Presentation
Modulating Pretrained Diffusion Models for Multimodal Image Synthesis
SessionDiffusion for Geometry
DescriptionWe introduce the multimodal conditioning module (MCM), a small modulation network that enables multimodal image synthesis using pretrained diffusion models without any updates to the diffusion model parameters.
Event Type
Technical Paper
TimeWednesday, 9 August 20239:42am - 9:52am PDT
LocationRoom 502 AB
Research & Education
Livestreamed
Recorded
Artificial Intelligence/Machine Learning
Modeling
FC
FCS
V
VS
EFC