Revolutionizing Visuals: Kuaishou Keling AI Unveils Groundbreaking 1.5 Model Upgrade, Delivering Stunning 1080p HD Video Output
Kuaishou Keling AI Global Upgrade: Enhanced Image Quality and Motion Control
Keling AI has recently undergone a significant upgrade, introducing the new Keling 1.5 model, which boasts substantial improvements in image quality, dynamic quality, aesthetic performance, motion rationality, and semantic understanding. This upgrade also brings a powerful “motion brush” function, enabling precise control over video generation.
Upgraded Base Model: Keling 1.5
The Keling 1.5 model supports direct output of 1080p high-definition video in high-quality mode, challenging the clarity and texture of large screens. Compared to the Keling 1.0 model, the 1.5 model has significant improvements in picture quality, dynamic quality, text responsiveness, and overall internal evaluation effect, with a 95% increase.
Comparison of Keling 1.0 and Keling 1.5 Models
By inputting the prompt word “girl looking at the car window” and comparing the effects generated by the two versions of the video on the left and right, it can be found that the picture quality of the new model of Kelin 1.5 has been significantly improved: the picture clarity is intuitive and perceptible, and the girl on the right side of the picture Facial details are clearer and richer, and the water mist on the car windows and the overall light and shadow performance are also better.
Enhanced Dynamic Quality
The new model has also been significantly improved in terms of dynamic quality. For example, compared with Keling AI’s popular noodle-eating case before, enter the prompt word “little boy eating noodles”. In the video generated by the 1.5 model on the right, the noodles have different elasticity and vertical characteristics during the process from being clamped to the entrance. The falling feeling and other aspects have very realistic physical expressions.
Improved Image-Generated Videos
Keling’s new 1.5 model can respond to more complex text description requirements. For example, through a food photo without people and the prompt “zoom out, a little boy walks to the table, picks up a spoon and starts eating”, in the generated video, as the camera shakes slightly, a spoon “enters the scene”, and then the picture focuses on the little boy holding the spoon, watching him put a spoonful of food into his mouth, and the details of the spoon pushing the rice grains in the bowl are also presented in detail, showing a strong ability to understand image-generated videos.
Motion Brush Function
The “motion brush” function supports specifying motion trajectories for elements in the picture (people or objects, etc.). Users only need to outline the part of the picture that needs to control the direction of movement, and then draw an arrow to indicate the direction of movement to achieve precise motion control. This function supports specifying motion trajectories for up to 6 elements (people or objects, etc.) in the picture after uploading the picture.
Other Upgrades and Features
Keling AI has also recently upgraded a series of other functions, such as supporting the generation of up to 4 videos at a time, which makes it easier for creators to quickly select the best generation result; the “Image to Video” function now supports 10 seconds of duration and supports adding tail frames in standard mode; the ”AI Picture” function supports “image quality enhancement”. In addition, the official user guide has been launched to help users better control Keling AI.
Global Launch and User Adoption
Since its release in June this year, this is the 9th iteration and upgrade of Keling AI. This upgrade will also be launched globally. In July this year, Keling AI announced the official launch of the international version 1.0, which was officially open to global users, and then launched a global membership system. At present, Keling AI has accumulated a large number of domestic and foreign users.