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
|
generate an image of the fierce battle of warriors and the dragon
|
Input prompt
|
| negative_prompt |
string
|
lowres, bad anatomy, bad hands, cropped, worst quality
|
Specify things to not see in the output
|
| image_width |
integer
|
896
|
Width of output image
|
| image_height |
integer
|
1152
|
Height of output image
|
| num_inference_steps |
integer
|
25
Min: 1 Max: 100 |
Number of denoising steps
|
| guidance_scale |
number
|
5
Min: 1 Max: 32 |
Scale for classifier-free guidance
|
| temperature |
number
|
0.6
Max: 2 |
Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic
|
| top_p |
number
|
0.9
Max: 1 |
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
|
| max_new_tokens |
integer
|
4096
Min: 128 Max: 4096 |
Maximum number of tokens to generate
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'code': {'title': 'Code', 'type': 'string'},
'image': {'format': 'uri', 'title': 'Image', 'type': 'string'}},
'required': ['code', 'image'],
'title': 'ModelOutput',
'type': 'object'}