.

Recent Comments

    generative adversarial network tagged posts

    AI Generates High-Quality Images 30 times faster in a Single Step

    March 22, 2024, Categories  Physics

    Three by two grid of AI-generated images, with small black illustrated robots peeking from behind. The images show a scenic mountain range; a unicorn in a forest; a vintage Porsche; an astronaut riding a camel in a desert; a sloth holding a cup, dressed in a turtleneck sweater; and a red fox in a spacesuit against a starry background.
    Caption: With their DMD method, MIT researchers created a one-step AI image generator that achieves image quality comparable to StableDiffusion v1.5 while being 30 times faster.
    Credits:Illustration by Alex Shipps/MIT CSAIL using six AI-generated images develped by researchers.

    In our current age of artificial intelligence, computers can generate their own “art” by way of diffusion models, iteratively adding structure to a noisy initial state until a clear image or video emerges.

    Diffusion models have suddenly grabbed a seat at everyone’s table: Enter a few words and experience instantaneous, dopamine-spiking dreamscapes at the intersection of reality and fantasy...

    Read More

    AI behind Deepfakes may Power Materials Design Innovations

    November 10, 2021, Categories  Physics

    This image depicts a generative adversarial network creating new alloy compositions
    The Generator network (G) uses statistical distributions learned from prior observations to imagine new materials with specific properties. Credit: Wesley Reinhart. All Rights Reserved.

    The person staring back from the computer screen may not actually exist, thanks to artificial intelligence (AI) capable of generating convincing but ultimately fake images of human faces. Now this same technology may power the next wave of innovations in materials design, according to Penn State scientists.

    “We hear a lot about deepfakes in the news today – AI that can generate realistic images of human faces that don’t correspond to real people,” said Wesley Reinhart, assistant professor of materials science and engineering and Institute for Computational and Data Sciences faculty co-hire, at Penn S...

    Read More