You're looking at a specific version of this model. Jump to the model overview.
daanelson /plug_and_play_image_translation:c88bde4d
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 |
|---|---|---|---|
| input_image |
string
|
Image to edit (instead of generation prompt
|
|
| generation_prompt |
string
|
|
Edit an image generated from this prompt (Input image is ignored if this is supplied)
|
| scale |
number
|
10
|
unconditional guidance scale. Note that a higher value encourages deviation from the source image (10 is the default for tranlsation from image 7.5 for text
|
| feature_injection_threshold |
number
|
0.8
Max: 1 |
Control the level of structure preservation. What timestep to stop Injecting the saved features into the translation diffusion process. (0 is first and 1 is final timestep meaning more preservation)
|
| translation_prompts |
string
|
a photo of a robot horse
|
Text to Image prompts. A list of edit texts (separated by ';') an image will be output for each edit txt
|
| negative_prompt |
string
|
|
Control the level of deviation from the source image
|
| negative_prompt_alpha |
number
|
1
Max: 1 |
Strength of the effect of the negative prompt (lower is stronger)
|
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'}