On December 2, the Qianwen APP integrated the newest model, Wan2.5, from the Wanxiang series. This integration has significantly upgraded its video creation capabilities, bringing about comprehensive enhancements in motion accuracy and bodily coordination. The Qianwen APP has now emerged as the first mobile AI assistant capable of delivering simultaneous audio and video output.
Leveraging this new integration, users can now create singing and dancing videos that boast 1080P high-definition quality, natural bodily movements, and synchronized lip movements. These videos can be up to 10 seconds long and can be generated using just a single photo and a piece of text. Furthermore, the Qianwen APP has introduced the innovative Qwen-Image model, which supports advanced functions such as precise image editing and multi-perspective conversion.
