Edit photos with AI using natural language text prompts
Generative video models for animation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
SG
US
Pricing model
Freemium
Not given
Pricing
Free plan with account creation (no credit card required). Paid subscriptions: Basic $15/month (200 credits/month), Pro $39/month (800 credits/month), Max $160/month (3600 credits/month). Annual billing available with 50% discount. Credit packs available for additional usage.
Not given
Key features
Natural language editing for complex photo changes
Character consistency across up to 5 characters
4K output upscaling
Text rendering in generated images
Multi-image fusion and blending
Background removal tool
Image enhancement and upscaling
Video generation from text and images
6+ AI image models available
10+ AI video models available
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
Workspace designed for production work rather than one-off demos, with consistent outputs and team collaboration
Clear control over prompts, models, and credit usage before generation
Multiple frontier AI models from leading providers in one interface
Professional-grade output supporting 2K/4K resolution and commercial use
Mobile-friendly browser-based editor with no software installation needed
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