OpenAI’s DALL-E isn’t the only artificial intelligence capable of generating images from a brief text description. A few weeks ago, Google presented “Image,” an AI alternative from the company founded by Elon Musk (among others), capable of creating more realistic and better-quality designs, according to Mountain View. Today, Microsoft has joined the fray. He does it NUWA Infinity An AI, which is capable of generating images from texts alone, But convert static drawing to video.
Microsoft describes NUWA as “a multimodal generative model designed to generate high-quality images and video given text, image, or video.” Its functionality is not too different from what DALL-E or even Image (Google) can do. However, it has many advantages over the two models of artificial intelligence. It is the only AI capable of creating a video from an image created by a text description. AI, moreover, A video can be created directly from a description.
Compared to DALL-E, Imagen and Parti, NUWA-Infinity can produce high-resolution images of arbitrary size and support long video creation.
NUWA, Microsoft’s AI can stretch any type of image
NUWA, Microsoft’s AI capable of generating images and videos from text description… “Stretch” any image and create a larger, higher resolution image. Artificial intelligence, in particular, finds information in the original photo and, depending on its parameters, creates another complete one. For example, NUWA can extend Vincent van Gogh’s “Starry Night.” And, it does so with a level of detail and more accurate continuity than that provided in the original design.
At this time, Microsoft has not provided more details about Nuva, beyond a few examples showing the capabilities of this AI, such as how to convert text to image, image to video, or text to video. , as well as the ability to extend any design. It’s certainly an interesting alternative to DALL-E and Imagen, although both algorithms have their advantages.
The image, for example, Creates more realistic mapsAlthough it is not yet available to users. DALL-E, on the other hand, offers less realistic images, but is accessible to users, and is available through public beta, albeit with limited access.