alibaba/happy-horse/text-to-video
Generate 1080p video with synchronized native audio from a text prompt. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.
Inference
Commercial use
Partner
Prompt examples
Examples are generated using the Happy Horse. You can customize them by clicking on the "Playground" button.
Shot 1 (wide, 0-1.5s): A man in a charcoal wool sweater stands at a tall window in a quiet living room, looking out at an overcast afternoon street, soft diffused grey light, warm wood and leather interior, dust drifting in the air.
Shot 2 (mid close up, 1.5-3.5s): He turns and sits down into a leather armchair beside the window, opens a worn paperback in his lap, and starts to read, the leather creaking softly under him.
Shot 3 (over the shoulder, 3.5-5s): The camera glides slowly over his shoulder down onto the open book, his thumb gently turning a single page, soft window light falling across the paper, shallow depth of field on his hand.
aspect_ratio16:9
Shot 1 (mid wide, 0-1.5s): A young woman in a beige cable knit sweater walks slowly into frame inside a sunlit cafe, threading past a wooden chair, late morning, warm side light through tall windows, soft wood and brass interior.
Shot 2 (close up, 1.5-3.5s): She sits at a small marble topped table by the window, wraps both hands around a white ceramic coffee cup, soft steam rising in a thin curl, warm amber backlight skimming her hair.
Shot 3 (slow push in, 3.5-5s): The camera slowly pushes toward her face as she lifts the cup, takes a small sip, and settles back into the chair, eyes briefly closing, soft bokeh of the cafe behind her.
aspect_ratio16:9