OmniHuman·by ByteDanceTalking avatar
OmniHuman 1.5
ByteDance OmniHuman 1.5: turns a portrait image and an audio track into a realistic, lip-synced talking video with facial expression and body motion. Billed per second of audio (≤60s).
Open in workspace →
bytedance/avatar-omni-human-v1.5Parameters
| Parameter | Type | Default | Range or options |
|---|---|---|---|
seed seedRandom seed; -1 for random. | number | -1 | — |
Resolution output_resolutionOutput video resolution (720 or 1080). Does not affect price. | select | 1080 | 720, 1080 |
Inputs
Files this model takes in addition to the prompt.
| Input | Accepts | Max files | |
|---|---|---|---|
Image image_url | image | 1 | Required |
Audio File audio_url | audio | 1 | Required |