HappyHorse-1.1-R2V

HappyHorse 1.1 Reference-to-Video composes a video from the characters, objects, and styles you supply. Upload 1 to 9 reference images and weave them into one scene through your prompt, calling each out in order with tags like [Image 1], [Image 2] — "the woman in the red qipao from [Image 1] sways the tassel earrings from [Image 3] while unfolding the fan from [Image 2]." HappyHorse keeps each subject consistent while it stages their actions and interactions into coherent motion. Choose from nine aspect ratios, output at 720P or 1080P for 3 to 15 seconds with an optional watermark — perfect for character-driven storytelling, virtual try-on, and bringing your own assets together in a single shot.