Wan 2.6 is a native multimodal AI model that turns ideas into cinematic-quality videos and images. It supports multi-shot storytelling, consistent character casting from reference videos, natural audio-visual sync with realistic lip-sync, and 1080p HD generation. With advanced control over motion, lighting, lenses, and aesthetics, Wan 2.6 enables creators to produce coherent, professional-grade visual narratives from simple prompts.

Wan 2.2 is a major open-source update to the Wan video models. It introduces a Mixture-of-Experts (MoE) architecture for top-tier performance and offers fine-grained cinematic control over lighting, color, and composition.

Wan2.2-S2V is an open-source model by the Wan team that creates film-grade digital human videos from a single image and an audio file. It generates natural expressions, lip-sync, and smooth body movements, with text prompts for extra control over the scene.