tyFlow 1.111 adds Stable Diffusion in 3DSMax, with its tyDiffusion module “matching simple guide geometry” and “depth” from the 3D scene, to make “detailed” generated images that closely follow the 3D scene. The SD UI being used is ComfyUI. SD 1.5 Models, LORAs and ControlNets are supported.
Interestingly, it appears to be free…
tyDiffusion is available in both the Free and Pro editions of tyFlow, with users of the Free edition getting support for GPU acceleration.
Requires 3ds Max 2018 or higher[tyFlow = “Max 2018”, but tyDiffusion = “Max 2023+”].
Yup, and on an open 435Mb download.
Theoretically then, one could take a Poser scene to Vue, then to Max, then ‘render’ it with AI. Though you can do something similar manually, rendering line-art and a depth map from a Poser scene and using them in ControlNet slots. Unless tyDiffusion is extracting some extra ‘secret sauce’ from the 3D scene, such as PoseNet poses from figures, or light maps for scene lighting.
However, I’m still hoping Renderosity has the sense to save Poser, by making a similar free and robust SD ‘rendering’ plugin for Poser 12 through 14.