You're looking at a specific version of this model. Jump to the model overview.
afiaka87/laionide-v4:b21cbe27
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
|
Prompt to use.
|
|
| style_prompt |
string
(enum)
|
<pixelart>
Options: <pixelart>, <cc12m>, <pokemon>, <country211>, <openimages>, <ffhq>, <coco>, <vaporwave>, <virtualgenome>, <imagenet> |
Additional style guidance to use. Handles any sequence of tokens, but works particularly well on the listed pretrained 'dataset tokens'.
|
| batch_size |
integer
|
1
Min: 1 Max: 8 |
Batch size. Number of generations to predict
|
| side_x |
string
(enum)
|
64
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 |
string
(enum)
|
64
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
|
If true, uses both the base and upsample models. If false, only the (finetuned) base model is used.
|
| upsample_temp |
string
(enum)
|
0.997
Options: 0.996, 0.997, 0.998, 0.999, 1.0 |
Upsample temperature. Consider lowering to ~0.997 for blurry images with fewer artifacts.
|
| 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.
|
| style_guidance_scale |
number
|
4
|
Same as guidance scale, but applied to glide model outputs from the style prompt instead of the prompt.
|
| timestep_respacing |
string
(enum)
|
27
Options: 15, 17, 19, 21, 23, 25, 27, 30, 35, 40, 50, 100 |
Number of timesteps to use for base model PLMS sampling. Usually don't need more than 50.
|
| sr_timestep_respacing |
string
(enum)
|
17
Options: 15, 17, 19, 21, 23, 25, 27 |
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.
{'format': 'uri', 'title': 'Output', 'type': 'string'}