5 datasets found

A text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion.

Diffusion models for image synthesis

LADI-VTON: Latent diffusion textual-inversion enhanced model for virtual try-on

Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing

FashionSD-X: Multimodal Fashion Garment Synthesis using Latent Diffusion