Open-source SDXL-based AI model for native high-resolution anime art generation
Turn one photo into a 5-second AI dance video
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Open source
Paid
Pricing
Free for personal and research use; prohibits closed-source proprietary monetization
$9.90 for 50 credits (about 5 videos), $19.90 for 105 credits (about 10 videos), $49.00 for 270 credits (about 27 videos). Each video costs 10-50 credits depending on the effect. No subscription, paid once.
Key features
Native 1536x1536 high-resolution generation without upscaling
Hybrid Prompting System combining natural English and Danbooru tags
Stable text encoder fine-tuning for superior concept understanding
Trained on comprehensive Danbooru2023 dataset
Full compatibility with ComfyUI, Automatic1111, Forge, and Draw Things
Superior anatomy rendering with flawless hands and character details
V-Prediction architecture for enhanced dynamic range and contrast
Highly flexible base canvas for LoRA training and custom checkpoints
Choose from four dance styles: hip-hop, groove, freestyle, or sway
Generate videos in your web browser without installing an app
Get results in about 3 minutes
5-second vertical MP4 videos optimized for TikTok and Instagram Reels
AI checks photos before processing to ensure compliance with content policy
Automatic credit refund if video generation fails
Other effects including AI Kiss, AI Hug, AI Cat Dance, and holiday themes
Videos come silent to pair with any trending audio
What makes it different
Only open-source SDXL model natively trained at 1536x1536 resolution
Stylistically neutral untuned base canvas unlike Pony Diffusion
Continuous rapid iterations from v0.1 to v3.5 with aggressive optimization
Thousands of compatible community-trained LoRAs and derivatives
Uses a real dancer as reference instead of guessing motion, making results look like actual dancing rather than wobbling
No subscription or app required, works entirely in browser
Pay once per video with automatic refunds on failed generations
Private videos never used for training or examples