AI Elephant using an image to model workflow

This was a test of a highly modified version of Tencent's new Hunyuan3d image to generated mesh. I modified the connectors and workflow to optimize the model for 3d printing rather than a textured 3d model for animation, or other uses. It works shockingly well, and is pretty smart about removing the main object from a photo. The uploaded model is unedited by me, and is probably pretty obvious it wasn't hand-created. You can see on the trunk there is an extra appendage - a classic issue with AI generation. Even in the photo above, the second tusk isn't in the atomically correct place. This is running on my local machine and is completely open-source. I would upload it here, but there is a limit on the upload size. If you are interested in trying it out, send me a note and I can put it up someplace to download.