-
LASPA: Latent Spatial Alignment for Fast Training-free Single Image Editing
A novel framework for single-image editing using pre-trained text-to-image diffusion models. -
InstantID: Zero-shot Identity-Preserving Generation in Seconds
InstantID is a zero-shot identity-preserving generation method for pre-trained text-to-image diffusion models. -
De-Fake: Detection and Attribution of Fake Images Generated by Text-to-Image ...
The De-Fake dataset is a detection and attribution of fake images generated by text-to-image diffusion models. -
Sketch-Guided Scene Image Generation
Scene image generation from scene sketches using text-to-image diffusion models -
Video Colorization with Pre-trained Text-to-Image Diffusion Models
Video colorization is a challenging task that involves inferring plausible and temporally consistent colors for grayscale frames. -
VGDiffZero: Text-to-Image Diffusion Models Can Be Zero-Shot Visual Grounders
VGDiffZero is a zero-shot visual grounding framework that leverages pre-trained text-to-image diffusion models' vision-language alignment abilities. -
Text2video-zero: Text-to-image diffusion models are zero-shot video generators
Text2video-zero: Text-to-image diffusion models are zero-shot video generators. -
Ablating Concepts in Text-to-Image Diffusion Models
Large-scale text-to-image diffusion models can gener-ate high-fidelity images with powerful compositional ability. However, these models are typically trained on an enormous...
