German neuroscientist Fabian Stelzer is in the process of making a 1970s-style science fiction film called ‘Salt’ using only generative AI art tools like DALL-E 2, Stable Diffusion and Midjourney. Apart from his own, a tool called Murf produces all the voices you hear. With the aim of creating a “community cut”, Fabian has told […]
London’s Framestore is famous for so convincingly putting Sandra Bullock into space and settling a marmalade-loving bear in London. More recently, for an equestrian action sequences in Season 4 of The Crown, their VFX wizards have now turned their hand to replacing the face of a skilled equestrian with that of Erin Doherty, who plays […]
A group of academics at CVIT (Center for Visual Information Technology) in Hyderabad, India has successfully mastered the process of accurately lip-sync’ing dynamic, unconstrained talking face videos, using Generative Adversarial Networks (GANs). As you will see in the demo video, this includes matching a live language translation to an original video spoken in a native […]
Five university researchers from Hong Kong and China have created an application called DeepFaceDrawing which “allows users with little training in drawing to produce high-quality images from rough or even incomplete freehand sketches”. Abstract of the team’s academic paper Recent deep image-to-image translation techniques allow fast generation of face images from freehand sketches. However, existing solutions tend […]
AI artist Mario Klingemann has used GANs (Generative Adversarial Networks) and specifically NVIDIA’s StyleGAN2 to create NeuralFace, a deepfake video that morphs a collection of artificially generated faces pulling a range of increasingly unsettling expressions in sync to Kraftamt’s 2014 track “Triggernometry”. The results are fairly disturbing and the bets are open on whose next edgy promo […]
At the World Economic Forum in Davos in January, Pinscreen demonstrated a new real-time, photo-realistic face synthesis technology. While primarily intended as a tool for creating next-gen virtual assistants and fashion avatars, it will be of great interest to VFX companies, as it enables them to create photo-real humans quickly and efficiently and at scale. […]