
wan2.6-t2v
API Overview
Tongyi Wanxiang 2.6 is a professional-grade AI video generation model launched by Alibaba’s Tongyi Lab. Its core positioning is as a “film-quality video generation tool that supports role-playing and multi-camera storytelling,” empowering creation across all scenarios.
- Exclusive Feature: The first in China to support “video role-playing”—simply upload a reference video, and the character will perform in a new setting while maintaining consistent appearance and voice tone.
- Upgrade Highlights: Compared to the previous version Wan 2.5, the duration has increased from 10 seconds to 15 seconds, and intelligent shot planning has been added, supporting cinematic camera movements such as wide shots and close-ups.
- Competitive Edge: Compared to OpenAI Sora 2, it offers free trials + open APIs, more flexible role-playing capabilities, and better adaptation to Chinese-language creative scenarios.
- Image Quality Performance: Outputs high-definition videos at 1080P/24fps, with enhanced realism in human portraits, significantly reducing the “AI feel” and delivering professional-level lighting and shadow aesthetics.
- Applicable Scenarios: Covers short films, commercial ads, and virtual character interactions—just input text to generate coherent narrative videos.
───────────────────────────────────────────────────────────────────
Core Capabilities
🎬 One-Click Film Production: Input “A detective running in the rain,” and automatically generate a professional 15-second short film featuring wide shots, close-ups, and tracking shots.
🎥 Intelligent Multi-Camera Directing: Automatically analyzes prompts, orchestrates camera language, lighting rhythms, and emotional dynamics, saying goodbye to monotonous single-shot outputs.
🔊 Native Audio-Visual Synchronization: AI generates voices, background music, lip-sync, expressions, and motions with millisecond-level precision, supporting audio-driven storytelling.
🎞️ Film-Quality Realism: Outputs in 1080P HD, with skin textures, environmental reflections, and motion blur approaching cinematic standards.
📽️ 15-Second Complete Narrative: The longest continuous generation duration in the industry, capable of carrying a complete story structure with introduction, development, twist, and conclusion.
───────────────────────────────────────────────────────────────────
Effect Demonstrations
Prompt: A stylish young male artist is spray-painting a colorful mural of flowers on a brick wall in a sunny city alleyway. Suddenly, the painted flowers magically detach from the wall and transform into glowing, semi-transparent 3D butterflies. The artist looks surprised and then delighted, reaching out his hand to let one butterfly land on his finger. The scene is bathed in warm natural sunlight, dust motes dancing in the air. Vibrant colors, smooth motion, magical realism, award-winning cinematography.
API Console
Log in to explore more features! Click to Log In