Whether you’re gazing at a palace or church, a mythological or religious painting, a tapestry or fresco, the answer is almost always that the works were first conceived by means of drawing.

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.

The draw is finished. Select Play to watch it back.