Kuaishou Coling AI has officially launched the new keyframe feature based on the 2.1 model, with an effect improvement of 235% compared to the 1.6 model.


Kuaishou Coling AI has officially launched the new keyframe feature based on the 2.1 model, with an effect improvement of 235% compared to the 1.6 model.

In the global AI video field, Kuaishou's Keling AI has shown strong growth momentum, with monthly revenue reaching 20 million US dollars. CEO Cheng Yixiao issued a military order, aiming for doubling revenue growth this year, highlighting the commercialization potential of domestic video large models.
Recently, the world's first AI anthology series 'New World Loading...' produced by Keling AI and Xingmang Short Series held a grand premiere on June 25th. This series combines diverse genres such as science fiction, history, fantasy, and absurd comedy, showcasing new attempts of AI technology in film and television creation. In actual viewing, audiences found that the series performed well in innovative content and sci-fi elements. By using detailed action scripts and start-end frame technology, the series successfully solved the problem of insufficient smoothness in fast fight scenes. However, the series also faces
In the field of artificial intelligence, Kuaishou's Keling AI is gradually emerging as a dark horse in video generation applications. According to the latest earnings call, Cheng Yixiao, founder and CEO of Kuaishou, revealed that since its launch in June last year, Keling AI's revenue has exceeded 100 million yuan, making it the largest commercially successful video generation AI application in China. Keling AI's strong functionality and early market entry have secured its position in the fiercely competitive AI market. Cheng Yixiao emphasized that with the continued development of AI...
By the end of the year, domestic AI has really ramped up. Today, Keling AI officially announced the launch of its multi-image reference feature, which supports referencing multiple subjects simultaneously. Users can upload 1 to 4 reference images and select specific people, objects, props, or scenes from them. Combined with textual descriptions, the model will create imaginative videos based on these references, helping users achieve more personalized creations. This feature is particularly suitable for short films that require visual consistency. Users can upload multiple images of the same character to ensure consistency of individuals or subjects across multiple shots.
In the realm of AI visual creation, the MOKI short film tool has recently announced its latest upgrade, introducing the highly anticipated membership features and integrating two major models, VIDU and Keling AI, further enriching the creation experience for creators. This update not only retains the original Meitu Qixiang large model but also provides customized optimizations for animation scenes, motion effects, and controllability through the newly added VIDU and Keling AI large models to meet the diverse needs of different creators.