Wan 2.6 Video Generator

Next-generation multimodal video with 1080p at 24 fps, native audio-visual sync, precise lip-sync, and multi-shot narrative support.

Key Features

**1080p at 24 fps**: High-definition video output with smooth 24 frames per second motion.

**Native Audio-Visual Sync**: Visuals automatically align with provided audio tracks for music videos or dialogue.

**Precise Lip-Sync**: Accurate lip movements driven by audio input for realistic talking characters.

**Multi-Shot Narratives**: Generate videos with stable characters across multiple shots or transitions.

**Multimodal Inputs**: Supports Text, Image, Audio, and Video inputs for maximum creative flexibility.

**Extended Duration**: Generate clips up to 15 seconds long for more complete storytelling.

**Prompt Expansion**: Built-in prompt enhancement to add detail and style to brief descriptions.

**Negative Prompts**: Use negative prompts to remove unwanted elements or artifacts.

Wan 2.6 Specifications

Model NameWan 2.6
Input ModesText, Image, Audio, Video
Resolutions720p, 1080p
Durations5s, 10s, 15s
Frame Rate24 fps
Special FeaturesLip-Sync, A/V Sync, Multi-Shot
PricingStarting at 60 gold / 5s

Ideal Use Cases

Epic Fantasy Cutscenes

Create high-quality, cinematic cutscenes for D&D campaigns with stable characters and fluid motion.

Narrative Storytelling

Use multi-shot mode to tell short stories with consistent visual style and character identity.

Music Videos

Sync visuals perfectly to music tracks with beat-aware motion generation.

Character Dialogue

Bring NPCs or characters to life with precise lip-syncing to recorded voice lines.