ComfyUI Node
daVinci-MagiHuman · Text to Video
Put a line in quotes and the person on screen says it From $0.024 per second. Model: sand-ai/davinci-magihuman/text-to-video Fields, prices and examples: https://popnow.ai/docs/models/davinci-magihuman
daVinci-MagiHuman · Text to Video
- audio_url
- video
- task id
◄prompt►
◄aspect_ratio16:9►
◄resolution720p►
◄duration_seconds5►
◄seed0►
CategoryPopNow/Video/Sand.ai
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | What happens, and in quotes what the person says. The model speaks quoted lines itself. | |
| aspect_ratio | COMBO | 16:9 | Output aspect ratio. |
| resolution | COMBO | 720p | Output resolution. The model generates at a low base size and upscales with its own super-resolution stage; higher tiers cost more per second. |
| duration_seconds | INT | 55–10 | Clip length in whole seconds, 5 to 10. Billed per second. |
| seed | INT | 00–2147483647 | Same seed and settings, same result. Set 'control after generate' to randomize to get a new result on every run; every run is billed. |
| audio_urlopt | AUDIO | Optional speech or song (MP3 or WAV). When given, the clip is generated in sync with it instead of a voice the model writes. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| task id | STRING | The PopNow task id, for the API console logs or support. |