You're looking at a specific version of this model. Jump to the model overview.
smoretalk /avatar-generator:a0e842cb
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 |
|---|---|---|---|
| face_image |
string
|
Input face image
|
|
| pose_image |
string
|
Reference pose image
|
|
| prompt |
string
|
Portrait photo, hyperrealistic art, extremely high resolution details, detailed, photographic, realism pushed to extreme, fine texture, incredibly lifelike, intimidate mood, 8k
|
Input prompt
|
| negative_prompt |
string
|
|
Input negative prompt
|
| gender |
string
(enum)
|
No choice
Options: Male, Female, No choice |
Pick the character's gender
|
| num_inference_steps |
integer
|
8
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
1
Min: 1 Max: 20 |
Scale for classifier-free guidance
|
| ip_adapter_scale |
number
|
0.8
Max: 1.5 |
Scale for image adapter strength (for detail)
|
| face_strength |
number
|
0.8
Max: 1.5 |
Scale for strength of IdentityNet (for fidelity)
|
| composition_strength |
number
|
0.5
Max: 1 |
Scale for strength of ControlNet
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| resemblance |
number
|
0.8
Max: 1 |
Conditioning scale for controlnet
|
| creativity |
number
|
0.8
Max: 1 |
Denoising strength. 1 means total destruction of the original image
|
| hdr |
number
|
0
Max: 1 |
HDR improvement over the original image
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}