I've ran hunyuanvideoai from their GitHub and it seems to generate realistic videos. It is a bit slow (30-60min per video clip) and requires ~50GB VRAM. I wonder how the quality compares though?
HunYuan is all everybody on Banodoco and the broader comfy ecosystem are talking about. And that's with Lightricks' LTX model having just been announced too.
HunYuan is seriously amazing and it looks like it'll be the Flux/Stable Diffusion of AI video.