You're looking at a specific version of this model. Jump to the model overview.
adirik /masactrl-stable-diffusion-v1-4:4e86d80a
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 |
|---|---|---|---|
| source_image |
string
|
Image to edit for image editing mode.
|
|
| source_prompt |
string
|
Prompt for the first image for consistent image synthesis mode
|
|
| target_prompt |
string
|
If consistent image syhnthesis mode, prompt for the second image. If image editing mode, prompt for the target image.
|
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| num_inference_steps |
integer
|
50
Min: 1 Max: 100 |
Number of denoising steps
|
| masactrl_start_step |
integer
|
4
Min: 1 Max: 100 |
The step to start mutual self-attention control. It should be lower than num_inference_steps
|
| masactrl_start_layer |
integer
|
10
Min: 1 Max: 16 |
The layer to start mutual self-attention control
|
| seed |
integer
|
Random seed.A random seed will be used if not provided.
|
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'}