contemporary dance footage vs. stylized / Stable Diffusion/ControlNet/OpenPose
This generative animation study show two example renderings, using a pretty straightforward data pipeline from raw casual video footage of contemporary dance body motion through a Stable Diffusion / A1111 / ControlNet / OpenPose setup. In addition, the generative setup comes with stylized offset of a contemporary acrylic painting and and traditonal japanese woodcut.
On additional feature is the static vs. moving camera in the raw footage. Check the details on this difference in the generated results :)