{"id":21887,"date":"2025-03-10T14:09:39","date_gmt":"2025-03-10T12:09:39","guid":{"rendered":"https:\/\/forklog.com\/en\/tencent-unveils-ai-video-generator-based-on-images\/"},"modified":"2025-03-10T14:09:39","modified_gmt":"2025-03-10T12:09:39","slug":"tencent-unveils-ai-video-generator-based-on-images","status":"publish","type":"post","link":"https:\/\/forklog.com\/en\/tencent-unveils-ai-video-generator-based-on-images\/","title":{"rendered":"Tencent Unveils AI Video Generator Based on Images"},"content":{"rendered":"<p>The Chinese technology company Tencent has <a href=\"https:\/\/github.com\/Tencent\/HunyuanVideo-I2V\">introduced<\/a> a new open-source AI model, HunyuanVideo-I2V, designed to transform images into videos.<\/p>\n<p>This tool enables the conversion of a static photograph into a video clip with 720p resolution and up to 129 frames (approximately five seconds) using prompts.<\/p>\n<p>HunyuanVideo-I2V is built on the HunyuanVideo model, unveiled in December 2024, which is the world&#8217;s largest open-source video generation model, containing over 13 billion parameters.<\/p>\n<p>The tool allows the use of individual <span data-descr=\"a method for optimizing large neural networks, enabling rapid adaptation and fine-tuning of models with reduced computational and memory costs\" class=\"old_tooltip\">LoRA<\/span> adapters to create unique visual styles and effects, providing users with greater control.<\/p>\n<p>HunyuanVideo-I2V requires a powerful graphics processor\u201480 GB of video memory is recommended, with a minimum requirement of 60 GB.<\/p>\n<p>Users have reported that an RTX 4090 24 GB is sufficient if dynamic scenes are not involved.<\/p>\n<blockquote class=\"twitter-tweet\">\n<p lang=\"en\" dir=\"ltr\">Some test on HunyuanVideo I2V model for on local RTX 4090 24G<br \/>If not dynamic movement, performance is fine. <a href=\"https:\/\/t.co\/3fBfLMuwZp\">pic.twitter.com\/3fBfLMuwZp<\/a><\/p>\n<p>\u2014 TTPlanet (@ttplanet) <a href=\"https:\/\/twitter.com\/ttplanet\/status\/1898927568163897646?ref_src=twsrc%5Etfw\">March 10, 2025<\/a><\/p><\/blockquote>\n<p> <script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n<p>Following the <a href=\"https:\/\/forklog.com\/en\/news\/openai-unveils-sora-enthusiasm-and-challenges\">announcement<\/a> of OpenAI&#8217;s text-to-video generative AI model\u2014<a href=\"https:\/\/forklog.com\/en\/news\/openai-launches-sora-an-ai-video-generator\">Sora<\/a>\u2014many startups have begun developing and offering similar tools.<\/p>\n<p>Previously, DeepMind, Google&#8217;s AI-focused division, <a href=\"https:\/\/forklog.com\/en\/news\/google-deepmind-unveils-advanced-ai-video-and-image-generators\">announced<\/a> a new model for creating videos, Veo 2.<\/p>\n<p>In October, Meta <a href=\"https:\/\/forklog.com\/en\/news\/meta-unveils-ai-video-generator-movie-gen\">introduced<\/a> Movie Gen, an AI generator for creating new videos, editing existing ones, and adding sound to them.<\/p>\n<p>In July, the AI model Kling from Chinese developer Kuaishou <a href=\"https:\/\/forklog.com\/en\/news\/chinese-kling-emerges-as-a-rival-to-sora\">became available<\/a> worldwide.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The Chinese technology company Tencent has introduced a new open-source AI model, HunyuanVideo-I2V, designed to transform images into videos. This tool enables the conversion of a static photograph into a video clip with 720p resolution and up to 129 frames (approximately five seconds) using prompts. HunyuanVideo-I2V is built on the HunyuanVideo model, unveiled in December [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":21886,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"","news_style_id":"","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1771,1392],"class_list":["post-21887","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-tencent","tag-video"],"aioseo_notices":[],"amp_enabled":true,"views":"86","promo_type":"","layout_type":"","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/21887","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/comments?post=21887"}],"version-history":[{"count":0,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/21887\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media\/21886"}],"wp:attachment":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media?parent=21887"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/categories?post=21887"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/tags?post=21887"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}