ComfyUI Node
Omnihuman 1.5
Omnihuman 1.5 OpenAPI Specification
Omnihuman 1.5
- image_url
- audio_url
- video
- url
- all_urls_json
- task_id
- raw_json
- credits_consumed
- credits_left
◄promptA person speaking naturally with gentle expressions.►
◄mask_url[
"https://your-domain.com/image/mask.png"
]►
◄output_resolution1080►
◄pe_fast_modefalse►
◄seed-1►
◄timeout_seconds1200►
◄callback_url►
CategoryKIE Next/Video/OmniHuman
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| image_url | IMAGE | — | |
| audio_url | AUDIO | — | |
| prompt | STRING | A person speaking naturally with gentle expressions. | Optional prompt text. Limited to Chinese, English, Japanese, Korean, Spanish, and Indonesian. Recommended 300 characters or less. Maximum length: 1000 characters. |
| mask_urlopt | STRING | [ "https://your-domain.com/image/mask.png" ] | Optional mask image URL(s). To have a specific subject in the image speak, use 'Subject Detection' to get the corresponding mask image and pass it as input. Accepted file types: image/jpeg, image/png, image/webp. Max file size: 10MB. Multiple file upload is supported, up to 5 files. |
| output_resolutionopt | COMBO | 1080 | Output video resolution. - `720`: 720P - `1080`: 1080P (default) |
| pe_fast_modeopt | BOOLEAN | false | Fast mode. Sacrifices some quality to speed up generation. Default value: `false`. |
| seedopt | INT | -1-2147483648–2147483647 | Random seed. Default is `-1` (random). When using the same positive integer and keeping all other parameters identical, the result will be highly consistent. |
| timeout_secondsopt | INT | 120030–7200 | — |
| callback_urlopt | STRING | Optional KIE callback URL. Leave empty for normal ComfyUI use. |
Outputs (7)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| url | STRING | — |
| all_urls_json | STRING | — |
| task_id | STRING | — |
| raw_json | STRING | — |
| credits_consumed | FLOAT | — |
| credits_left | FLOAT | — |