AI creative suite for generating videos and images from text prompts and visual references
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Not given
Paid
Pricing
Not given
Basic: $10 one-time for 1,000 credits ($0.0100 per credit). Major: $30 one-time for 3,500 credits ($0.0086 per credit). Profession: $99 one-time for 14,000 credits ($0.0071 per credit). Credits never expire and are shared across all connected image and video models.
Key features
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
AI image generation from text prompts
AI video generation from text or images
Reference-led image and video creation with upload control
Multiple AI model options including Seedance, Gemini, and Grok
Model-specific output settings and controls
AI Video Extender to generate footage before or after existing video
AI Clothes Changer to modify clothing in photos
One-time credit purchases with no expiration
Unified library to organize and manage all creations
Six-month retention of generated works in My Creations
What makes it different
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
No subscription required; credits never expire
One shared credit balance works across all connected image and video tools
Estimated cost shown before generation begins
Support for both text-to-media and image-to-media workflows
Linum
ZMS AI