18347366. CUSTOMIZING GENERATION OF OBJECTS USING DIFFUSION MODELS (Lemon Inc.)
Jump to navigation
Jump to search
Contents
CUSTOMIZING GENERATION OF OBJECTS USING DIFFUSION MODELS
Organization Name
Inventor(s)
Jun Hao Liew of Singapore (SG)
CUSTOMIZING GENERATION OF OBJECTS USING DIFFUSION MODELS
This abstract first appeared for US patent application 18347366 titled 'CUSTOMIZING GENERATION OF OBJECTS USING DIFFUSION MODELS
Original Abstract Submitted
Methods of customizing generation of objects using diffusion models are provided. One or more parameters (e.g., a conditioning signal, network weights, or an initial or starting noise) of the diffusion model can be optimized by a backpropagation process, which can be performed by solving an augmented adjoint ordinary differential equation (ODE) based on an adjoint sensitivity method. The customized diffusion model can generate stylized objects, generate objects with specific visual effect(s), and provide adversary examples to audit security of an object generation system.
