OmniHuman-1

Published

Feb 13, 2025

OmniHuman-1 is an AI model developed by ByteDance (China), first published in February 2025. It works in the video, vision and audio domain, on tasks such as video generation and image-to-video.

Epoch AI has no training-compute estimate for this model.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: ByteDance
Country of organization: China
Domain: Video, Vision, Audio
Task: Video generation, Image-to-video
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident