A new open source AI image generator capable of producing realistic pictures from any text prompt has seen stunningly swift uptake in its first week. Stability AI’s Stable Diffusion, high fidelity but capable of being run on off-the-shelf consumer hardware, is now in use by art generator services like Artbreeder, Pixelz.ai and more. But the model’s unfiltered nature means not all the use has been completely above board.
For the most part, the use cases have been above board. For example, NovelAI has been experimenting with Stable Diffusion to produce art that can accompany the AI-generated stories created by users on its platform. Midjourney has launched a beta that taps Stable Diffusion for greater photorealism.
But Stable Diffusion has also been used for less savory purposes. On the infamous discussion board 4chan, where the model leaked early, several threads are dedicated to AI-generated art of nude celebrities and other forms of generated pornography. Read More
Monthly Archives: August 2022
Self-Taught AI Shows Similarities to How the Brain Works
Self-supervised learning allows a neural network to figure out for itself what matters. The process might be what makes our own brains so successful.
For a decade now, many of the most impressive artificial intelligence systems have been taught using a huge inventory of labeled data. An image might be labeled “tabby cat” or “tiger cat,” for example, to “train” an artificial neural network to correctly distinguish a tabby from a tiger. The strategy has been both spectacularly successful and woefully deficient.
Such “supervised” training requires data laboriously labeled by humans, and the neural networks often take shortcuts, learning to associate the labels with minimal and sometimes superficial information. For example, a neural network might use the presence of grass to recognize a photo of a cow, because cows are typically photographed in fields.
“We are raising a generation of algorithms that are like undergrads [who] didn’t come to class the whole semester and then the night before the final, they’re cramming,” said Alexei Efros, a computer scientist at the University of California, Berkeley. “They don’t really learn the material, but they do well on the test.” Read More
Transframer: Arbitrary Frame Prediction with Generative Models
We present a general-purpose framework for image modelling and vision tasks based on probabilistic frame prediction. Our approach unifies a broad range of tasks, from image segmentation, to novel view synthesis and video interpolation. We pair this framework with an architecture we term Transframer, which uses U-Net and Transformer components to condition on annotated context frames, and outputs sequences of sparse, compressed image features. Transframer is the state-of-the-art on a variety of video generation benchmarks, is competitive with the strongest models on few-shot view synthesis, and can generate coherent 30 second videos from a single image without any explicit geometric information. A single generalist Transframer simultaneously produces promising results on 8 tasks, including semantic segmentation, image classification and optical flow prediction with no task-specific architectural components, demonstrating that multi-task computer vision can be tackled using probabilistic image models. Our approach can in principle be applied to a wide range of applications that require learning the conditional structure of annotated image-formatted data Read More
#big7, #image-recognitionGoogle’s New Robot Learned to Take Orders by Scraping the Web
LATE LAST WEEK, Google research scientist Fei Xia sat in the center of a bright, open-plan kitchen and typed a command into a laptop connected to a one-armed, wheeled robot resembling a large floor lamp. “I’m hungry,” he wrote. The robot promptly zoomed over to a nearby countertop, gingerly picked up a bag of multigrain chips with a large plastic pincer, and wheeled over to Xia to offer up a snack.
The most impressive thing about that demonstration, held in Google’s robotics lab in Mountain View, California, was that no human coder had programmed the robot to understand what to do in response to Xia’s command. Its control software had learned how to translate a spoken phrase into a sequence of physical actions using millions of pages of text scraped from the web.
That means a person doesn’t have to use specific preapproved wording to issue commands, Read More
Upcoming AI image generator will run on an RTX 3080
An announcement from Stability.ai comes with some great news for anyone on the AI image generation hype. Stable Diffusion, an image generation software that uses consumer level hardware, will soon be going public. Read More
#image-recognitionFighting AI with AI: The Battle against Deepfakes
NEARLY A DECADE AGO, Ian Goodfellow, then a PhD candidate at Université de Montréal, was drinking with friends at the 3 Brasseurs in Montreal’s downtown when he conceived an idea that would change machine learning—and the world of disinformation—forever.
“I don’t want to be someone who goes around promoting alcohol for the purposes of science, but in this case, I do actually think that drinking helped a little bit,” said Goodfellow in his appearance on the Lex Fridman Podcast. If the idea came to him at lunchtime rather than over a beer in the evening, he added, he might have been able to talk himself out of it. Instead, he went home and started working on the project.
Goodfellow suspected that pitting two computer systems against each other—called generative adversarial networks, or GANs—would yield more realistic outputs than the deep-learning machines that existed at the time, which would often generate blurry images of people, usually with missing facial features, did. His early model was able to create numbers that looked hand drawn, human-like faces, and photos of animals that resembled something out of a pixelated Monet painting, but as the technology evolved, it became possible to create strikingly realistic forgeries using a much less involved process. Read More
You can (sort of) generate art like Dall-E with TikTok’s latest filter
If
you’re still on the waiting list to try out DALL-E and you just want a quick peek at the kind of technology that powers it, you might want to open up TikTok.
TikTok’s latest filter may have been around for a few days now, but we first noticed its new A.I. text-to-image generator filter on Sunday. It’s called AI Greenscreen, and it lets you generate painterly style images based on words you input. And the images you generate can become the background of your TikTok videos, like a green screen. Read More
China regulator says Alibaba, Tencent have submitted app algorithm details
China’s top internet watchdog said on Friday tech giants such as Tencent Holdings and Alibaba Group have submitted details of algorithms used in some of their products, complying with a drive by authorities to tighten oversight of platform algorithms.
The rules are part of a broad regulatory crackdown by Beijing against its once free-wheeling technology sector. State media had accused internet platforms of using algorithms to invade user privacy and influencing their choices. Read More
CyberOne’s stage debut with Lei Jun!
NVIDIA announces new Omniverse Avatar Cloud Engine (ACE) for building virtual assistants and digital humans
NVIDIA has today announced NVIDIA Omniverse Avatar Cloud Engine (ACE), a suite of cloud-native AI models and services that make it easier to build and customize lifelike virtual assistants and digital humans.
NVIDIA stated that by bringing these models and services to the cloud, ACE will enable businesses of any size to instantly access the massive computing power needed to create and deploy assistants and avatars that understand multiple languages, respond to speech prompts, interact with the environment and make intelligent recommendations. Read More
Visit Site
Rick's Cafe AI 