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
PL
Not given
Pricing model
Not given
Open source
Pricing
Free plan: 30 credits (3 videos or 1 AI film clip). Creator: $23/month with 400 credits (40 videos). Pro: $75/month with 2400 credits (240 videos). Credit top-ups: small $19 (300 credits), medium $49 (1000 credits), large $119 (3000 credits). Credits never expire and failed generations are refunded
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
Automatic script generation from sentences or custom scripts
AI scene generation with 19 video engines
Voiceover in 30 languages with word-timed captions
Recurring character rendering with pinned portrait
Automatic series scheduling and publishing
13 visual styles and 6 music styles
Most renders complete in 2 to 5 minutes
Failed generation credits refunded automatically
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
Generate complete vertical videos from a single sentence with no camera or editing required
Same recurring character in every episode for consistent channel branding
Automated series that publish on schedule while you sleep
Credits never expire and failed renders are refunded automatically
Full control with no automatic publishing by default
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