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
Not given
Not given
Pricing model
Freemium
Open source
Pricing
Creator $10/month (250 Credits/month or $120/year for 3,000 Credits/year); Pro $20/month (550 Credits/month or $240/year for 6,600 Credits/year); Studio $40/month (1,200 Credits/month or $480/year for 14,400 Credits/year). Credit packs: Starter Credits $20 (200 permanent Credits at $0.10 per Credit)
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
Text or image character reference input (PNG, JPEG, or WebP)
Open-ended animation descriptions in plain language
Frame-by-frame preview with timing adjustment
Natural language animation adjustment
Transparent sprite sheet export
Animation metadata and engine guidance
GIF preview export
Commercial use rights included
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
Keep one character as reference context to maintain consistency across multiple animations
Open-ended descriptions instead of preset animations
Adjust completed animations with plain language instructions
Credits consumed only for completed usable assets, not for planning or testing
Export includes Godot and Unity engine guidance
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