AI image generator with multi-reference fusion and advanced character consistency
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
Freemium
Freemium
Pricing
Free credits available upon signup. Subscription options include monthly subscriptions with automatic monthly billing and annual subscriptions with up to 50% savings. One-time credit packs available for purchase. Specific plan names and prices not stated on the pages.
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
Text-to-image generation with flux text to image prompts
Image-to-image editing and refinement
Output up to 4MP with flexible aspect ratios
90% text legibility with multilingual typography support
Physics-aware lighting and realistic rendering
Three model variants: Pro, Flex, and Dev
Generation in under 10 seconds
JSON-structured prompts for precise control
FP8 quantization for 40% VRAM savings
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
Eliminates stochastic drift in edits that plague other tools
32-billion parameter rectified flow matching architecture for physics-aware generation
Professional-grade output up to 4MP for print-ready results
90% typography accuracy for multilingual layouts and text rendering
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