This paper introduces ViscoNet, a novel one-branch-adapter architecture for concurrent spatial and visual conditioning. Our lightweight model requires trainable parameters and dataset size multiple orders of magnitude smaller than the current state-of-the-art IP-Adapter. However, our method successfully preserves the generative power of the frozen text-to-image (T2I) backbone. Notably, it excels in addressing mode collapse, a pervasive issue previously overlooked. Our novel architecture demonstrates outstanding capabilities in achieving a harmonious visual-text balance, unlocking unparalleled versatility in various human image generation tasks, including pose re-targeting, virtual try-on, stylization, person re-identification, and textile transfer.Demo and code are available from project page https://soon-yau.github.io/visconet/ .
@article{arxiv.2312.03154,
title = {ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet},
author = {Soon Yau Cheong and Armin Mustafa and Andrew Gilbert},
journal= {arXiv preprint arXiv:2312.03154},
year = {2024}
}