Free: unlimited builds and demos with watermarked exports up to 15 seconds. Indie: $29/month or $290/year (2 months free) for 1 app with up to 500 monthly editor users and no watermark. Team: $79/month or $790/year (2 months free) for 1 app with unlimited users, plus $29/month per additional app. Bu
Not given
Key features
Effects on clips or specific moments
Karaoke captions with word-by-word timing
35 easing curves for text animation
Automatic audio mixing for music and voices
Voice changers including robot, chipmunk and telephone
Smooth transitions between clips
Ready-made text styles for titles and captions
Full customization of colors, fonts and video formats
MP4 export ready to post
On-device rendering with no servers
Pyramid-JiT (P-JiT) architecture with 32×32 token reduction
4× more aggressive token reduction than Linum v2
Converges in 11× fewer samples than Linum v2
2B-parameter model with frozen Qwen text encoder
Pixel-space diffusion with multi-resolution readouts
PixelREPA alignment with DINOv3-L
Curriculum learning over noise schedule
What makes it different
One view integration for iOS, Android, React Native and web with the same implementation
Full customization to match any app's brand and workflow
Complete feature set ready to use without building
On-device processing with no per-export cost or data leaving the device
Low-cost training: full 2B model trained for just $21K in compute
Controls baked into model training rather than post-hoc fine-tuning
Pixel-space compression without separate VAE bottleneck
Apache 2.0 open release with full model weights and code