Nvidia researchers have developed a new AI image generation technique that could allow highly customized text-to-image models with a fraction of the storage requirements. According to a paper published on arXiv, the proposed method called “Perfusion” enables adding new visual concepts to an existing model using only 100KB of parameters per concept. As the paper’s […]

The post Nvidia shrinks AI image generation method to size of a WhatsApp message appeared first on CryptoSlate.