Generative models have revolutionized the AI landscape, headlined by popular applications like ChatGPT and Stable Diffusion. According to the NVIDIA Blog, foundational AI models and generative adversarial networks (GANs) have sparked a leap in productivity and creativity.
NVIDIA’s GauGAN, an AI model that transforms rough sketches into photorealistic artwork, exemplifies this revolution. GauGAN powers the NVIDIA Canvas app, which has become a cornerstone for creative professionals worldwide.
How It All BeGAN
GANs are deep learning models involving two complementary neural networks: a generator and a discriminator. The generator creates lifelike imagery, while the discriminator attempts to discern between real and generated images. Through this competitive process, GANs improve their ability to produce realistic samples.
These models excel at understanding complex data patterns and generating high-quality results, finding applications in image synthesis, style transfer, data augmentation, and image-to-image translation.
NVIDIA’s GauGAN, named after post-Impressionist painter Paul Gauguin, is an AI demo for photorealistic image generation. Built by NVIDIA Research, it directly led to the development of the NVIDIA Canvas app. GauGAN has been widely popular since its debut at NVIDIA GTC in 2019, used by art teachers, creative agencies, museums, and millions more online.
Giving Sketch to Scenery a Gogh
Powered by GauGAN and local NVIDIA RTX GPUs, NVIDIA Canvas uses AI to turn simple brushstrokes into realistic landscapes in real time. Users start by sketching lines and shapes with a palette of real-world elements like grass or clouds, referred to as “materials.”
The AI model then generates an enhanced image on the other half of the screen in real time. For instance, triangular shapes sketched using the “mountain” material will appear as a photorealistic mountain range. Users can select the “cloud” material to transform environments from sunny to overcast with a few clicks.
The creative possibilities are endless. Sketch a pond, and other elements like trees and rocks will reflect in the water. Change the material from snow to grass, and the scene shifts from a winter setting to a tropical paradise.
Canvas features a Panorama mode that enables artists to create 360-degree images for use in 3D applications. YouTuber Greenskull AI demonstrated Panorama mode by painting an ocean cove and importing it into Unreal Engine 5.
Canvas offers nine different styles, each with 10 variations and 20 materials to play with. The app is available for download on NVIDIA’s website.
In addition to Canvas, NVIDIA offers other AI-powered content creation apps like NVIDIA Broadcast, which transforms any room into a home studio and is free for RTX GPU owners.
Generative AI is transforming gaming, videoconferencing, and interactive experiences. Stay updated on the latest developments by subscribing to the AI Decoded newsletter.
Image source: Shutterstock
