You're looking at a specific version of this model. Jump to the model overview.

andreasjansson /stable-diffusion-animation:fc5f8698

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_start
string
Prompt to start the animation with
prompt_end
string
Prompt to end the animation with. You can include multiple prompts by separating the prompts with | (the 'pipe' character)
width
integer (enum)
512

Options:

128, 256, 512, 768, 1024

Width of output image
height
integer (enum)
512

Options:

128, 256, 512, 768

Height of output image
num_inference_steps
integer
50

Min: 1

Max: 500

Number of denoising steps
prompt_strength
number
0.8
Lower prompt strength generates more coherent gifs, higher respects prompts more but can be jumpy
num_animation_frames
integer
10

Min: 2

Max: 50

Number of frames to animate
num_interpolation_steps
integer
5

Min: 1

Max: 50

Number of steps to interpolate between animation frames
guidance_scale
number
7.5

Min: 1

Max: 20

Scale for classifier-free guidance
gif_frames_per_second
integer
20

Min: 1

Max: 50

Frames/second in output GIF
gif_ping_pong
boolean
False
Whether to reverse the animation and go back to the beginning before looping
film_interpolation
boolean
True
Whether to use FILM for between-frame interpolation (film-net.github.io)
intermediate_output
boolean
False
Whether to display intermediate outputs during generation
seed
integer
Random seed. Leave blank to randomize the seed
output_format
string (enum)
gif

Options:

gif, mp4

Output file format

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'}