CNET: AI Art Is About to Get Sharper, Better Looking, Less Porny. “Stability AI, the developers behind popular AI-generated art program Stable Diffusion, released a major update to the software on Thursday, European time (Wednesday night in the US).”
Ars Technica: Stable Diffusion in your pocket? “Draw Things” brings AI images to iPhone. “On Wednesday, a San Francisco-based developer named Liu Liu released Draw Things: AI Generation, a free app available in the App Store that lets iPhone owners run the popular Stable Diffusion AI image generator. Type in a description, and the app generates an image within several minutes. It’s a notable step toward bringing image synthesis to a wider audience—with the added privacy of running it on your own hardware.
Ars Technica: “Too easy“—Midjourney tests dramatic new version of its AI image generator. “On Saturday, AI image service Midjourney began alpha testing version 4 (‘v4’) of its text-to-image synthesis model, which is available for subscribers on its Discord server. The new model provides more detail than previously available on the service, inspiring some AI artists to remark that v4 almost makes it ‘too easy’ to get high-quality results from simple prompts.”
Motherboard: This Tool Lets Anyone See the Bias in AI Image Generators. “Called the Stable Diffusion Bias Explorer, the project is one of the first interactive demonstrations of its kind, letting users combine different descriptive terms and see firsthand how the AI model maps them to racial and gender stereotypes.”
TechCrunch: Digital assets marketplace Creative Fabrica launches generative AI tool. “Creative Fabrica, a marketplace for digital files like print-on-demand assets, fonts and graphics, announced today it will launch its own generative AI tool. Called CF Spark, it’s already seen three million prompts generated, and more than 500,000 published by Creative Fabrica creators over the past three weeks. Like other digital assets on the platform, users can put up their generative AI files for paid use by other members, which Creative Fabrica says makes it the first generative AI that also allows creators to make money.”
Hackaday: How The Art-generating AI Of Stable Diffusion Works. “[Jay Alammar] has put up an illustrated guide to how Stable Diffusion works, and the principles in it are perfectly applicable to understanding how similar systems like OpenAI’s Dall-E or Google’s Imagen work under the hood as well. These systems are probably best known for their amazing ability to turn text prompts (e.g. ‘paradise cosmic beach’) into a matching image. Sometimes. Well, usually, anyway.”
Bing Blog: Image Creator now live in select countries for Microsoft Bing and coming soon in Microsoft Edge
Bing Blog: Image Creator now live in select countries for Microsoft Bing and coming soon in Microsoft Edge. “Image Creator allows you to create an image that doesn’t exist, limited only by your imagination. Simply type in a description of something, any additional context like location or activity, and an art style, and Image Creator will make it for you.”
Bulletin of the Atomic Scientists: AI is plundering the imagination and replacing it with a slot machine
Bulletin of the Atomic Scientists: AI is plundering the imagination and replacing it with a slot machine. “These tools represent the complete corporate capture of the imagination, that most private and unpredictable part of the human mind. Professional artists aren’t a cause for worry. They’ll likely soon lose interest in a tool that makes all the important decisions for them. The concern is for everyone else. When tinkerers and hobbyists, doodlers and scribblers—not to mention kids just starting to perceive and explore the world—have this kind of instant gratification at their disposal, their curiosity is hijacked and extracted.” And here is my periodic reminder that I include articles in this section (opinion) with which I do not necessarily agree.
Analytics India: Google Releases a New Text-Based Image Editing Model Called ‘Imagic’. “Google researchers recently came up with a new text-based image editing method called ‘Imagic’. Imagic uses an input image and a text prompt—describing the edit—to then produce an edited image as its output. This new method, they claim, is unlike any of their previous methods for it doesn’t require any additional inputs.”
Search Engine Journal: Google On The Use Of AI Images. “In a recent Search off the Record podcast, Google’s Lizzi Sassman and John Mueller discussed the use of AI generated images on websites. Some of their opinions might seem surprising given how AI generated text content is treated by Google.”
Motherboard: AI Is Probably Using Your Images and It’s Not Easy to Opt Out. “Viral image-generating AI tools like DALL-E and Stable Diffusion are powered by massive datasets of images that are scraped from the internet, and if one of those images is of you, there’s no easy way to opt out, even if you never explicitly agreed to have it posted online. In one stark example of how sensitive images can end up powering these AI tools, a user found a medical image in the LAION dataset, which was used to train Stable Diffusion and Google’s Imagen.”
How-To Geek: “UnstableFusion” Makes AI Art Easy on Windows, Mac, and Linux. “‘UnstableFusion’ is another front-end that is rising in popularity, available on Windows, Mac, and Linux. It’s a native desktop application, instead of a command-line tool or a local web server, so it’s one of the easiest ways to try Stable Diffusion right now. The main catch is that you still need to install Python, the Stable Diffusion model, and other components on your own — the full instructions are available in the readme file.”
Ars Technica: DALL-E image generator is now open to everyone. “If you’ve been itching to try OpenAI’s image synthesis tool but have been stymied by the lack of an invitation, now’s your chance. Today, OpenAI announced that it removed the waitlist for its DALL-E AI image generator service. That means anyone can sign up and use it.”