{"id":75887,"date":"2024-02-14T23:13:48","date_gmt":"2024-02-14T23:13:48","guid":{"rendered":"https:\/\/entertainment.runfyers.com\/index.php\/2024\/02\/14\/stability-ai-tries-to-stay-ahead-of-the-pack-with-a-new-image-generating-ai-model\/"},"modified":"2024-02-14T23:13:48","modified_gmt":"2024-02-14T23:13:48","slug":"stability-ai-tries-to-stay-ahead-of-the-pack-with-a-new-image-generating-ai-model","status":"publish","type":"post","link":"https:\/\/entertainment.runfyers.com\/index.php\/2024\/02\/14\/stability-ai-tries-to-stay-ahead-of-the-pack-with-a-new-image-generating-ai-model\/","title":{"rendered":"Stability AI tries to stay ahead of the pack with a new image-generating AI model"},"content":{"rendered":"<p> <br \/>\n<\/p>\n<div>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Stability AI\u2019s newest model for image generation is <a href=\"https:\/\/stability.ai\/news\/introducing-stable-cascade\" target=\"_blank\" rel=\"noopener\">Stable Cascade<\/a> promises to be faster and more powerful than its industry-leading predecessor, Stable Diffusion, which is the basis of many other text-to-image generation AI tools. <\/p>\n<\/div>\n<div>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Stable Cascade can generate photos and give variations of the exact image it created, or try to increase an existing picture\u2019s resolution. Other text-to-image editing features include inpainting and outpainting, where the model will fill edit only a specific part of the image, as well as canny edge, where users can make a new photo just by using the edges of an existing picture.<\/p>\n<\/div>\n<div>\n<div class=\"my-9\">\n<p><figcaption class=\"duet--article--dangerously-set-cms-markup inline text-gray-13 dark:text-gray-e9 [&amp;&gt;a:hover]:text-black [&amp;&gt;a:hover]:shadow-underline-black dark:[&amp;&gt;a:hover]:text-gray-e9 dark:[&amp;&gt;a:hover]:shadow-underline-gray-63 [&amp;&gt;a]:shadow-underline-gray-13 dark:[&amp;&gt;a]:shadow-underline-gray-63\">Stable Cascade images generated from the prompt \u201cCinematic photo of an anthropomorphic penguin sitting in a cafe reading a book and having a coffee.\u201d<\/figcaption><cite class=\"duet--article--dangerously-set-cms-markup inline not-italic text-gray-63 dark:text-gray-bd [&amp;&gt;a:hover]:text-gray-63 [&amp;&gt;a:hover]:shadow-underline-black dark:[&amp;&gt;a:hover]:text-gray-bd dark:[&amp;&gt;a:hover]:shadow-underline-gray [&amp;&gt;a]:shadow-underline-gray-63 dark:[&amp;&gt;a]:text-gray-bd dark:[&amp;&gt;a]:shadow-underline-gray\">Image: Stability AI<\/cite><\/p>\n<\/div>\n<\/div>\n<div>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">The new model is available <a href=\"https:\/\/github.com\/Stability-AI\/StableCascade\" target=\"_blank\" rel=\"noopener\">on GitHub<\/a> for researchers but not commercial use, and brings more options even as companies like Google and even Apple release their own image generation models. <\/p>\n<\/div>\n<div>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Unlike Stability\u2019s flagship Stable Diffusion models, Stable Cascade isn\u2019t one large language model \u2014 it\u2019s three different models that rely on the <a href=\"https:\/\/openreview.net\/forum?id=gU58d5QeGv\" target=\"_blank\" rel=\"noopener\">W\u00fcrstchen architecture<\/a>, The first stage, stage C, compresses text prompts into latents (or smaller pieces of code) that are then passed to stages A and B to decode the request. <\/p>\n<\/div>\n<div>\n<div class=\"my-9\">\n<p><figcaption class=\"duet--article--dangerously-set-cms-markup inline text-gray-13 dark:text-gray-e9 [&amp;&gt;a:hover]:text-black [&amp;&gt;a:hover]:shadow-underline-black dark:[&amp;&gt;a:hover]:text-gray-e9 dark:[&amp;&gt;a:hover]:shadow-underline-gray-63 [&amp;&gt;a]:shadow-underline-gray-13 dark:[&amp;&gt;a]:shadow-underline-gray-63\">Comparison of inference time Stable Cascade v other models<\/figcaption><cite class=\"duet--article--dangerously-set-cms-markup inline not-italic text-gray-63 dark:text-gray-bd [&amp;&gt;a:hover]:text-gray-63 [&amp;&gt;a:hover]:shadow-underline-black dark:[&amp;&gt;a:hover]:text-gray-bd dark:[&amp;&gt;a:hover]:shadow-underline-gray [&amp;&gt;a]:shadow-underline-gray-63 dark:[&amp;&gt;a]:text-gray-bd dark:[&amp;&gt;a]:shadow-underline-gray\">Stability AI<\/cite><\/p>\n<\/div>\n<\/div>\n<div>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Breaking the requests into smaller bits compresses the request to require less memory (and fewer hours of training <a href=\"https:\/\/www.theverge.com\/2024\/2\/1\/24058186\/ai-chips-meta-microsoft-google-nvidia\" target=\"_blank\" rel=\"noopener\">on those hard-to-find GPUs<\/a>) and run faster. while performing better \u201cin both prompt alignment and aesthetic quality.\u201d\u00a0It took about 10 seconds to create an image compared to 22 seconds for the SDXL model used currently. <\/p>\n<\/div>\n<div>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph mb-20 font-fkroman text-18 leading-160 -tracking-1 selection:bg-franklin-20 dark:text-white dark:selection:bg-blurple [&amp;_a:hover]:shadow-highlight-franklin dark:[&amp;_a:hover]:shadow-highlight-blurple [&amp;_a]:shadow-underline-black dark:[&amp;_a]:shadow-underline-white\">Stability AI helped popularize the stable diffusion method and has also been the subject of several lawsuits alleging Stable Diffusion trained on copyrighted data without permission from rights holders \u2014 a UK lawsuit by Getty Images against Stability AI is scheduled <a href=\"https:\/\/www.theverge.com\/2023\/12\/4\/23988403\/getty-lawsuit-stability-ai-copyright-infringement\" target=\"_blank\" rel=\"noopener\">to go to trial <\/a>in December. It began offering commercial licenses <a href=\"https:\/\/www.theverge.com\/2023\/12\/19\/24008149\/stability-ai-paid-subscription-commercial-rights-safety\" target=\"_blank\" rel=\"noopener\">through a subscription<\/a> in December, which the company said was necessary to help fund its research. <\/p>\n<\/div>\n<p><br \/>\n<br \/><a href=\"https:\/\/www.theverge.com\/2024\/2\/14\/24073253\/stablity-ai-image-generation-stable-cascade-diffusion-model\" target=\"_blank\" rel=\"noopener\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Stability AI\u2019s newest model for image generation is Stable Cascade promises to be faster and more powerful than its industry-leading predecessor, Stable Diffusion, which is the basis of many other text-to-image generation AI tools. Stable Cascade can generate photos and give variations of the exact image it created, or try to increase an existing picture\u2019s [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":75888,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14],"tags":[],"class_list":{"0":"post-75887","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-tech"},"_links":{"self":[{"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/posts\/75887","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/comments?post=75887"}],"version-history":[{"count":0,"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/posts\/75887\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/media\/75888"}],"wp:attachment":[{"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/media?parent=75887"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/categories?post=75887"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/entertainment.runfyers.com\/index.php\/wp-json\/wp\/v2\/tags?post=75887"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}