July 18, 2024
1 Solar System Way, Planet Earth, USA

Deciphering how the generative AI revolution began

Editor's note: This post is part of the AI Decoded Serieswhich demystifies AI by making the technology more accessible and showcases new hardware, software, tools, and accelerations for RTX PC users.

Generative models have completely transformed the AI ​​landscape, led by popular applications such as ChatGPT and Stable Diffusion.

What paved the way for this boom were fundamental AI models and generative adversarial networks (GANs), which brought about a leap in productivity and creativity.

from NVIDIA GauGANthat feeds the NVIDIA Canvas Appis one of those models that uses AI to transform sketches into photorealistic works of art.

How it all began

GANs are deep learning models that involve two complementary neural networks: a generator and a discriminator.

These neural networks compete with each other. The generator tries to create realistic, believable images, while the discriminator tries to distinguish between what is real and what is generated. As their neural networks challenge each other, GANs get better and better at creating realistic-looking samples.

GANs are great at understanding complex data patterns and creating high-quality results. They are used in applications including image synthesis, style transfer, data augmentation, and image-to-image translation.

NVIDIA GauGAN, named after post-impressionist painter Paul Gauguin, is an AI demonstration for photorealistic image generation. Developed by NVIDIA Research, it directly led to the development of the NVIDIA Canvas app, and can be tried for free through NVIDIA. NVIDIA AI Playground.

GauGAN has been wildly popular since its debut on NVIDIA GTC in 2019—used by art educators, creative agencies, museums, and millions more online.

Giving a Gogh touch to the landscape

Powered by GauGAN and local NVIDIA RTX GPUNVIDIA Canvas uses AI to turn simple brush strokes into realistic landscapes and display the results in real time.

Users can start by drawing simple lines and shapes using a palette of real-world elements, such as grass or clouds, referred to in the app as “materials.”

The AI ​​model then generates the enhanced image on the other half of the screen in real time. For example, a few triangular shapes drawn with the “mountain” material will appear as a stunning photorealistic array. Or users can select the “cloud” material and with a few mouse clicks transform environments from sunny to cloudy.

The creative possibilities are endless: draw a pond and other elements of the image, such as trees and rocks, will be reflected in the water. Change the material from snow to grass and the scene will go from a cozy winter setting to a tropical paradise.

Canvas offers nine different styles, each with 10 variations and 20 materials to play with.

Canvas features a panoramic mode that allows artists to create 360-degree images for use in 3D applications. YouTuber Greenskull Artificial Intelligence Panorama mode was demonstrated by painting an ocean cove, before importing it into Unreal Engine 5.

Discharge the NVIDIA Canvas app to get started.

Consider exploring NVIDIA Streaminganother AI-powered content creation app that transforms any room into a home studio. Broadcast is free for RTX GPU owners.

Generative AI is transforming gaming, video conferencing, and interactive experiences of all kinds. Find out what's new and coming by subscribing to the AI Decoded Newsletter.

    Leave feedback about this

    • Quality
    • Price
    • Service


    Add Field


    Add Field
    Choose Image
    Choose Video