-
Visual ChatGPT
Visual ChatGPT is a system that integrates different Visual Foundation Models to understand visual information and generation corresponding answers. -
Expanding small-scale datasets with guided imagination
The dataset is used for image generation and editing tasks. -
Non-Hair-FFHQ
The Non-Hair-FFHQ dataset is a high-quality image dataset that contains 6,000 non-hair-FFHQ portraits. -
LazyDiffusion for Interactive Image Generation and Editing
LazyDiffusion is a novel transformer-based encoder-decoder architecture for interactive image generation and editing using a diffusion model.