Open-source SDXL-based AI model for native high-resolution anime art generation
AI rendering workspace for architects that works from a sketch, model view or photo
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
5 free renders with no card required. Paid plans: Essential $19/month for 40 credits, Premium $29/month for 100 credits, Pro $79/month for 300 credits. One-time credit pack: $99 once for 300 credits that never expire. Annual billing available at discount: $190/year, $290/year, $790/year respectively
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
Upload sketches, model views or site photos to start rendering
Select specific areas with brush, lasso or polygon to edit
Attach reference images to communicate materials and style
Keep all versions and compare directions in one project
Create review links with expiry and comment collection
Upscale images 2× for presentations
Generate short videos from still images
Export comparison boards and image bundles
No plugin installation or GPU required
Works with exported views from SketchUp, Revit, Rhino, Archicad and Blender
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 plugin or GPU needed – works entirely in the browser from image uploads
Keep every version as you iterate – all results stored together for comparison
Works from sketches, model views and photos – not native CAD or BIM files