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. Keep it simple/literal and avoid using poetic language (unlike CLIP).
|
|
| batch_size |
integer
|
3
Min: 1 Max: 8 |
Batch size. Number of generations to predict
|
| side_x |
None
|
64
|
Must be multiple of 8. Going above 64 is not recommended. Actual image will be 4x larger.
|
| side_y |
None
|
64
|
Must be multiple of 8. Going above 64 is not recommended. Actual image will be 4x larger.
|
| upsample_stage |
boolean
|
False
|
If true, uses both the base and upsample models. If false, only the (finetuned) base model is used. This is useful for testing the upsampler, which is not finetuned.
|
| guidance_scale |
number
|
4
|
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 |
None
|
0.998
|
Upsample temperature. Consider lowering to ~0.997 for blurry images with fewer artifacts.
|
| timestep_respacing |
None
|
35
|
Number of timesteps to use for base model PLMS sampling. Usually don't need more than 50.
|
| sr_timestep_respacing |
None
|
17
|
Number of timesteps to use for upsample model PLMS sampling. Usually don't need more than 20.
|
| seed |
integer
|
0
|
Seed for reproducibility
|
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',
'x-cog-array-type': 'iterator'}