You're looking at a specific version of this model. Jump to the model overview.
afiaka87 /clip-guided-diffusion:a9650e4b
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.
|
|
| init_image |
string
|
an image to blend with diffusion before clip guidance begins. Uses half as many timesteps.
|
|
| respace |
string
(enum)
|
250
Options: 25, 50, 100, 200, 250, ddim25, ddim50, ddim100, ddim200, ddim250 |
Number of timesteps. Fewer is faster, but less accurate.
|
| clip_guidance_scale |
integer
|
1000
Max: 2500 |
Scale for CLIP spherical distance loss. Values will need tinkering for different settings.
|
| tv_scale |
number
|
50
Max: 250 |
Scale for a denoising loss that effects the last half of the diffusion process. 0, 100, 150 and 200
|
| range_scale |
number
|
50
Max: 250 |
Controls how far out of RGB range values may get.
|
| sat_scale |
number
|
0
Max: 128 |
Controls how much saturation is allowed. Use for ddim. From @nshepperd.
|
| use_augmentations |
boolean
|
False
|
Whether to use augmentation during prediction. May help with ddim and respacing <= 100.
|
| use_magnitude |
boolean
|
False
|
Use the magnitude of the loss. May help (only) with ddim and respacing <= 100
|
| 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'}