You're looking at a specific version of this model. Jump to the model overview.
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 |
|---|---|---|---|
| message |
string
|
User message to generate Trump response for
|
|
| recent_news |
string
|
|
Recent news context for Trump response
|
| chat_history |
string
|
[]
|
JSON string of chat history
|
| audio_prompt_path |
string
|
Optional reference audio to condition the voice
|
|
| repetition_penalty |
number
|
1.2
|
Penalty to reduce repetition
|
| min_p |
number
|
0.05
|
Minimum probability mass for sampling
|
| top_p |
number
|
1
|
Top-p nucleus sampling
|
| cfg_weight |
number
|
0.5
|
Classifier-free guidance weight
|
| temperature |
number
|
0.8
|
Softmax temperature
|
| exaggeration |
number
|
0.5
|
Controls expressiveness
|
| seed |
integer
|
Random seed for determinism
|
|
| face_image |
string
|
Face image for lip-sync
|
|
| generate_lip_sync |
boolean
|
False
|
Generate lip-synced video
|
| wav2lip_model |
None
|
wav2lip
|
Wav2Lip model variant
|
| fps |
number
|
25
|
FPS for lip-sync video
|
| out_height |
integer
|
480
|
Output video height
|
| negative_prompt |
string
|
|
Negative prompt
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'additionalProperties': {'anyOf': [{'type': 'string'},
{'anyOf': [],
'format': 'uri',
'type': 'string'}]},
'title': 'Output',
'type': 'object'}