Tous les modèles
génération de vidéos
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. Le devis affiché dans l’outil est celui que vous payez.
Ink currents in clear water
Généré par IA · HappyHorse 1.1
Idéal pour
- Expressive short clips where sound is part of the scene
- Image-guided character or product motion
Limites connues
- Audio is always generated, so silent output requires post-processing.
- First-frame and reference inputs have model-specific limits.
Capacités
- Text-to-video and image-to-video
- Native audio with seed support
- 720p and 1080p output from 3 to 15 seconds
Entrées
- Text prompt
- Duration and output format
- Optional supported image, video, or audio references
Sorties
- MP4 video
Comparer