Presentation / Installation


Attend-and-Excite: Attention-based Semantic Guidance for Text-to-image Diffusion Models
SessionNeural Image Generation and Editing
DescriptionCan a diffusion process be corrected after taking a wrong turn? We present Attend-and-Excite, a novel method that guides a text-to-image diffusion model to attend to all subjects in a text prompt and strengthen — or excite — their activations, encouraging the generation of all subjects in the prompt.
Authors
Hila Chefer
Tel Aviv University
Yuval Alaluf
Tel Aviv University
Yael Vinker
Tel Aviv University
Lior Wolf
Tel Aviv University
Daniel Cohen-Or
Tel Aviv University
Event Type
Technical Paper
TimeThursday, 10 August 20232pm - 2:11pm PDT
LocationPetree Hall D
ACM Digital Library Technical Papers pdfs
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Thursday, 10 August 20232pm - 3:30pm PDTPetree Hall D
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Video
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
Blended Latent Diffusion