Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis
Author:
Wu Qiucheng1,
Liu Yujian1,
Zhao Handong2,
Bui Trung2,
Lin Zhe2,
Zhang Yang3,
Chang Shiyu1
Affiliation:
1. UC Santa Barbara
2. Adobe Research
3. MIT-IBM Watson AI Lab
Reference58 articles.
1. ediffi: Text-to-image diffusion models with an ensemble of expert denoisers;Balaji,2022
2. End-to-End Object Detection with Transformers