Im2Vide0: A Zero-Shot approach using diffusion models for natural language conditioned Image-to-Video.

Constantin Orasan Gabriela Czibula

Published in: ICCP (2023)

Keyphrases

natural language
image data
input image
multiscale
image analysis
image segmentation
diffusion models
video data
social networks
edge detection
video sequences
multiresolution
high resolution
natural images
key frames
diffusion model