Since audio is processed separately this isn't just close to real. it is real. After all what is video if not a stack of frames! :D
Releasing a model with a magnet link and some ascii art gives me way more confidence in the product than any OpenAI blog post ever could. Excited to play with this once it's somewhat documented on how to get it running…
Since audio is processed separately this isn't just close to real. it is real. After all what is video if not a stack of frames! :D
Releasing a model with a magnet link and some ascii art gives me way more confidence in the product than any OpenAI blog post ever could. Excited to play with this once it's somewhat documented on how to get it running…