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
|
|
Your text prompt.
|
| negative |
string
|
|
(optional) Negate the model's prediction for this text from the model's prediction for the target text.
|
| init_image |
string
|
(optional) Initial image to use for the model's prediction. If provided alongside a mask, the image will be inpainted instead.
|
|
| mask |
string
|
a mask image for inpainting an init_image. white pixels = keep, black pixels = discard. resized to width = image width/8, height = image height/8
|
|
| guidance_scale |
number
|
5
Min: -20 Max: 100 |
Classifier-free guidance scale. Higher values will result in more guidance toward caption, with diminishing returns. Try values between 1.0 and 40.0. In general, going above 5.0 will introduce some artifacting.
|
| steps |
integer
|
50
Min: 15 Max: 250 |
Number of diffusion steps to run. Due to PLMS sampling, using more than 100 steps is unnecessary and may simply produce the exact same output.
|
| batch_size |
integer
|
4
Min: 1 Max: 16 |
Batch size. (higher = slower)
|
| width |
integer
(enum)
|
256
Options: 128, 192, 256, 320, 384 |
Target width
|
| height |
integer
(enum)
|
256
Options: 128, 192, 256, 320, 384 |
Target height
|
| init_skip_fraction |
number
|
0
Max: 1 |
Fraction of sampling steps to skip when using an init image. Defaults to 0.0 if init_image is not specified and 0.5 if init_image is specified.
|
| aesthetic_rating |
integer
|
9
|
Aesthetic rating (1-9) - embed to use.
|
| aesthetic_weight |
number
|
0.5
|
Aesthetic weight (0-1). How much to guide towards the aesthetic embed vs the prompt embed.
|
| seed |
integer
|
-1
Min: -1 Max: 4294967295 |
Seed for random number generator. If -1, a random seed will be chosen.
|
| intermediate_outputs |
boolean
|
False
|
Whether to return intermediate outputs. Enable to visualize the diffusion process and/or debug the model. May slow down inference.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'items': {'format': 'uri', 'type': 'string'}, 'type': 'array'},
'title': 'Output',
'type': 'array',
'x-cog-array-type': 'iterator'}