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
Free: 1 AI video and 1 hour of video processing per month. Pro from US$19 per month or US$100 per year, scaling from 10 to 100 AI videos and 5 to 50 hours of processing. Local pricing: MX$199 monthly or MX$1,049 yearly in Mexico; R$59 monthly or R$309 yearly in Brazil; €15 monthly or €80 yearly in t
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
AI Agent: generates complete videos from text ideas with script, images, narration, captions and music
AI Clipping: analyzes long videos to find and extract best moments as vertical clips with captions
25 visual styles from cinematic to claymation
Auto captions in multiple languages
Video reframing: automatic aspect ratio conversion following faces and key subjects
Narration in 20 languages with custom voice cloning on Pro
Recurring characters: same face consistent across videos in series
Full browser-based video editor with no software installation
Multi-language translation: redub videos in different languages
Export in multiple aspect ratios: 9:16, 4:5, 1:1 and 16:9
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
No watermark on Pro exports; free plan includes small watermark
Entire video editing in browser with no software to install or learn
Unused credits roll over month to month on Pro plans
AI scores clips by viral potential to help identify best moments
60 free minutes per month for AI clipping without requiring credit card
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