Max Resolution
720p · 1080p
AI / Video Generation & Editing / Alibaba
Wan 2.6
Alibaba video generation family with text, image and reference-to-video plus synchronized audio.
Video GenerationNative AudioDeveloper API
Max Duration
T2V/I2V: 2–15s · R2V: 2–10s
Generation Modes
Text-to-Video · Image-to-Video · Image-to-Video Flash · Reference-to-Video · Reference-to-Video Flash
Native Audio
Native synchronized audio in Wan 2.6 T2V/I2V/R2V; supports automatic dubbing or uploaded audio in supported generation modes
About Wan 2.6
Wan 2.6 is a production-oriented generative video family available through Alibaba Cloud Model Studio, supporting multi-shot narratives and audio synchronization.
Specifications
Developer & Integration
1 specifications +
| API Access | Alibaba Cloud Model Studio API |
Overview
4 specifications +
| Main Specialization | Multimodal video generation with synchronized audio, multi-shot narratives and reference video |
| Target Audience | Developers, creators and production teams using Alibaba Cloud Model Studio |
| Best For | Cinematic short-form video, multi-shot storytelling, character-reference video, multi-character dialogue and synchronized audiovisual content |
| Current Model | Wan 2.6 family entry; Wan 2.7 is the newer recommended Wan generation family |
Generation
5 specifications +
| Text-to-Video | Wan 2.6 T2V: text + optional audio → synchronized video; supports multi-shot narrative |
| Image-to-Video | Wan 2.6 I2V: first-frame image + prompt + optional audio → synchronized video; supports multi-shot narrative |
| Reference-to-Video | Wan 2.6 R2V uses reference video to preserve character appearance and voice; supports single- and multi-character scenes |
| Multi-Shot Generation | Native multi-shot narrative in T2V/I2V; R2V supports narrative single/multi-character compositions |
| Generation Modes | Text-to-Video · Image-to-Video · Image-to-Video Flash · Reference-to-Video · Reference-to-Video Flash |
