すべてのモデル
動画生成
HappyHorse 1.1
HappyHorse 1.1 is Alibaba’s expressive audio-visual generation model for text and image-driven clips. Gobostock exposes always-on native sound, reproducible seeds, 720p or 1080p output, first-frame guidance, multiple reference images, and 3-to-15-second durations for short cinematic and character-focused footage.
From 187 Gobostock credits; surcharges or usage-based pricing may apply where shown in the tool quote. ツールに表示される見積もりが、お支払いいただく金額です。
Ink currents in clear water
AI生成 · HappyHorse 1.1
最適な用途
- Expressive short clips where sound is part of the scene
- Image-guided character or product motion
既知の制限
- Audio is always generated, so silent output requires post-processing.
- First-frame and reference inputs have model-specific limits.
機能
- Text-to-video and image-to-video
- Native audio with seed support
- 720p and 1080p output from 3 to 15 seconds
入力
- Text prompt
- Duration and output format
- Optional supported image, video, or audio references
出力
- MP4 video
比較