Kuaishou Keling launches the function of creating videos from pictures and continuing videos up to 3 minutes long

quick workerKelingThe new features “Photo to Video” and “Video Continuation” are launched today.

Figure videoFunction that supports converting static images into 5-second videos, and users can control the movement of objects in the image through prompt text;Video continuationFunction, supports one-click and multiple-time continuation of generated videos, and can generate up to about 3 minutes of video; in additionVincent VideoAdded 9:16 and 1:1 video size options.

Attached KuaishouCan LingguanWebsite:https://www.1ai.net/12558.html

Kuaishou Keling launches the function of creating videos from pictures and continuing videos up to 3 minutes long

Keling is a large video generation model developed by Kuaishou that can generate large-scale reasonable movements and simulate the characteristics of the physical world.

KeLing uses the DiT architecture, and Kuaishou has upgraded the dimensions of modules such as latent space encoding/decoding and time series modeling in the model.

In latent space encoding/decoding, Kuaishou developed its own 3D VAE network to achieve spatiotemporal synchronous compression, obtain high reconstruction quality, and strike a balance between training performance and effect. In temporal information modeling, Kuaishou designed a full attention mechanism as a spatiotemporal modeling module.

statement:The content is collected from various media platforms such as public websites. If the included content infringes on your rights, please contact us by email and we will deal with it as soon as possible.
Information

SoftBank founder Masayoshi Son: New round of investment will be dedicated to building "super artificial intelligence"

2024-6-22 9:28:03

Information

Leju Kuafu humanoid robot debuts at HDC 2024, equipped with Huawei Cloud Pangu embodied intelligent large model

2024-6-22 9:30:33

Search