You're looking at a specific version of this model. Jump to the model overview.
vivalapanda /conceptual-image-to-image-1.5:738154b9
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
|
|
Input prompt
|
| init_image |
string
|
Inital image to provide structural or conceptual guidance
|
|
| captioning_model |
None
|
blip
|
Captioning model to use. One of 'blip' or 'clip-interrogator-v1'
|
| structural_image_strength |
number
|
0.15
|
Structural (standard) image strength. 0.0 corresponds to full destruction of information, and does not use the initial image for structure.
|
| conceptual_image_strength |
number
|
0.4
|
Conceptual image strength. 0.0 doesn't use the image conceptually at all, 1.0 only uses the image concept and ignores the prompt.
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
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'}