Alibaba's HappyHorse 1.0 Video Generation Model Available on Replicate
Alibaba's HappyHorse 1.0 video generation model is now accessible via Replicate's API, supporting both text-to-video and image-to-video generation at 720p and 1080p resolutions with durations from 3 to 15 seconds.
Alibaba's HappyHorse 1.0 is a video generation model available through Replicate. It supports two primary modes: text-to-video generation from prompts, and image-to-video animation using a provided first-frame image. When both an image and prompt are supplied, the prompt guides the motion of the animated image.
The model accepts inputs including a text prompt (up to 2,500 characters), an optional first-frame image (JPG/PNG/BMP/WEBP, ≤10MB, minimum 300px per side, aspect ratio between 1:2.5 and 2.5:1), resolution (720p or 1080p), aspect ratio for text-to-video (16:9, 9:16, 1:1, 4:3, or 3:4), duration (3–15 seconds), and an optional seed for reproducible generation.
Pricing on Replicate is based on output resolution: $0.14 per second for 720p video and $0.28 per second for 1080p video. The model can be run via Replicate's Playground, API, or client libraries for Node.js and Python.
The Wire · Newsletter
One careful email,
every Monday.
The week's most important AI stories, lightly edited and personally vouched for. No autoplay, no spam, easy to leave.
Comments · 0
Sign in to join the discussion.
Be the first to leave a thought.