Researchers at ByteDance, TikTok's parent company, showcased an AI model designed to generate full-body deepfake videos from one image and audio — and the results are scarily impressive.

Chinese giant Alibaba released Wan 2.1 and made it open-source: It's a text-to-video AI service similar to OpenAI's Sora.

ByteDance said that, unlike some deepfake models that can animate only faces or upper bodies, its OmniHuman-1 could generate realistic full-body animations that sync gestures and facial ...