SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models.
ShanShan ZhongZhongzhan HuangWushao WenJinghui QinLiang LinPublished in: CoRR (2023)
Keyphrases
- pre trained
- language model
- language modeling
- information retrieval
- probabilistic model
- image classification
- image analysis
- speech recognition
- image content
- multiscale
- image features
- training data
- image segmentation
- diffusion models
- input image
- n gram
- control signals
- retrieval model
- query expansion
- high resolution
- image retrieval
- image representation
- semi supervised learning
- lighting conditions
- small number
- edge detection
- supervised learning