{"id":516717,"date":"2023-11-23T16:48:32","date_gmt":"2023-11-23T14:48:32","guid":{"rendered":"https:\/\/mybroadband.co.za\/news\/?p=516717"},"modified":"2023-11-23T16:50:26","modified_gmt":"2023-11-23T14:50:26","slug":"stable-diffusion-creator-testing-ai-powered-video-generator","status":"publish","type":"post","link":"https:\/\/mybroadband.co.za\/news\/software\/516717-stable-diffusion-creator-testing-ai-powered-video-generator.html","title":{"rendered":"Stable Diffusion creator testing AI-powered video generator"},"content":{"rendered":"<p>Stable Diffusion creator Stability AI has <strong><a href=\"https:\/\/stability.ai\/news\/stable-video-diffusion-open-ai-video-model\" target=\"_blank\" rel=\"noopener\">announced<\/a><\/strong> that users can now test a new generative AI that animates a single image generated from a text prompt to create AI-generated videos.<\/p>\n<p>&#8220;Stable Video Diffusion is released in the form of two image-to-video models, capable of generating 14 and 25 frames at customizable frame rates between 3 and 30 frames per second,&#8221; Stability AI said.<\/p>\n<p>The videos are generated in 1,024 x 576 resolution.<\/p>\n<p>&#8220;This state-of-the-art generative AI video model represents a significant step in our journey toward creating models for everyone of every type,&#8221; the company said.<\/p>\n<p>&#8220;Latent diffusion models trained for 2D image synthesis have been turned into generative video models by inserting temporal layers and fine-tuning them on small, high-quality video datasets.&#8221;<\/p>\n<p>Stability AI conducted user preference studies on its new AI video generator and said it has been well received.<\/p>\n<p>&#8220;At the time of release in their foundational form, through external evaluation, we have found these models surpass the leading closed models in user preference studies,&#8221; it said.<\/p>\n<p>For reference, the user preference studies compared Stable Video Diffusion to text-to-video platforms like Runway and Pika Labs.<\/p>\n<p>The AI video generator is only available for research purposes now, and potential users can join the waitlist to access an &#8220;upcoming web experience featuring a text-to-video interface&#8221;.<\/p>\n<p>Stable Diffusion has noted that the generative AI has <strong><a href=\"https:\/\/huggingface.co\/stabilityai\/stable-video-diffusion-img2vid\" target=\"_blank\" rel=\"noopener\">some limitations<\/a><\/strong>, including:<\/p>\n<ul>\n<li>The generated videos are rather short (up to 4 seconds).<\/li>\n<li>The model lacks perfect photorealism.<\/li>\n<li>The model can&#8217;t do camera motion except for slow camera pans.<\/li>\n<li>The model cannot be controlled through text.<\/li>\n<li>The model cannot render legible text.<\/li>\n<li>Faces and people in general may not be generated properly.<\/li>\n<li>The autoencoding part of the model is lossy.<\/li>\n<\/ul>\n<hr \/>\n<h3 class=\"my-4\">Now read: <a href=\"https:\/\/mybroadband.co.za\/news\/software\/516083-nvidia-sued-after-engineer-shares-screen-with-stolen-file-during-video-call.html\" rel=\"bookmark\">Nvidia sued after engineer shares screen with stolen file during video call<\/a><\/h3>\n","protected":false},"excerpt":{"rendered":"<p>Stable Video Diffusion generates short videos by animating single images created using its text-to-image generator.<\/p>\n","protected":false},"author":341076,"featured_media":516719,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[16],"tags":[84939,85253,83445,91015,91017],"class_list":["post-516717","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-software","tag-generative-ai","tag-stability-ai","tag-stable-diffusion","tag-stable-video-diffusion","tag-video-generator"],"_links":{"self":[{"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/posts\/516717"}],"collection":[{"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/users\/341076"}],"replies":[{"embeddable":true,"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/comments?post=516717"}],"version-history":[{"count":1,"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/posts\/516717\/revisions"}],"predecessor-version":[{"id":516889,"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/posts\/516717\/revisions\/516889"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/media\/516719"}],"wp:attachment":[{"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/media?parent=516717"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/categories?post=516717"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mybroadband.co.za\/news\/wp-json\/wp\/v2\/tags?post=516717"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}