I guess it uses LCM - Latent Consistency Models and Img2Img for making this possible, Not very sure about the potential face swap. But this super impressive! 🔗 Links 🔗 Try it out yourself https://www.fal.ai/camera Fal AI - https://www.fal.ai/ ❤️ If you want to support the channel ❤️ Support here: Patreon - https://www.patreon.com/1littlecoder/ Ko-Fi - https://ko-fi.com/1littlecoder 🧭 Follow me on 🧭 Twitter - https://twitter.com/1littlecoder Linkedin - https://www.linkedin.com/in/amrrs/