Microsoft’s new VALL-E “neural codec language model” can closely simulate a person’s voice when given just a three-second audio sample, and once it learns a specific voice, it can synthesise audio of that person saying anything, including with the right emotional tone. Pair VALL-E with another generative AI models such as GPT-3 and you have a content […]
NEWS
Make your own “super trippy” generative animations
If you would like to have a go at making some “super trippy” animations using generative AI tools you have come to the right place. Writing on Linkedin, Head of Immersive at design agency Seymour Powell, Chris Doughty has provided us all with a handy set of instructions. Download and install Python 3.10.6 – https://lnkd.in/eWH67UVv Download and […]
AI is not coming to steal your lunch
Though people who know how to get the best out of leading edge, state-of-the-art machine learning technology would like to join you for snacks The arrival in our midst of synthetic media generated from text prompts has caused disquiet. Individuals are concerned that their skills, knowledge and experience are under threat like never before. However, […]
NVIDIA Omniverse updates announced
NVIDIA has updated its AI-assisted reel-time collaboration and simulation platform Omniverse, announcing at a virtual event to coincide with CES in Las Vegas that it now supports generative AI and Unity’s game engine. Performance and usability have both been improved and new connectors have been added to expand the Omniverse ecosystem. Omniverse customers include Dentsu, Mercedes […]
Point-E seizes the Text-To-3D baton for OpenAI
The highly-valued startup behind popular text-to-image generator Dall-E, OpenAI ,has announced the release of Point-E, which can produce 3D point clouds directly from text prompts in a minute or two using a computer with a sufficiently powerful GPU. How is it done? “To produce a 3D object from a text prompt, we first sample an image […]
How Disney’s multiplane camera worked
In February 1957 Walt Disney recorded this video in which he talks about how the company made and used multi-plane cameras to create image segmentation in 2.5 dimensions and give depth to animated feature films. Here’s the Wikipedia explanation for how the technology worked. The multiplane camera is a motion-picture camera that was used in the traditional animation process that moves a […]