The YouTube administration announced that the updated Dream Screen feature is now available in the Shorts section of short vertical videos – generating dynamic background images using artificial intelligence. Previously, the Dream Screen function made it possible to generate still images as backgrounds rather than videos.
A new feature has emerged thanks to the integration of the Google DeepMind Veo video generation model – it allows you to create videos with a resolution of 1080p in different cinematic styles. To launch the new feature, you need to go to the Shorts camera, select the “Green Screen” icon and the Dream Screen option – here you can enter a text query, for example, “candy landscape” or “magical forest and stream”; after which all you have to do is select the animation style and click the “Create” button. Dream Screen will create several video backgrounds, from which you need to select one, after which you can record a video with this image behind you.
The new feature will be useful, for example, to immerse the viewer in the atmosphere of a favorite book or prepare an animated introduction to the main video. In the future, YouTube plans to give creators the ability to create 6-second videos entirely generated by Dream Screen. The world’s largest short video platform TikTok also supports AI-powered background images, but these images are still static. YouTube users from the USA, Canada, Australia and New Zealand can use the updated version of Dream Screen.
This week, Congress held confirmation hearings for new ministers nominated by new US President Donald…
California-based startup Vast Space has announced the completion of the world's first commercial space station,…
In October, Qualcomm introduced the flagship processor Snapdragon 8 Elite, which received two powerful cores…
Samsung has previously announced the development of functions based on Vision AI artificial intelligence that…
OpenAI CEO Sam Altman announced on Platform X on Friday that work on the large…
US scientists have used an innovative method of combining images from two optical telescopes to…