Bytedance Omnihuman V2
Animates a person from one image and supplied audio, with optional text guidance for the performance.
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 generates video with native audio from up to 30 images, 10 videos, and 10 audio references. Supports reference-guided generation, video editing, and extension at 480p, 720p or 1080p.
Scores appear here when an evaluation matches this exact model.
bytedance/seedance-2.5/us/reference-to-videoUpdated Oct 18, 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.
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.
US-hosted ByteDance Seedance 2.5 generates cinematic video from text with synchronized audio, up to 30-second duration, and 480p, 720p or 1080p output.