ComfyUI Node
OmniHuman 2.0 · Talking Avatar
A portrait that performs your speech or song, as long as the audio $0.1084 per second. Model: bytedance/omnihuman-2.0/talking-avatar Fields, prices and examples: https://popnow.ai/docs/models/omnihuman-2-0
OmniHuman 2.0 · Talking Avatar
- image_url
- audio_url
- video
- task id
◄prompt►
CategoryPopNow/Video/ByteDance
Inputs (3)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Optional direction for the performance: mood, gestures, where the eyes go, camera movement. Up to 300 characters. | |
| image_url | IMAGE | Portrait to bring to life: JPEG, PNG, WebP, BMP, TIFF, GIF, HEIC or HEIF, under 30 MB, 300 to 6000 px per side, width-to-height ratio 0.4 to 2.5. | |
| audio_url | AUDIO | Speech or singing the portrait performs, WAV or MP3, under 15 MB, 4 to 300 seconds. The clip is as long as this audio. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| task id | STRING | The PopNow task id, for the API console logs or support. |