Hedra

Recently, there was a big news in the field of AI video creation. The Hedra platform successfully raised $10 million in seed funding, which attracted widespread attention. Hedra was founded by employees who had worked at NVIDIA, Google, and Metaverse, and its investors are strong, including Index Ventures, Abstract, and A16Z Speedrun. In the seed round, Hedra also launched its basic model Character-1 focused on video. The company said that Character, which was previewed to researchers as early as June…

Today, we introduce you to Hedra, an AI lip-sync video generation tool created by a research team from Stanford University. What is Hedra? Hedra, an AI lip-sync video generation tool from Digital Creation Lab. It combines cutting-edge AI technology with the ability to transform text, images and speech into highly realistic and dynamic videos. Whether it's a real person or an anime, or even an object, Hedra generates matching lip-syncs from the audio you upload! Core features of Hedra Upload audio or text to match mouth patterns Hedra is able to accurately capture speech...

By uploading a photo and voice of any person, you can generate a dynamic video artifact that can speak and sing, while keeping the lip shape, expression, posture and voice content matching. Hedra Labs launched a research preview version of Character-1. By uploading a photo and voice of any person, you can generate a dynamic video that can speak and sing, that is, an artifact that can generate speaking and singing videos through text and pictures, while keeping the lip shape, expression, posture and voice content matching. Hedra can be used on desktop and mobile devices, unlimited duration (30 seconds open preview)…