{"id":1219924,"date":"2022-10-10T05:43:28","date_gmt":"2022-10-10T05:43:28","guid":{"rendered":"https:\/\/www.ghanamma.com\/2022\/10\/10\/google-announces-ai-text-to-video-generator\/"},"modified":"2022-10-10T05:43:28","modified_gmt":"2022-10-10T05:43:28","slug":"google-announces-ai-text-to-video-generator","status":"publish","type":"post","link":"https:\/\/www.ghanamma.com\/2022\/10\/10\/google-announces-ai-text-to-video-generator\/","title":{"rendered":"Google announces AI text to video generator"},"content":{"rendered":"

<\/p>\n

\n
\n

<\/p>\n

Google Research is working on an AI text to video generator.<\/p>\n

The tech giant\u2019s research branch has announced plans for Imagen Video, which would take user prompts to build looping high-definition video clips in a similar way to Meta\u2019s recently-unveiled Make-A-Video system.<\/p>\n

While Meta\u2019s new offering has a sign-up option, Google is waiting until it has ironed out some safeguarding issues.<\/p>\n

In a tweet, Jonathan Ho, an author of the research paper, said: \u201cWith the help of progressive distillation, Imagen Video can generate high-quality videos using just eight diffusion steps per sub-model.<\/p>\n

\u201cThis speeds up video generation time substantially, by a factor of ~18x.\u201d<\/p>\n

The team has admitted there is a \u201crisk that Imagen has encoded harmful stereotypes and representations\u201d, despite trying to filter \u201cundesirably content\u201d.<\/p>\n

This means Google won\u2019t be releasing Imagen Video to the public until the team knows the system won\u2019t be abused by the AI or its own users.<\/p>\n

Meta recently said it was being \u201cthoughtful\u201d when it came to building \u201cnew generative AI systems like this\u201d.<\/p>\n

It said: \u201cMake-A-Video uses publicly available datasets, which adds an extra level of transparency to the research.<\/p>\n

\u201cWe are openly sharing this generative AI research and results with the community for their feedback, and will continue to use our responsible AI framework to refine and evolve our approach to this emerging technology.\u201d<\/p>\n

BANG ShowBiz Tech<\/strong><\/p>\n

Source <\/a><\/p>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

Google Research is working on an AI text to video generator. The tech giant\u2019s research branch has announced plans for Imagen Video, which would take user prompts to build looping high-definition video clips in a similar way to Meta\u2019s recently-unveiled Make-A-Video system. While Meta\u2019s new offering has a sign-up option, Google is waiting until it […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[21],"tags":[],"class_list":["post-1219924","post","type-post","status-publish","format-standard","category-celebrity-gossip"],"_links":{"self":[{"href":"https:\/\/www.ghanamma.com\/2022\/wp-json\/wp\/v2\/posts\/1219924","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ghanamma.com\/2022\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.ghanamma.com\/2022\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.ghanamma.com\/2022\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ghanamma.com\/2022\/wp-json\/wp\/v2\/comments?post=1219924"}],"version-history":[{"count":0,"href":"https:\/\/www.ghanamma.com\/2022\/wp-json\/wp\/v2\/posts\/1219924\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.ghanamma.com\/2022\/wp-json\/wp\/v2\/media?parent=1219924"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ghanamma.com\/2022\/wp-json\/wp\/v2\/categories?post=1219924"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ghanamma.com\/2022\/wp-json\/wp\/v2\/tags?post=1219924"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}