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
Paid
Open source
Pricing
Free: 3 watermarked previews (1 without account, 2 more after Google sign-in). Starter $4.99 USD for 7 HD portraits. Plus $6.99 USD for 10 HD portraits. Creator $9.99 USD for 20 HD portraits. One-time payments, no subscription.
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
5 traditional dress styles: Xunpu flower crown, Ming horse-face skirt, qipao, Song dynasty hanfu, and tang suit
Face-preserving AI generation keeps your face and skin tone
Automatic variation in pose, expression and background for each portrait
Generates full portrait in about one minute
Before and after image included with each HD portrait pack
Watermark-free HD downloads for paid packs
Fixed menu selections for style, headwear and outfit without free-text prompts
Share directly to TikTok, Instagram or YouTube Shorts from phone
Secure payment processed by Waffo, merchant of record
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
Specialized in traditional Chinese dress styles with cultural detail instead of general portraits
No subscription model; pay once per pack of portraits you want
Photos never used for AI training or sold, deleted within 24 hours
Free previews let you check likeness before paying for HD versions
You own the portraits you create and may use for personal and social media
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
Dynasty Portrait
Illustrious XL