InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following.

Shufan Li Harkanwar Singh Aditya Grover

Published in: CoRR (2023)

Keyphrases

multimodal information
visual information
cross modal
database
multimedia
multi modal
lightweight
real time
visual cues
visual perception
multimodal interaction
high level
hidden markov models
visual features
audio visual