You're looking at a specific version of this model. Jump to the model overview.
expa-ai /avatar-model:6f4605c2
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 |
|---|---|---|---|
| process_type |
string
(enum)
|
generate
Options: generate, upscale, generate_and_upscale, face_swap, generate_swap, generate_swap_upscale |
Choose a process type. Can be 'generate', 'upscale' or 'generate_and_upscale'. Defaults to 'generate'
|
| prompt |
string
|
a woman in pink jacket,(barbie-themed office), princess room, princess, (pink accessories), (pink office), (costume:1.1),(best quality), (photo realistic), (small breast:1.1), ((hands))
|
Input prompt.
|
| negative_prompt |
string
|
(bad_pictures:1.2), negative_hand-neg, negative_hand, (nsfw:2), (worst quality), (low quality), (normal quality), lowres, watermark, monochrome
|
Input negative prompt.
|
| width |
integer
(enum)
|
640
Options: 128, 256, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, 1024 |
Width of output image.
|
| height |
integer
(enum)
|
640
Options: 128, 256, 384, 448, 512, 576, 640, 704, 768, 832, 896, 960, 1024 |
Height of output image.
|
| num_inference_steps |
integer
|
25
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
7
Min: 1 Max: 20 |
Scale for classifier-free guidance
|
| scheduler |
string
(enum)
|
DPM++
Options: DDIM, K_EULER, K_EULER_ANCESTRAL, DPM++, UniPC |
Choose a scheduler.
|
| seed |
integer
|
-1
|
Random seed. Leave blank to randomize the seed.
|
| upscaler_model |
string
(enum)
|
4x_UniversalUpscalerV2-Neutral_115000_swaG
Options: 4x_UniversalUpscalerV2-Neutral_115000_swaG, 1x_NMKDDetoon_97500_G |
Model to use for upscaling
|
| image_to_upscale |
string
|
Input image for the upscaler (ESRGAN).
|
|
| image |
string
|
Inital image to generate variations of. Supproting images size with 512x512 or 512x768
|
|
| mask_image |
string
|
Black and white image to use as mask for inpainting over the image provided. White pixels are inpainted and black pixels are preserved
|
|
| need_mask |
boolean
|
True
|
Generate a mask with built-in helper function.
|
| strength |
number
|
0.3
|
How much to transform the masked portion of the reference image. Always use 0.3 for avatars.
|
| target_for_swap |
string
|
Target image for adding the face from original image. (***This is just to test the face swap feature. Do not use***)
|
|
| num_outputs |
integer
|
1
Min: 1 Max: 10 |
Number of images to output. If the NSFW filter is triggered, you may get fewer outputs than this.
|
| need_lora |
boolean
|
False
|
Whether to use LoRA or not.
|
| paid |
boolean
|
False
|
Whether it is paid user or not
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}