Create driving poses for magic-animate
This model costs approximately $0.067 to run on Replicate, or 14 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 70 seconds. The predict time for this model varies significantly based on the inputs.
Use DensePose to create driving poses for magic-animate
This model uses the R_50_FPN_s1x (Kirillov et al, 2019) model, on the Detectron2 implementation of DensePose.
It uses the Viridis colormap, and the background is 0 on that colormap, rather than black.
