Bytedance Omnihuman V2
Animates a person from one image and supplied audio, with optional text guidance for the performance.
US hosted version of ByteDance's most advanced image-to-video model. Animate still images into cinematic video with synchronized audio, start and end frame control, and motion prompts.
Scores appear here when an evaluation matches this exact model.
bytedance/seedance-2.0/us/image-to-videoUpdated Oct 20, 2026
Animates a person from one image and supplied audio, with optional text guidance for the performance.
Draft completion endpoint for Seedance 2.5 - submit a draft id to regenerate the task at 1080p.
Generates, edits or extends video using up to 30 images, ten video clips and ten audio clips through a US-hosted endpoint.
US-hosted ByteDance Seedance 2.5 animates still images with synchronized audio and optional end-frame control. Generate videos up to 30 seconds at 480p, 720p or 1080p.