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 |
|---|---|---|---|
| only_render_first_frame |
boolean
|
False
|
If true, only the first frame will be rendered, providing a preview of the initial and final positions. Remember to check `show_points_and_arrows`!
|
| show_points_and_arrows |
boolean
|
True
|
Toggles the display of arrows and points denoting the interpolation path in the generated video.
|
| stylegan2_model |
string
(enum)
|
ada/afhqcat.pkl
Options: stylegan2/stylegan2-ffhq-config-f.pkl, stylegan2/stylegan2-cat-config-f.pkl, stylegan2/stylegan2-church-config-f.pkl, stylegan2/stylegan2-horse-config-f.pkl, ada/ffhq.pkl, ada/afhqcat.pkl, ada/afhqdog.pkl, ada/afhqwild.pkl, ada/brecahad.pkl, ada/metfaces.pkl, self_distill/bicycles_256_pytorch.pkl, self_distill/dogs_1024_pytorch.pkl, self_distill/elephants_512_pytorch.pkl, self_distill/giraffes_512_pytorch.pkl, self_distill/horses_256_pytorch.pkl, self_distill/lions_512_pytorch.pkl, self_distill/parrots_512_pytorch.pkl |
The chosen StyleGAN2 model to perform the operation.
|
| source_pixel_coords |
string
|
[(200, 100)]
|
Pixel values defining the starting coordinates. String should be formatted as '(y, x)', where 'y' is the pixel count from the bottom, higher y values mean higher up on the screen and 'x' is the pixel count from the left, higher x values mean further to the right on the screen.
|
| target_pixel_coords |
string
|
[(100, 200)]
|
Pixel values defining the final coordinates. String should be formatted as '(y, x)', where 'y' is the pixel count from the bottom, higher y values mean higher up on the screen and 'x' is the pixel count from the left, higher x values mean further to the right on the screen.
|
| learning_rate |
number
|
0.003
Min: 0.0001 Max: 0.15 |
Set the learning rate for the operation, which controls how quickly the model learns to drag the path from the initial to the final position.
|
| maximum_n_iterations |
integer
|
20
Min: 1 Max: 100 |
The maximum number of iterations allowed for the operation, limiting how long the path dragging can continue.
|
| seed |
integer
|
-1
|
Changes init image via the random seed. Set to -1 for a random seed, otherwise provide an integer value.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}