AI short video generator for scripts, storyboards, and social content
Upload one photo and get a 12-second Window Dance video in minutes
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Paid
Pricing
Starter: $29.90/month with 3,000 credits; Creator: $59.90/month with 7,500 credits; Studio: $119.90/month with 16,500 credits. Add-on credit packs available with non-expiring credits.
Single: $9.99 for 1 video. Trio: $19.99 for 3 videos ($6.66 each). One-time payment, no subscription. Credits never expire. Unused credits refundable within 7 days.
Key features
Multiple AI video and image models in one platform
Script-to-storyboard breakdown with character and scene analysis
Support for text, image, and reference-based video generation
Character consistency tools across shots
Canvas workspace for organizing scripts, characters, and assets
Access to 12 video models including Seedance, Kling, and Veo
Shot rhythm and motion control settings
Free trial credits for new users
Credit refunds for failed generations
Free photo check before payment to verify photo quality
Generate videos in browser without app or account
12-second vertical 720p MP4 with original AI-generated beat
Pet detection and generation for dogs and cats
Video delivery by email within 3–5 minutes
Full scene regenerated around your photo
QR code upload from phone to computer
Failed generations automatically refund credit
What makes it different
Combines 12 video and 10 image models in a single unified interface
Script-to-storyboard workflow with automatic story analysis
Keep generated assets, characters, and references in one project canvas
Maintain character consistency across multiple project shots
One credit balance for both video and image generation
No CapCut template needed; full scene generated instead of face-swap
Works with pets, which CapCut templates cannot do
Pay per video with no subscription or account required
Videos preserve your face, hair and outfit from the photo
Private by default; photos and videos not used to train AI models