AI video generator for creating videos from text prompts or image frames
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Not given
Not given
Pricing
Not given
Basic Yearly: $14.95/month or $179.40/year (30,000 credits, 1080p video); Plus Yearly: $29.95/month or $359.40/year (72,000 credits, 4K video); Pro Yearly: $64.95/month or $779.40/year (180,000 credits, 4K video, unlimited AI image generation). Individual generations cost 160 credits for a 5-second
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
Text-to-video generation from written prompts
Image-to-video with first and last frame guidance
Video duration selection from 5 to 30 seconds
Resolution options: 720p, 1080p, and 4K
Optional generated audio with dialogue and atmosphere
Multiple video models including Kling 4.0, Kling 3.0, and Seedance variants
AI image generation and editing tools
Reference-guided video workflows
Credit-based generation system with plan quotas
Automated content moderation before generation
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
Clear, user-friendly workspace combining input controls, generation options, and result preview
Fair pricing with responsive customer support
Independent platform with no affiliation to ByteDance or model providers
Instant credit availability on annual plans with no per-day limits
Linum