Video models
OmniHuman 1.5
On this page
OmniHuman 1.5 — high-quality AI video generation.
| modelId | omnihuman-1-5 |
| Modality | video |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | Endpoint | Description |
|---|---|---|
| Text to video | POST /api/v1/generate | Base generation from a text prompt. |
| Image to video | POST /api/v1/generate | Condition on a reference image — upload it via /api/v1/files/upload and pass the URL. |
| Poll task | GET /api/v1/task/{id}?model=omnihuman-1-5 | Retrieve state and result URLs. |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| image_url | image | required | Drag and drop or click to upload your image |
| mask_url | text | optional | JSON array, e.g. [ … ] |
| audio_url | image | required | Drag and drop or click to upload your image |
| prompt | textarea | optional | Enter your prompt here... |
| output_resolution | select | optional | 720, 1080 |
| pe_fast_mode | select | optional | false, true |
| seed | number | optional | Enter number... |
Example request
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"omnihuman-1-5","input":{"mask_url":"…","prompt":"Make the person in the photo speak the audio naturally with warm, friendly gestures.","output_resolution":"1080","pe_fast_mode":"false","seed":-1}}'