Search form

NVIDIA Canvas Update with New AI Model Released

Latest version of tool, which allows artists to quickly turn simple brushstrokes into realistic landscape images, features powerful new AI model based on GauGAN2 research.

NVIDIA has just announced an update to NVIDIA Canvas, powered by the GauGAN2 AI model and NVIDIA RTX GPU Tensor Cores, that generate backgrounds with increased quality and 4x higher resolution, with five new materials to paint with.

NVIDIA Canvas, the free beta app and part of the NVIDIA Studio suite of creative apps and tools, brings real-time painting tool GauGAN to anyone with an NVIDIA RTX GPU. The program allows artists to use advanced AI to quickly turn simple brushstrokes into realistic landscape images, speeding up concept exploration and freeing more time to visualize ideas.

Updates to NVIDIA Canvas, the launch of Omniverse for individuals and newly announced NVIDIA Studio products, were all announced today at CES. Read the full recap here.

Artwork Made More Easel-y

The NVIDIA Canvas update enables even more realistic images with greater definition and fewer artifacts, adding significant photorealism, all in up to 1K pixel resolution for increased visual quality.

Exports can easily be integrated into existing creative workflows by exporting to Adobe Photoshop or an artist’s preferred creative app.

Artists start in Canvas by sketching simple shapes and lines, then the AI model immediately fills the screen with real-world materials such as water, grass, snow, mountains and more for show-stopping results.

The update adds five new materials to create richer landscape environments: straw, flowers, mud, dirt, and bushes.

These new materials can be further customized with nine preset styles that modify the look and feel of the painting. Artists have the option to upload their own imagery to create a one-of-a-kind background.

You can start painting with AI by downloading the latest NVIDIA Canvas app update here.

Source: NVIDIA

Dan Sarto's picture

Dan Sarto is Publisher and Editor-in-Chief of Animation World Network.

randomness