Alibaba · Video Model
Generate High-Quality Videos from Text and Images
Alibaba's multimodal AI model for text-to-video and image-to-video generation
Happy Horse transforms text prompts and images into coherent video sequences. The model handles diverse visual concepts, maintains temporal consistency across frames, and supports controllable video generation. Input your description or reference image, configure parameters like duration and style, and generate videos suitable for content creation, prototyping, and creative workflows. Specs: up to Up to 15 seconds, up to Up to 1080p.
Video model
- Modality
- Text or Image → Video
- Flexibility
- Multiple ratios & durations
- Resolution
- Up to 1080p
- Max Duration
- Up to 15s
