Open-source SDXL-based AI model for native high-resolution anime art generation
Turn text into realistic voiceovers in minutes
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
VN
Pricing model
Open source
Freemium
Pricing
Free for personal and research use; prohibits closed-source proprietary monetization
Free plan with 10,000 credits/month; Creator plan $4/month (billed $49 annually) with 500,000 credits/month; Pro plan $9/month (billed $99 annually) with 2,000,000 credits/month; Team plan $8.33/seat/month (billed $100 annually per seat) with 2,000,000 credits/seat/month. Extra credits available at
Key features
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
200+ AI voices in 150+ languages and accents
Long script and document import with automatic segmentation
AI voice cloning with permission
Customizable voice settings including pitch and pace
Downloadable voiceover audio
Celebrity and character-style voices for entertainment
Text to speech API access
What makes it different
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
Handles long scripts and full documents with automatic segmentation unlike basic text-to-speech demos
Realistic AI voice cloning that sounds remarkably human-like
Create voiceovers once, download, and reuse across multiple projects unlike platform-limited tools
Import and edit long scripts in blocks without pasting text repeatedly
Consistent voice cloning for recurring narration and branded content
Illustrious XL
Lazybird