Type a topic and turn your photo into a rapper with AI-generated lyrics, vocals, beat and lip sync
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Not given
Paid
Pricing
Not given
$9.90 for 40 credits (two 480p videos), $19.90 for 100 credits (five videos) and $49 for 270 credits (thirteen videos). One 10-second video uses 20 credits at 480p or 48 credits at 720p. Songs cost 5 credits each.
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
Free lyrics preview up to 10 times per day
AI-generated original music and lyrics
Automatic credit refund if video fails
AI-generated label and Content Credentials on videos
Songs available in MP3 and lyrics format
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
Writes original rap lyrics about your topic before generating the video, unlike tools that only animate existing audio
Generates video, vocals, beat and lip sync all together in one pass
Personalized lyrics based on user input rather than generic templates
No subscription, pay only once per video with credits that never expire
Fast results in approximately 8 minutes for a complete video