Presentation
Text2Human: Text-driven Controllable Human Image Generation
SessionTechnical Papers
Event Type
Technical Paper
Research & Education
Virtual
Full Conference Supporter
Full Conference
Virtual Conference Supporter
Virtual Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
Time
Location
DescriptionIn this work, we present a text-driven controllable framework, Text2Human, for a high-quality and diverse human generation. We synthesize full-body human images from a given human pose and some texts describing the shapes and textures of clothes.
