Composing Visual Relations with Composable Diffusion Models
Humans are able to build complex representations of our world – representing the world as compositional combinations of both objects and their interdependent relations. Recent work in text-guided diffusion models have produced impressive results in generating photorealistic images, but such models o...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2023
|
| Online Access: | https://hdl.handle.net/1721.1/151470 |