Experts from Google Research and Hebrew University of Jerusalem they developed Dreamix, software that can use any material to create videos that correspond to text instructions. Another step forward for generative artificial intelligence in safeguarding all forms of expression (after testi, images e audio). What is special about Dreamix is that it is not limited to text instructions, but also accepts reference photos or videos for better adaptability to users' ideas.
Three operating modes starting from text instructions, images, clips
Starting with images, clips or text instructions, Dreamix provides three main features: video editing, generation of video from images and generation based on the subject.
With thevideo editing, Dreamix can easily play input videos and replace elements with your favorite objects. For example, you can upload a clip of a person cutting a fruit, and ask the AI to replace the fruit with a slice of cake. You can provide some shots of a corn field and create a more dramatic scene. As always, I'll first show you the clips of the two examples.
Dreamix is capable of producing videos starting with images (and/or text instructions). In this example, artificial intelligence transformed a static image into a dynamic work by inserting a swimming shark and making the turtle move. The position and background were kept faithful to the original image, while the direction of the turtle was changed.
The last of the three features allows Dreamix to create animated videos from a small collection of images showing the same subject. For example, if you feed this AI some images of a toy firefighter, it extracts the subject's visual features and animates them so that the subject can perform actions defined in text instructions.
In short (Italian only)
This technology could be a game-changer for creatives who don't just rely on verbal language, but who are also inspired by visual art. At the moment the results still seem very uncertain, but they nevertheless demonstrate the AI's ability to understand text instructions, and the context of input images.
Dreamix can be a valid aid in speeding up the creation of storyboards or generating reference illustrations. It is not currently accessible to the public (and we wonder if Google will make it one of the "standard bearers" to respond to ChatGPT), however it won't take long to see this or other similar tools developed by different companies.
Generative artificial intelligence is destined to have its say also with TV and cinema. Do you want more examples? Here is the whole presentation.
