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 |
|---|---|---|---|
| prompt |
string
|
a photorealistic chicken
|
The global prompt for generating the collage.
|
| patch_url |
string
|
https://storage.googleapis.com/dm_arnheim_3_assets/collage_patches/animals.npy
|
An .npy file for the collage patches.
|
| num_patches |
integer
|
100
|
Number of images to start with
|
| background_red |
integer
|
0
|
None
|
| background_green |
integer
|
0
|
None
|
| background_blue |
integer
|
0
|
None
|
| initial_positions |
array
|
[]
|
List of lists representing the initial positions of patches.
|
| optim_steps |
integer
|
250
|
Number of optimization steps to run during collage generation.
|
| loss |
string
(enum)
|
CLIP
Options: CLIP, MSE, Multi-region MSE |
Loss function to optimize the collage. Choose between CLIP and MSE.
|
| target_image |
string
|
Upload an image file for MSE loss. Required if loss is set to MSE.
|
|
| target_image2 |
string
|
Second target image for MSE loss.
|
|
| blend_ratio |
number
|
0.5
|
Blending ratio between target images (0.0 = only first image, 1.0 = only second image).
|
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'}