3D Model Generation
Stable Fast 3DStable Point Aware 3D
Anti-AI Aesthetic Technology
Audio Generation
Stable Audio 2
Authentic Texture Rendering
FLUX.1-Krea Model
12-billion parameter diffusion transformer
Generation Speed After Training
30-90 seconds
Human-like Aesthetic Output
Image Control Features
SketchStructureStyle GuideStyle TransferRecolor
Image Editing
Erase ObjectInpaintOutpaintRemove BackgroundSearch and RecolorSearch and ReplaceReplace Background & Relight
Image Generation
Stable Image UltraStable Image CoreStable Diffusion 3.5 LargeStable Diffusion 3.5 Large TurboStable Diffusion 3.5 MediumStable Diffusion 3.5 FlashSDXL 1.0
Image Size Selection
Square (1:1)Landscape (3:2)Portrait (2:3)
Natural Lighting & Composition
Number of Images per Generation
Preview Features
Stable Point Aware 3DStable Audio 2
Supported Image Types
PortraitsLandscapesArtistic CompositionsCommercial Imagery