Unlock stock picks and a broker-level newsfeed that powers Wall Street. Upgrade Now
Kuaishou Kling AI Unveils “Multi-Image Reference” Feature to Further Tackle AI Video Consistency Challenges

In This Article:

HONG KONG, Jan. 23, 2025 (GLOBE NEWSWIRE) -- Kuaishou Technology (“Kuaishou” or the “Company”; HKD Counter Stock Code: 01024 / RMB Counter Stock Code: 81024), a leading content community and social platform, recently announced the global launch of Kling AI’s “multi-image reference” feature, addressing one of the most persistent challenges in AI video generation – maintaining visual consistency. This cutting-edge technology enables AI to analyze and integrate diverse subjects from multiple images and creatively generate composite videos based on users’ text descriptions, empowering creators to produce seamless and professional-quality videos with greater precision.

The “multi-image reference” feature is now available to users worldwide through the Kling AI 1.6 model. Users can upload one or more images of the same subject (such as a person, animal, movie character or object), and the model will reference these images to generate a video with a consistent style, ensuring the subject remains visually consistent across multiple scenes. For example, by uploading images of a cat, a jacket, and sunglasses and entering a prompt like “A humanoid cat in a jacket and sunglasses turns on stage and poses for the camera,” the model skillfully blends the reference images and user instructions to produce a professional-grade video.

Kuaishou Kling-1
Kuaishou Kling-1

Users can also use reference images to define specific scenes, enabling characters to don different outfits and undertake actions within designated settings, thus greatly enhancing creative control. For example, by uploading reference images of an elderly man, a cup of coffee, and a café scene, and entering a prompt such as “A cartoon-style elderly man grabs a cup of coffee in a café,” users can generate a video depicting a man sitting in a café sipping his coffee.

Kuaishou Kling-2
Kuaishou Kling-2

Furthermore, the “multi-image reference” feature enables dynamic interactions between different characters. Users can upload images of multiple subjects (such as people, animals or movie characters) and describe their desired interactions through text prompts. For example, by uploading reference images of a boy and a Corgi and entering the prompt “A cute boy is petting a Corgi,” the feature will generate a video that brings the scene to life (video frame shown below).

Kuaishou Kling-3
Kuaishou Kling-3

Since its initial rollout on June 6, 2024, Kling AI has undergone dozens of extensive iterations and upgrades. Most notably, in December 2024, the video generation model Kling AI 1.6 was officially launched, building upon the foundation model and elevating its capabilities significantly. Kling AI 1.6 introduced major advancements in text responsiveness, increasing its ability to interpret text descriptions related to motion, temporal action, and camera movement. Additionally, the upgraded model enhanced motion quality with smoother motion and more natural expressions. Kling AI 1.6 also delivered comprehensive upgrades in color accuracy, lighting dynamics, and detailed rendering, resulting in a striking improvement in overall video quality. Users can access the new feature via the web portal (Chinese version: https://klingai.kuaishou.com; English version: https://klingai.com) or by searching for and downloading KLINGAI in the app store.