Open-source SDXL-based AI model for native high-resolution anime art generation
AI motion capture from video without suits or markers
Stage
Not given
Established
Founded
Not given
2014
Based in
Not given
DK
Pricing model
Open source
Freemium
Pricing
Free for personal and research use; prohibits closed-source proprietary monetization
Free plan: 30 seconds/month of Vision AI processing. Basic plan (annual): $10/month with 600 seconds/month of Vision AI processing. Basic plan (monthly): $12/month with 600 seconds/month of Vision AI processing. Plus plan (annual): $20/month with 3000 seconds/month of Vision AI processing. Plus plan
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
Convert video to 3D motion data without suits or markers
Rebuilt AI solver for cleaner motion data
Export to FBX and BVH formats
Compatible with major 3D software and skeletons
Edit and clean motion data in Rokoko Studio
Integrated with Rokoko Create platform
Character retargeting support
Cloud storage for projects
Smoothing filters and loop segments
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
Up to 4x more AI processing per dollar than competitors at the same price point
Complete motion creation platform with Video-to-Motion and Text-to-Motion in one ecosystem
Illustrious XL
Rokoko Vision