You're looking at a specific version of this model. Jump to the model overview.
pollinations /stable-diffusion-dance:861f0c74
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
|
A lively and whimsical apothecary where chrome robots shop grows from the stalk of a giant mushroom"
A lively and whimsical dark apothecary shop, cinematic framing, rain lit, chrome robots on single wheels shop, the shop grows from the stalk of a giant mushroom
Surreal gouache painting, by yoshitaka amano, by ruan jia, by conrad roset, by kilian eng, by good smile company, detailed anime 3 d render of floating molecules and a robot artist holding an icosahedron with stars, clouds, and rainbows in the background
|
None
|
style_suffix |
string
|
retrofuturism. artwork by roger dean, by dean ellis
|
Style suffix to add to the prompt. This can be used to add the same style to each prompt.
|
audio_file |
string
|
input audio file
|
|
prompt_scale |
number
|
15
|
Determines influence of your prompt on generation.
|
random_seed |
integer
|
13
|
Each seed generates a different image
|
diffusion_steps |
integer
|
20
|
Number of diffusion steps. Higher steps could produce better results but will take longer to generate. Maximum 30 (using K-Euler-Diffusion).
|
audio_smoothing |
number
|
0.7
|
Audio smoothing factor.
|
audio_noise_scale |
number
|
0.15
|
Larger values mean audio will lead to bigger changes in the image.
|
audio_loudness_type |
string
(enum)
|
peak
Options: rms, peak |
Type of loudness to use for audio. Options are 'rms' or 'peak'.
|
frame_rate |
integer
|
10
|
Frames per second for the generated video.
|
width |
integer
|
384
|
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.
|
batch_size |
integer
|
24
|
Number of images to generate at once. Higher batch sizes will generate images faster but will use more GPU memory i.e. not work depending on resolution.
|
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'}