LibTV launches HappyHorse 1.0 video model for the first time online.

LibTV has launched its new-generation video model, HappyHorse 1.0, which supports three modes: text-based video, image-based video, and reference image generation. It can output 15-second 1080P multi-camera narrative videos. The model features natural language video editing, cinematic picture quality, intelligent scene arrangement, synchronized audio-visual generation, and multi-style reproduction capabilities, significantly improving the naturalness of character movements, micro-expression portrayal, and the realism of dialogue.