Tous les modèles
génération de vidéos
Wan 3.0
Wan 3.0 is Alibaba’s all-in-one multimodal video model, built for longer and more reference-heavy work than its predecessors. It handles text-to-video, first- and last-frame guidance, and reference-driven generation in one model, produces native audio, and supports clips up to 30 seconds — the longest single generation in the Gobostock catalogue — at 480p, 720p, or 1080p.
From 134 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.
Aucun exemple publié pour l’instant.
Idéal pour
- Longer narrative clips that would otherwise need stitching
- Reference-led scenes where subject identity must hold across the shot
Limites connues
- It does not accept a negative prompt.
- Cost per second doubles at each resolution step.
Capacités
- Text-to-video and image-to-video generation up to 30 seconds
- Native audio aligned to the visuals
- Prompt rewriting and heavy reference support across image, video, and audio
Entrées
- Text prompt
- Duration and output format
- Optional supported image, video, or audio references
Sorties
- MP4 video
Comparer