How are those Ronaldo & Messi AI videos made? Can I do this with my own photos?

Hi everyone, I’ve been seeing a lot of AI-generated videos featuring Cristiano Ronaldo and Lionel Messi - things like them talking, interacting, or being placed in different scenarios - and I’m really curious about how these are actually made. I’m especially interested in understanding the workflow behind it. Are people using Stable Diffusion with extensions, or combining multiple tools (like face swapping, animation, or video generation models)? importantly, I’d like to try something similar using my own local setup and personal photos.