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
|
|
Text prompt to use.
|
| batch_size |
integer
|
3
Min: 1 Max: 6 |
Batch size. Number of generations to predict
|
| side_x |
integer
(enum)
|
Options: 32, 48, 64, 80, 96, 112, 128 |
Must be multiple of 8. Going above 64 is not recommended. Actual image will be 4x larger.
|
| side_y |
integer
(enum)
|
Options: 32, 48, 64, 80, 96, 112, 128 |
Must be multiple of 8. Going above 64 is not recommended. Actual image size will be 4x larger.
|
| upsample_stage |
boolean
|
True
|
Performs prompt-aware upsampling by 4x base resolution
|
| guidance_scale |
number
|
4.0
|
Classifier-free guidance scale. Higher values move further away from unconditional outputs. Lower values move closer to unconditional outputs. Negative values guide towards semantically opposite classes. 4-16 is a reasonable range.
|
| upsample_temp |
number
(enum)
|
Options: 0.997, 0.998, 1.0 |
Upsample temperature. Consider lowering to ~0.997 for blurry images with fewer artifacts.
|
| timestep_respacing |
string
(enum)
|
27
Options: 5, 10, 15, 20, 25, 27, fast27, 30, 35, 40, 45, 50, 75, 100, 125, 150 |
Number of timesteps to use for base model. Going above 150 has diminishing returns.
|
| sr_timestep_respacing |
string
(enum)
|
17
Options: 5, 10, 15, 17, 19, 20, 21, 23, 25, 27, fast27, 30, 35, 40, 45, 50, 75, 100, 125, 150 |
Number of timesteps to use for base model. Going above 150 has diminishing returns.
|
| seed |
integer
|
0
|
Seed for reproducibility
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'properties': {'file': {'format': 'uri',
'type': 'string',
'x-order': 0},
'text': {'type': 'string', 'x-order': 1}},
'type': 'object'},
'type': 'array',
'x-cog-array-type': 'iterator'}