You're looking at a specific version of this model. Jump to the model overview.
pollinations /stable-diffusion-dance:78ccb777
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 |
---|---|---|---|
prompts |
string
|
Rainbow synthesizer in mountain by Henri Rousseau
colors in the style of Henri Rousseau
Two chimney by Henri Rousseau
Pride by Henri Rousseau
Envy by Henri Rousseau
|
None
|
audio_file |
string
|
input audio file
|
|
prompt_scale |
number
|
5
|
Determines influence of your prompt on generation.
|
num_frames_per_prompt |
integer
|
128
|
Number of frames to generate per prompt (limited to a maximum of 15 for now because we are experiencing heavy use).
|
random_seed |
integer
|
42
|
Each seed generates a different image
|
diffusion_steps |
integer
|
10
|
Number of diffusion steps. Higher steps could produce better results but will take longer to generate. Maximum 30 (using K-Euler-Diffusion).
|
width |
integer
|
512
|
Width of the generated image. The model was really only trained on 512x512 images. Other sizes tend to create less coherent images.
|
height |
integer
|
512
|
Height of the generated image. The model was really only trained on 512x512 images. Other sizes tend to create less coherent images.
|
init_image |
string
|
input image
|
|
init_image_strength |
number
|
0.7
|
How strong to apply the input image. 0 means disregard the input image mostly and 1 copies the image exactly. Values in between are interesting.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}