ComfyUI Workflow
you can quickly navigate in the workflow with the num keys 1-5
reduced to a minimum (compared to the older flows) for artistic but also realistic vid2vid creations.
Description
based on the scarface workflow v0.9 with some updates. squeezed into the layout of v2.
Changes v2 -> v3
rework of background replacement (interpolates frames of too short videos, color match of bg/fg, fg/bg, switch of both as side effect)
added scale by factor (image settings)
added latents group to either work with the input images (vae encode) or empty latents
reworked mask area
added aio blend (combines lineart+hed in its current state, can be used with lineart or softedge models)
added wd14 auto prompt
rework of animatediff group
added a cleanup to free memory
removed hires-fix, added a 2nd sampler (upscale)
reworked/merged filter groups