You're looking at a specific version of this model. Jump to the model overview.
lex2029 /vlogme-avatar-bridge:e3f75f8e
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| avatar_image |
string
|
Face/avatar reference image
|
|
| audio |
string
|
Speech audio to animate
|
|
| vlogme_api_token |
string
|
VlogMe API token. Use a Secret input or VLOGME_API_TOKEN env var.
|
|
| vlogme_api_url |
string
|
https://vlogme.ai/api/public/v1
|
VlogMe public API root
|
| title |
string
|
Replicate avatar render
|
Title for the VlogMe render job
|
| aspect_ratio |
None
|
9:16
|
Output aspect ratio
|
| live_subtitles |
boolean
|
True
|
Burn/live subtitle preference for the VlogMe render
|
| face_restore |
number
|
-1
|
Optional face restore strength 0.0..1.0. -1 keeps VlogMe defaults.
|
| video_prompt |
string
|
|
Optional render prompt override
|
| video_negative_prompt |
string
|
|
Optional negative prompt override
|
| watermark_text |
string
|
|
Optional watermark text. Empty uses the VlogMe brand watermark when watermark_enabled is true.
|
| watermark_enabled |
boolean
|
True
|
Burn a watermark into the final video. Keep true for free generations; paid callers can set false.
|
| timeout_sec |
integer
|
1740
|
Maximum time to wait for VlogMe to finish
|
| poll_interval_sec |
integer
|
10
|
Polling interval while VlogMe worker renders
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}