Open-source SDXL-based AI model for native high-resolution anime art generation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Freemium
Open source
Pricing
Pro from $50/month, Studio from $1,250/month, Enterprise from $2,500/month. Plans include monthly credit allowances for content generation; unused credits refresh monthly and do not stack, with additional pay-as-you-go credits available.
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
Cast characters once with locked face, body and voice across all videos
Art direction with locations, props and house style for consistent rendering
Director workflow for brief, storyboard, shooting and editing
Brand memory system that preserves cast, sets and visual style
Integration with multiple AI models and agents
Support for AI agents including Grok, Claude and ChatGPT
Video editing on single timeline with cuts, motion and captions
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
What makes it different
System of record for production that keeps consistency across AI model outputs
Unified studio system managing casting, art direction, directing and editing
Reuse characters indefinitely across unlimited videos once cast
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
Illustrious XL