Wan 2.6 is a multimodal creative model from Wan that enables generation and editing of visual content from text and images. It supports text-to-video, image-to-video, text-to-image, image-to-image and image editing workflows, lowering the barrier for creators to produce high-quality visual assets. The model is positioned as part of an integrated creative platform, aimed at accelerating concepting, prototyping, and content production by translating prompts and visual inputs into refined outputs.