-you-go pricing with no subscriptions
Works on full batches rather than individual pages
PixLate