AI video generator that turns text, images, video clips, and audio into finished videos
Generative video models for animation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
SI
US
Pricing model
Freemium
Not given
Pricing
Lite: $14.9/month (50% off, was $29.9) - 600 credits/month at $0.025 per credit; Standard: $39.9/month (50% off, was $79.9) - 2,500 credits/month at $0.016 per credit with 30% off Seedance models; Max: $99.9/month (50% off, was $199.9) - 8,000 credits/month at $0.012 per credit with 30% off Seedance
Not given
Key features
Multi-material input combining images, video clips, and audio
Consistent character and product appearance across shots
Precise editing of individual elements without full regeneration
Text-to-video generation
Image-to-video generation
Audio generation and integration on supported models
Multiple visual styles and aesthetic options
Video size and format selection
1080p and 4K video quality options
Video upscaler and image upscaler tools
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
Keep faces and products the same while editing any part without starting over
No filming or professional equipment needed
Simple three-step process from idea to finished video
Transparent credit costs shown before generation
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
https://seedance3.si/
Linum