Open-source SDXL-based AI model for native high-resolution anime art generation
Identify any shoe or bag from a photo: brand, model and colorway
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: one identification per day without account, or three per day with free account plus one resale listing. Seller Pass: $4.99 (one-time payment) for 20 listings and 30 days of unlimited identifications.
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
Identify sneakers, shoes, boots, heels, flats, sandals and loafers from photos
Identify handbags, totes, purses and backpacks from photos
Brand, model and colorway identification with confidence score
Close candidates shown when photo is not conclusive
Shopping, resale and look-alike links
No sign-up required for basic use
Ready-to-post resale listings with free account
Photo metadata removal before upload
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
Won't guess: shows candidates instead when details aren't visible
Does not judge authenticity—only identifies the design
Photos are not stored or used for training
89% shoes and 95% bags correctly named in blind tests
Illustrious XL
What Shoes Are These?