{"id":83214,"date":"2022-09-30T22:49:08","date_gmt":"2022-09-30T22:49:08","guid":{"rendered":"https:\/\/harchi90.com\/meta-is-using-ai-to-generate-videos-from-just-a-few-words\/"},"modified":"2022-09-30T22:49:08","modified_gmt":"2022-09-30T22:49:08","slug":"meta-is-using-ai-to-generate-videos-from-just-a-few-words","status":"publish","type":"post","link":"https:\/\/harchi90.com\/meta-is-using-ai-to-generate-videos-from-just-a-few-words\/","title":{"rendered":"Meta is using AI to generate videos from just a few words"},"content":{"rendered":"
\n

\n
\n
\n CNN Business<\/span>
\n \u2014
\n <\/cite>\n<\/p>\n

\n

Artificial intelligence is getting better and better at generating an image in response to a handful of words, with publicly available AI image generators such as DALL-E 2 and Stable Diffusion. Now, Meta are researchers taking AI a step further: they’re using it to concoct videos from a text prompt.\n <\/p>\n

\n

Meta CEO Mark Zuckerberg posted on Facebook on Thursday about the research, called Make-A-Video, with a 20-second clip that compiled several text prompts that Meta researchers used and the resulting (very short) videos. The prompts include \u201cA teddy bear painting a self portrait,\u201d \u201cA spaceship landing on Mars,\u201d \u201cA baby sloth with a knitted hat trying to figure out a laptop,\u201d and \u201cA robot surfing a wave in the ocean.\u201d\n <\/p>\n

\n

The videos for each prompt are just a few seconds long, and they generally show what the prompt suggests (with the exception of the baby sloth, which doesn’t look much like the actual creature), in a fairly low-resolution and somewhat jerky style. Even so, it demonstrates a fresh direction AI research is taking as systems become increasingly good at generating images from words. If the technology is eventually released widely, though, it will raise many of the same concerns sparked by text-to-image systems, such as that it could be used to spread misinformation via video.\n <\/p>\n

\n

A web page for Make-A-Video includes these short clips and others, some of which look fairly realistic, such as a video created in response to the prompt \u201cClown fish swimming through the coral reef\u201d or one meant to show \u201cA young couple walking in a heavy rain.\u201d\n <\/p>\n

\n

In his Facebook post, Zuckerberg pointed out how tricky it is to generate a moving image from a handful of words.\n <\/p>\n

\n

\u201cIt’s much harder to generate video than photos because beyond correctly generating each pixel, the system also has to predict how they’ll change over time,\u201d he wrote.\n <\/p>\n

\n

A research paper describing the work explains that the project uses a text-to-image AI model to figure out how words correspond with pictures, and an AI technique known as unsupervised learning \u2014 in which algorithms pore over data that isn’t labeled to discern patterns within it \u2014 to look at videos and determine what realistic motion looks like.\n <\/p>\n

\n

As with massive, popular AI systems that generate images from text, the researchers pointed out that their text-to-image AI model was trained on internet data \u2014 which means it learned \u201cand likely exaggerated social biases, including harmful ones,\u201d the researches wrote. They did note that they filtered data for \u201cNSFW content and toxic words,\u201d but as datasets can include many millions of images and text, it may not be possible to remove all such content.\n <\/p>\n

\n

Zuckerberg wrote that Meta plans to share the Make-A-Video project as a demo in the future.\n <\/p>\n<\/p><\/div>\n

.<\/p>\n","protected":false},"excerpt":{"rendered":"

CNN Business \u2014 Artificial intelligence is getting better and better at generating an image in response to a handful of words, with publicly available AI image generators such as DALL-E 2 and Stable Diffusion. Now, Meta are researchers taking AI a step further: they’re using it to concoct videos from a text prompt. Meta CEO …<\/p>\n

Meta is using AI to generate videos from just a few words<\/span> Read More »<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-global-header-display":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","spay_email":"","jetpack_publicize_message":"","jetpack_is_tweetstorm":false,"jetpack_publicize_feature_enabled":true},"categories":[4],"tags":[9363,329,4383,10148,4384,1323],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack-related-posts":[{"id":83682,"url":"https:\/\/harchi90.com\/meta-debuts-make-a-video-ai-system-that-generates-videos-from-nothing-but-text-prompts\/","url_meta":{"origin":83214,"position":0},"title":"Meta debuts ‘Make-A-Video’ AI system that generates videos from nothing but TEXT prompts","date":"October 1, 2022","format":false,"excerpt":"Meta debuts artificial intelligence system that generates videos from nothing but TEXT prompts - with some creepy, surreal resultsMeta's new artificial intelligence can generate video clips from nothing but text The AI \u200b\u200bsystem, called Make-A-Video, was trained with combination of existing captioned images and unlabeled videos Thus far, it produces\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"Meta debuted a new type of art-generating AI that can create videos from nothing but text prompts - with results that are creepy, surreal and impressive","src":"https:\/\/i0.wp.com\/i.dailymail.co.uk\/1s\/2022\/09\/30\/16\/62969991-11266897-Meta_debuted_a_new_type_of_art_generating_AI_that_can_create_vid-a-27_1664550127426.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":76310,"url":"https:\/\/harchi90.com\/meta-shows-stunning-full-body-tracking-only-via-quest-headset\/","url_meta":{"origin":83214,"position":1},"title":"Meta shows stunning full body tracking only via Quest headset","date":"September 24, 2022","format":false,"excerpt":"Image: meta Der Artikel kann nur mit aktiviertem JavaScript dargestellt werden. Bitte aktiviere JavaScript in deinem Browser und lade die Seite neu. So far, VR systems have tracked the head and hands. That could change soon: The predictive talent of artificial intelligence enables realistic full-body tracking and thus a better\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"Meta shows stunning full body tracking only via Quest headset","src":"https:\/\/i0.wp.com\/mixed-news.com\/en\/wp-content\/uploads\/2022\/09\/QuestSim_-Human-Motion-Tracking-from-Sparse-Sensors-with-Simulated-Avatars-2-2-screenshot-375x211.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":16192,"url":"https:\/\/harchi90.com\/metas-latest-generative-ai-system-creates-stunning-images-from-sketches-and-text\/","url_meta":{"origin":83214,"position":2},"title":"Meta’s latest generative AI system creates stunning images from sketches and text","date":"July 16, 2022","format":false,"excerpt":"Meta Platforms Inc. today unveiled an advanced \u201cgenerative artificial intelligence system\u201d that's designed to help artists better showcase their creativity. The system, called \u201cMake-A-Scene,\u201d is meant to demonstrate how AI has the potential to empower anyone to bring their imagination to life. The user can simply describe and illustrate their\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/d15shllkswkct0.cloudfront.net\/wp-content\/blogs.dir\/1\/files\/2022\/07\/1-776x600.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":19854,"url":"https:\/\/harchi90.com\/powerful-ai-can-finish-your-sentences-but-struggle-most-times-to-find-solutions-to-basic-tasks\/","url_meta":{"origin":83214,"position":3},"title":"Powerful AI can finish your sentences, but struggle most times to find solutions to basic tasks","date":"July 20, 2022","format":false,"excerpt":"The tech industry's latest artificial intelligence constructs can be pretty convincing if you ask them what it feels like to be a sentient computer, or maybe just a dinosaur or squirrel. But they're not so good - and sometimes dangerously bad - at handling other seemingly straightforward tasks. Take, for\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":57190,"url":"https:\/\/harchi90.com\/microsoft-tiktok-parent-bytedance-collaborate-on-ai-project-kuberay\/","url_meta":{"origin":83214,"position":4},"title":"Microsoft, Tiktok parent ByteDance collaborate on AI project KubeRay","date":"August 26, 2022","format":false,"excerpt":"Flags of China and the United States are seen near a ByteDance logo in this illustration picture taken Sept. 18, 2020.Florence Lo | ReutersThe high-stakes battle between the US and China for supremacy in artificial intelligence has domestic lawmakers growing increasingly concerned over what losing out could mean for national\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"fifu_image_url":"https:\/\/media.cnn.com\/api\/v1\/images\/stellar\/prod\/220929145441-meta-ai-text-to-video.jpg?c=16x9&q=w_800,c_fill","_links":{"self":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts\/83214"}],"collection":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/comments?post=83214"}],"version-history":[{"count":0,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts\/83214\/revisions"}],"wp:attachment":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/media?parent=83214"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/categories?post=83214"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/tags?post=83214"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}