HappyHorse 1.1
Alibaba video model that works from text, a start image or reference images.
HappyHorse 1.1 is an Alibaba video generation model that makes short clips from a text prompt, one starting image or several reference images.
- Provider
- Alibaba (Qwen)
- Type
- Video model
- Released
- Jun 22, 2026
- Input
- text, image
- Output
- video
- Open weights
- No
Best for
- Multimodal
Strengths
- Reference-image conditioning
- Text- or image-to-video
More from Alibaba (Qwen)
- Qwen3.8 Max — Alibaba (Qwen). Alibaba’s 2.4T-parameter proprietary flagship with video understanding.
- Qwen3.8 2.4T A95B — Alibaba (Qwen). The open-weight release of Qwen3.8 Max — one of the largest open models.
- Qwen3.8 Flash — Alibaba (Qwen). Open multimodal reasoning model for coding, desktop interaction and long video.
- Qwen3.6 35B A3B — Alibaba (Qwen). Open MoE with just 3B active parameters — popular for local inference.
- Qwen3.8 Omni Flash — Alibaba (Qwen). Omni-modal reasoning model with native audio and video understanding.
- Qwen3.8 27B — Alibaba (Qwen). Dense 27B open vision-language model with adjustable thinking.
- Qwen3-Embedding-8B — Alibaba (Qwen). Leading open-weight multilingual embedding model.
- Qwen-Image-3.0-Pro — Alibaba (Qwen). Alibaba’s flagship image model with strong text rendering.