Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis.
Qiucheng WuYujian LiuHandong ZhaoTrung BuiZhe LinYang ZhangShiyu ChangPublished in: CoRR (2023)
Keyphrases
- image synthesis
- spatial temporal
- high fidelity
- diffusion models
- computer graphics
- information diffusion
- real time
- action recognition
- diffusion model
- spatio temporal
- temporal information
- spatial and temporal
- social networks
- high quality
- text mining
- information retrieval
- keywords
- text documents
- spatial information
- high resolution
- video shots
- semantic information
- virtual environment
- viral marketing