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 plan includes 50 credits on sign-up with up to 3 shots per video (~24 seconds) and 480p output. Pro plan: $19.90/month (or from $0.67/day on monthly card, save 64% vs weekly at $1.86/day) with 1,500 credits upfront, supporting up to 37 SD videos or 18 HD videos, up to 3 MVs at once, and 720p ma
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
Reads BPM, mood, energy and structure from audio for synchronized visuals
Supports MP3, WAV, M4A and OGG formats up to 50MB
16:9 landscape for YouTube or 9:16 vertical for TikTok and Reels
720p HD export in H.264 MP4 format watermark-free
Automatic storyboarding, keyframe rendering and motion clip generation
Unlimited shots on paid plans to visualize full songs
Trim to specific chorus or section of track
Credit-based billing: 5 credits per second SD, 10 credits per second HD
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 filming or editing skills required
Music-synced visuals grounded in real audio analysis
Complete AI pipeline from storyboard to final composite
Failed generations cost nothing, only successful completions billed
You own the AI-generated visuals for personal and commercial use
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
SonusVid
Illustrious XL