Vidu is a Chinese AI Video Generator That Lets You Combine Still Images Into One Video

Vidu gave the example of a photo of a shirt, a moped, and Elon Musk. All three were used as reference images for the video (below).

Chinese AI video generator Vidu has launched its 1.5 model which can take elements from different photos and blend them into one video.

Vidu has a “Multiple-Entity Consistency Feature” which lets users upload separate images that bear no relation to each other and the program will merge them. This tools allows the user to choose up to three reference images.

PetaPixel uploaded a photo of a DSLR camera, Brad Pitt, and a studio to try and get a video of Pitt holding the camera moving around the studio. The attempts were largely unsuccessful because the character never looked like Pitt but it did successfully combine all three source pictures.

A camera lens on the left, a man in a suit on a red carpet in the center, and a studio light on the right.
The source pictures PetaPixel used for the below videos. | Depositphotos.


In another attempt, PetaPixel tried to take a camera lens and customize it by giving it a camouflage wrap.

Vidu is the first AI video platform to have Multi-Entity Consistency and the company says that it’s also unique in that Vidu 1.5 will maintain the unique attributes of multiple characters throughout a video. Instead of morphing or becoming inconsistent the way they do in most AI videos.

Another feature in Vidu is “Multiple Angle Consistency” which will build a “360-degree view” of a subject by using one to three still images. The AI will fill in the missing details and create a “cohesive video” that can look at the subject from any angle.

Vidu 1.5 also has an “Advanced Control” feature which enables “greater precision over camera movements, angles, and cinematic technique.” The Beijing-based company say Advanced Control has “advanced cinematographer styles” that include “adjustable dynamic ranges offering a higher degree of control over speed and scale resulting in complex shots like zooming, panning, and tilting or a combination of these.”

Vidu can also generate AI videos in 1080p but the quality of the videos isn’t particularly good so perhaps the foundation model needs to be improved before touting high-resolution AI video.

“The future of content creation is here, and it is powered by the limitless possibilities of AI,” says Jiayu Tang, CEO and co-founder of Shengshu Technology.

“Together, we can ignite a global wave of inspiration, reshaping industries, and democratizing creativity. At the core of this transformation lies the ability for anyone to engage in high-quality content production, unlocking new opportunities and breaking down traditional limitations.”

You can sign up to Vidu for free now via its website. Users get 80 credits monthly. If you want more then plans currently start at $7.99 per month.

FOLLOW US ON GOOGLE NEWS

Read original article here

Denial of responsibility! Todays Chronic is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – todayschronic.com. The content will be deleted within 24 hours.

Leave a Comment