Now Roscosmos, Russia's space agency, has shared a model of the country's future station, as it prepares to move out of the International Space Station. Nicknamed ROSS by state-controlled media, it would launch in two phases, starting with four modules and expanding to six with a service platform. The design would accommodate four people in rotating tours and reportedly offer better monitoring of Earth than Russia gets from the ISS today. State media claim the first phase will launch between 2025 and 2030, with Russia expected to leave the ISS in 2024. It announced its departure from the ISS in July in response to sanctions and other measures following Russia's invasion of Ukraine in February. Apple's M2-powered MacBook Air is $100 off at Amazon Tesla's Shanghai Gigafactory made its 1 millionth car Samsung has gone all-out on its next-generation monitor.

First photographers were creating portraits of people that don't exist, now Aurel Manea has created a series of "landscape photos" using a new artificially intelligent (AI) software program called Stable Diffusion. Manea tells PetaPixel that he has been blown away by what the London and Los Altos-based startup Stability AI has created. "I can't, as a landscape photographer myself, emphasize enough what these new technologies will mean for photography," explains Manea. "Of course, they are not real photos and they only resemble real places (for now, as the input data becomes larger and larger) but for most of the people that consume the images, it is only about the beauty of those images." Manea says that he has used DALLE-2 and it does "great images of people's faces that look like photos." But, he says, DALL-E fails to create landscape photography.

Text-to-picture AI frameworks are blasting in both capacity and notoriety at this moment, and what preferable evidence over their appearance on the planet's most sweltering application: TikTok The video stage as of late added another impact it calls "Artificial intelligence greenscreen" that permits clients to type in a text brief that the product will then create as a picture. This picture can then be utilized as the foundation to a video -- possibly an exceptionally valuable device for makers. The result of TikTok's framework is fundamental contrasted with that of best in class text-to-picture models like Google's Imagen, OpenAI's DALL-E 2, or Midjourney's eponymous programming. It makes just rather dynamic and whirling pictures; a strength reflected in the marvelous idea of TikTok's proposed prompts like "space explorer in the sea" and "bloom universe." Other models, by examination, can create both photorealistic symbolism and complicated and rational delineations that seem as though they were drawn or painted by people. TikTok's model just creates twirling, preoccupied, spread pictures.

Original artwork of mine conceived by descriptive text, and generated with AI thanks to DALL·E. Owning this NFT gives you the right to use the underlying image for personal and commercial purposes. Such uses include avatars, design projects, artistic references, and editorial content.

The recent influx and growth of machine learning and artificial intelligence rises questions about the way in which creative processes evolve.

OpenAI's DALL-E 2 is getting free competition. Behind it is an AI open-source movement and the startup Stability AI. Artificial intelligence that can generate images from text descriptions has been making rapid progress since early 2021. At that time, OpenAI showed impressive results with DALL-E 1 and CLIP. The open-source community used CLIP for numerous alternative projects throughout the year.

TikTok has rolled a new in-app text-to-image AI generator that lets users type in a prompt and receive an image that can be used as the background in their videos. The effect is called "AI greenscreen" and can be accessed via the short-form video app's camera screen. The new effect was first spotted by The Verge. The launch of the new filter comes as text-to-image AI generators are becoming increasingly popular, especially with the launch of OpenAI's DALL-E 2. It's worth noting that the images that TikTok's AI generator produces are quite basic when compared to the output from notable text-to-image models, including DALL-E 2 and Google's Imagen. TikTok's model produces abstract imagery, whereas DALL-E 2 and Imagen are able to create photorealistic imagery.

You don't need to fire up DALL-E if you want AI to create images from text -- you just need a popular social media app. The Verge notes TikTok has introduced a rudimentary "AI greenscreen" effect in its Android and iOS apps that turns your text descriptions into artwork. It's much simpler than OpenAI's DALL-E 2, producing abstract blobs rather than photorealistic depictions, but it might do the trick if you want an original background for your latest video. As The Verge explains, though, there may be strong reasons to limit the AI generator's capabilities. Even if the required computational power isn't a problem, the potential output might be.

Recently we are witnessing a major shift in the process of generating images. The recent influx and growth of machine learning and artificial intelligence rises questions about the way in which creative processes evolve and develop through technology. Systems like DALL-E, DALL-E 2 and Midjourney are AI programs trained to generate images from text descriptions using a dataset of text-image pairs. The diverse set of capabilities includes creating anthropomorphized versions of animals and objects, combining unrelated concepts in plausible ways, and applying transformations to existing images. DALL-E and similar systems are able to create plausible images for a great variety of sentences that explore the compositional structure of language.

I've become infatuated with this new set of capabilities and the opportunity to create in an utterly new way. While I've generated many random ideas, including some with my 10-year-old, I've also used it as an opportunity to be intentional in order to craft a series of images. As the son of an avid reader of science fiction, who grew up to be one myself, I was surrounded by amazing cover art in my formative years. Conceptually, I wanted to build out a set of portraits of a bear-like race known for their prowess as pilots in the deep reaches of space. It may sound silly, but it proved a wonderful starting point. For the curious, I built these out through many iterations within Midjourney, starting with the initial prompt Panda fighter pilot, cinematic and working from there.