NVIDIA Research's GauGAN AI Art Demo Responds to Words:
A picture worth a thousand words now takes just three or four words to create, thanks to GauGAN2, the latest version of NVIDIA Research's wildly popular AI painting demo.
The deep learning model behind GauGAN allows anyone to channel their imagination into photorealistic masterpieces — and it's easier than ever. Simply type a phrase like "sunset at a beach" and AI generates the scene in real time. Add an additional adjective like "sunset at a rocky beach," or swap "sunset" to "afternoon" or "rainy day" and the model, based on generative adversarial networks, instantly modifies the picture.
With the press of a button, users can generate a segmentation map, a high-level outline that shows the location of objects in the scene. From there, they can switch to drawing, tweaking the scene with rough sketches using labels like sky, tree, rock and river, allowing the smart paintbrush to incorporate these doodles into stunning images.
The new GauGAN2 text-to-image feature can now be experienced on NVIDIA AI Demos, where visitors to the site can experience AI through the latest demos from NVIDIA Research. With the versatility of text prompts and sketches, GauGAN2 lets users create and customize scenes more quickly and with finer control.
Direct link to YouTube video.
Kinda makes Turtle graphics from the 70s look rather basic. However, beware Rule 34…
Related Stories
US firm Getty Images on Tuesday threatened to sue a tech company it accuses of illegally copying millions of photos for use in an artificial intelligence (AI) art tool:
Getty, which distributes stock images and news photos including those of AFP, accused Stability AI of profiting from its pictures and those of its partners. Stability AI runs a tool called Stable Diffusion that allows users to generate mash-up images from a few words of text, but the firm uses material it scrapes from the web often without permission.
The question of copyright is still in dispute, with creators and artists arguing that the tools infringe their intellectual property and AI firms claiming they are protected under "fair use" rules.
Tools like Stable Diffusion and Dall-E 2 exploded in popularity last year, quickly becoming a global sensation with absurd images in the style of famous artists flooding social media.
Related:
- Adobe Stock Begins Selling AI-Generated Artwork
- Pixel Art Comes to Life: Fan Upgrades Classic MS-DOS Games With AI
- NVIDIA Research's GauGAN AI Art Demo Responds to Words
- Alien Dreams: An Emerging Art Scene
On Wednesday, Meta announced an AI model called the Segment Anything Model (SAM) that can identify individual objects in images and videos, even those not encountered during training, reports Reuters.
According to a blog post from Meta, SAM is an image segmentation model that can respond to text prompts or user clicks to isolate specific objects within an image. Image segmentation is a process in computer vision that involves dividing an image into multiple segments or regions, each representing a specific object or area of interest.
The purpose of image segmentation is to make an image easier to analyze or process. Meta also sees the technology as being useful for understanding webpage content, augmented reality applications, image editing, and aiding scientific study by automatically localizing animals or objects to track on video.
Related:
MIT's Computer Vision (CV) Algorithm Identifies Images Down to the Pixel (20220424)
NVIDIA Research's GauGAN AI Art Demo Responds to Words (20211130)
Ask Soylent: Beginning in Artificial Intelligence Methods (20150629)
(Score: -1, Flamebait) by Anonymous Coward on Tuesday November 30 2021, @11:26PM (1 child)
"Trump eaten by pigs"
(Score: 2) by DannyB on Wednesday December 01 2021, @07:31PM
Pigs don't usually eat their own kind. Googling shows that some sows will occasionally eat their offspring. That does not appear to have happened in this particular case.
The Centauri traded Earth jump gate technology in exchange for our superior hair mousse formulas.
(Score: 3, Informative) by bzipitidoo on Tuesday November 30 2021, @11:29PM (1 child)
I suppose I was too hasty. Clicked through the so-called tutorial, entered some text, and got a blank cyan image. Fiddled around a bit. Their site kept insisting I agree to some terms, over and over. Maybe I'll take the magic 8-ball's advice and try again later.
(Score: 4, Informative) by VanessaE on Wednesday December 01 2021, @12:07AM
Note that their page layout is incompatible with small windows. There's more off to the right of that cyan area (I had to reduce my page scale to 50% to fit it all in).
That aside, I tried a few simple phrases, but all it kept producing was an image of a galaxy of some sort, with varying degrees of distortion. The I turned off the "segmentation" checkbox at the upper left next to "input visualization", and ticked the "text" box right of that. THEN it started producing stuff that sometimes, vaguely resembled what I asked for.