Kuaishou Kelin's large model open diagram can make videos, and the video can be up to 3 minutes long if continued writing.

Breakings ·  Jun 21 14:50

Kuaishou Kelin's large model has released a major update: formally opening image-to-video functionality, supporting the transformation of static images into 5-second videos. Users can control the movement of objects in the image through text prompts. At the same time, the video continuation function is launched, supporting one-click continuation and continuous multiple continuations of generated videos, with a maximum length of about 3 minutes. In June of this year, Kuaishou released the self-developed video generation large model Kelin, which can support the production of videos up to 120 seconds. It has opened for invitation testing experience on the Kuaishou Video app, and currently has accumulated about 140,000 people applying for internal testing.

The translation is provided by third-party software.

The above content is for informational or educational purposes only and does not constitute any investment advice related to Futu. Although we strive to ensure the truthfulness, accuracy, and originality of all such content, we cannot guarantee it.
    Write a comment