HappyHorse 1.1 Image-to-Video is built around a hybrid brief that fuses a still source frame with text motion direction, so the model knows what to preserve from the image and what to animate on top of it. Within the wider HappyHorse 1.1 family, this variant focuses on image-to-video synthesis and sits alongside text-to-video and reference-to-video modes that share the same endpoint and differ only by a model parameter. The intended use is short, production-leaning clips where a product, character, or scene reference needs to stay recognizable while motion, camera timing, and expressive action are layered over it. Creators can pair a reference picture with a written motion prompt in a single workflow, rather than committing to pure text or pure image input up front.

In practice the model is positioned for social ads, user-generated-style clips, and early cinematic drafts that need consistent character or product detail across movement. It supports flexible durations of roughly 3 to 15 seconds and multiple aspect ratios including 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, and 21:9, with 720p and 1080p quality options. Pricing on third-party routing is around $0.124 per second at 720p and about $0.160 per second at 1080p, billed per second of output. The model fits teams that want a single image-anchored video tool for short marketing or storytelling assets, especially when reference continuity matters more than open-ended generation.