Open-source SDXL-based AI model for native high-resolution anime art generation
Turn a single photo into your own AI dance video with reference-based choreography
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
Single: $4.99 (1 video); Five Pack: $19.90 (5 videos at $3.98 per video); Ten Pack: $29.99 (10 videos at $3.00 per video). All packs include 9-10 second videos, choice of 5 dance templates, 12-month validity, and automatic refunds for failed generations.
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
Five reference dance templates with different scenes and choreography
Upload photos in JPG, PNG or WebP format
Video output in MP4 format at 768P resolution
Videos 9-10 seconds in duration
AI-generated audio track included with each video
Automatic refund for failed video generations
30-day download window for finished videos
12-month validity for video credits
Free preview of all reference templates
Support for adults and pets in photos
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
Reference-based generation eliminates need for manual filming or text prompts
Pre-choreographed templates ensure consistent, professional dance sequences
One-time purchase model with no subscription required
Automatic refunds for generation failures
Five distinct visual styles and choreography options