3 papers
cs.CV2024
Boosting Camera Motion Control for Video Diffusion Transformers
Soon Yau Cheong, Duygu Ceylan, Armin Mustafa +2
Recent advancements in diffusion models have significantly enhanced the quality of video generation. However, fine-grained control over camera pose remains a challenge. While U-Net…
cs.CV2023
ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet
Soon Yau Cheong, Armin Mustafa, Andrew Gilbert
This paper introduces ViscoNet, a novel one-branch-adapter architecture for concurrent spatial and visual conditioning. Our lightweight model requires trainable parameters and data…
cs.CV2023
UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer
Soon Yau Cheong, Armin Mustafa, Andrew Gilbert
Text-to-image models (T2I) such as StableDiffusion have been used to generate high quality images of people. However, due to the random nature of the generation process, the person…