This repository contains code to convert a 2D image generated by a text-to-image diffusion model into a 3D mesh and to animate the mesh.
The process of converting a 2D image into a 3D mesh and animating it involves several steps:
- Image Generation: Using an LLM based diffusion model to generate a 2D image from a text prompt.
- Image to Mesh Conversion: Use a 2D image as input and convert it into a 3D mesh using Meta's Sapiens model.
- Mesh Animation: Animate the 3D mesh by fitting the SMPL-X parametric human body model to the mesh.
