Bringing portraits to life. Alibaba introduces Wan2.2-S2V, an open-source Speech-to-Video model that generates high-quality animated videos from a single image and an audio clip. Create film-quality avatars that can speak, sing, and perform. Now available on Hugging Face, GitHub, and ModelScope. Read the full announcement for more details:int.alibabacloud.com/m/1000406617 #AI #OpenSource #VideoGeneration #DigitalHuman #Wan2S2V #AInnovation #WanAI