← All models
Expressive facial performance, natural speech-expression coordination, realistic body motion, and accurate audio-video synchronization with DaVinci-MagiHuman model
Example
Details
- Accepts
- image
Pricing
- Price
- 6.25 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed for reproducibility. |
| promptrequired | string | Text prompt describing the desired video content. |
| duration | integer | Duration of the generated video in seconds. |
| audio_url | — | Optional URL of the driving audio for lipsync mode. If omitted, audio is generated from the prompt. |
| image_urlrequired | string | URL of the reference image for image-to-video generation. |
| resolution | stringenum: 256p, 540p, 720p, 1080p | Output resolution. '256p' uses the official base-model 448x256 path. '1080p' uses the official base + 1080p super-resolution pipeline. '540p' and '720p' reuse that sharper 1080p SR path and downsample to the requested output size. |
| guidance_scale | number | Classifier-free guidance scale. |
| num_inference_steps | — | Number of denoising steps. Defaults to 8 for 256p and 32 for 540p/720p/1080p (base + SR). |
| enable_safety_checker | boolean | If enabled, runs safety checks on the prompt and input image. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used for generation. |
| video | — | The generated video with synchronized audio. |