By uploading a photo and voice of any person, you can generate a dynamic video artifact of the person talking and singing, while keeping the lip shape and expression, posture and voice content matching.
Hedra Labs has launched a research preview version of Character-1. By uploading a photo and voice of any person, you can generate a dynamic video of the person talking and singing. That is, it can generate a talking and singing video through text and pictures, while keeping the lip shape and expression, posture and voice content matching.
Hedra is available on desktop and mobile devices, with unlimited duration (30-second previews). It supports expressive dialogue, singing and rapping characters, and natural gestures and expressions.
Hedra Features
- Text and Image Generation: Character-1 is able to generate talking and singing videos from text and images.
- Unlimited duration: During the open preview period, Character-1 supports unlimited length video generation, up to 30 seconds.
- High efficiency: every 60 seconds of input can generate 90 seconds of video.
- Expression synchronization: The facial expressions and lip shapes of the characters in the generated video match the speech content.
- Diverse Characters: Character-1 enables the generation of expressive and controllable character videos.
- Virtual world building: Hedra also plans to launch a Worlds feature that will allow users to build their own virtual worlds.
- Creative Control: Hedra offers complete creative control, allowing users to imagine worlds, characters, and stories.
Official website link:https://www.hedra.com/