44 datasets found

LazyDiffusion is a novel transformer-based encoder-decoder architecture for interactive image generation and editing using a diffusion model.

PIE-Bench++ is a dataset for multi-aspect image editing. It contains 700 images with detailed text prompts and tailored to facilitate simultaneous edits across multiple image...

The dataset used for image editing and scene editing tasks.

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...