HappyHorse video model is live, integrated with Wu Kong!

On April 27, HappyHorse 1.0, a video generation model developed by Alibaba, officially launched its gray-scale testing. The Wukong platform has simultaneously completed its initial integration and has begun sending targeted invitations to enterprise customers for testing.

Developed by Alibaba's ATH Innovation Division, HappyHorse 1.0 adopts a native multimodal architecture and joint audio-video generation technology. It supports text-to-video, image-to-video, multi-image reference production, and video editing, capable of generating narrative clips up to 15 seconds with multiple shots. It accommodates various aspect ratios and delivers 1080P ultra-high-definition output, ensuring cinematic-quality visuals and synchronized audio-visual experience.

Enhanced Multimodal Creation Capabilities

With the integration of HappyHorse, Wukong will significantly strengthen its multimodal creation capabilities in text-to-image and video generation. Enterprise users can now directly generate high-quality images and videos within Wukong by simply entering natural language instructions—no professional design skills or frequent switching between different tools required.

Wukong has initiated an enterprise co-creation program, inviting users from sectors such as e-commerce and design to participate in scenario development, aiming to transform model technologies into practical productivity tools.

Example: E-commerce Applications

Previously, creating product promotional videos or main images often involved collaboration across photography, design, and editing teams—time-consuming and costly.

Now, through Wukong, operations staff can simply describe a product’s key features and desired style to quickly generate product showcase videos and promotional images, greatly shortening the cycle from concept to final output.

For design agencies, combining Wukong with HappyHorse enables instant visualization of design concepts, helping designers efficiently validate creative ideas at early stages and thereby improving overall efficiency from ideation to delivery.

Following its exclusive early access to Qwen 3.6-Plus on April 2, Wukong has once again prioritized the integration of a core model from the ATH ecosystem within just one month. While Qwen 3.6 enhances text understanding and agent-based programming, HappyHorse specializes in image and video generation. Wukong is gradually evolving into the enterprise-level launchpad for the full suite of ATH models, accelerating the formation of a multimodal AI workspace that encompasses text, code, images, and video.

We dedicated to serving clients with professional DingTalk solutions. If you'd like to learn more about DingTalk platform applications, feel free to contact our online customer service or email at This email address is being protected from spambots. You need JavaScript enabled to view it.. With a skilled development and operations team and extensive market experience, we’re ready to deliver expert DingTalk services and solutions tailored to your needs!