Open-source SDXL-based AI model for native high-resolution anime art generation
The female Draco Malfoy fan-made character creator
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
Not given
Pricing model
Open source
Freemium
Pricing
Free for personal and research use; prohibits closed-source proprietary monetization
Free: 1 credit for new accounts. Starter: $9.90 for 120 credits (≈ 120 images at 1K or ≈ 8 ten-second clips). Creator: $29.90 for 400 credits (≈ 400 images at 1K or ≈ 26 ten-second clips). Studio: $79.90 for 1200 credits (≈ 1200 images at 1K or ≈ 80 ten-second clips). Per action: 1K image costs 1 cr
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
Generate AI images from text descriptions, selfies, or sketches
Customizable outfits including school robe, ball gown, Quidditch, and casual wear
Multiple expression options like smirk, tsundere blush, pout, and soft smile
Various art styles including anime, manga ink, chibi, and painterly
Animate images into 5-second or 10-second 9:16 vertical videos
Keep character consistency across multiple scenes and comic panels
Create 4-panel comics and various layouts
Browse library of 175+ fan works including comics, art, videos, and fanfiction
Image resolution options of 1K and 2K
Credits never expire and can be used anytime
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
No subscription model; pay-per-credit with credits that never expire
Free tier available with 1 free credit and no credit card required
Maintains character consistency across multiple images using reference feature
All pricing and credit costs displayed before generation with automatic refunds on failed runs
Curated library of 175+ credited fan works from the community