charlesmccarthy
/
lavie
- Public
- 57K runs
Run charlesmccarthy/lavie with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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
|
a Corgi walking in the park at sunrise, oil painting style
|
Prompt for video generation.
|
sample_method |
string
(enum)
|
ddpm
Options: ddim, eulerdiscrete, ddpm |
Choose a scheduler for sampling base video output.
|
width |
integer
|
512
|
Width of output video.
|
height |
integer
|
320
|
Height of output video
|
num_inference_steps |
integer
|
50
|
Number of denoising steps
|
guidance_scale |
number
|
7
|
Scale for classifier-free guidance
|
quality |
integer
|
9
Max: 10 |
Quality of the output vide0
|
seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
interpolation |
boolean
|
False
|
Default output has 16 frames. Set interpolation to True to get 61 frames output.
|
super_resolution |
boolean
|
False
|
Super resolution 4x when set to True.
|
video_fps |
integer
|
8
|
Number of frames per second in the output video
|
{
"type": "object",
"title": "Input",
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 7,
"description": "Random seed. Leave blank to randomize the seed"
},
"width": {
"type": "integer",
"title": "Width",
"default": 512,
"x-order": 2,
"description": "Width of output video."
},
"height": {
"type": "integer",
"title": "Height",
"default": 320,
"x-order": 3,
"description": "Height of output video"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "a Corgi walking in the park at sunrise, oil painting style",
"x-order": 0,
"description": "Prompt for video generation."
},
"quality": {
"type": "integer",
"title": "Quality",
"default": 9,
"maximum": 10,
"minimum": 0,
"x-order": 6,
"description": "Quality of the output vide0"
},
"video_fps": {
"type": "integer",
"title": "Video Fps",
"default": 8,
"x-order": 10,
"description": "Number of frames per second in the output video"
},
"interpolation": {
"type": "boolean",
"title": "Interpolation",
"default": false,
"x-order": 8,
"description": "Default output has 16 frames. Set interpolation to True to get 61 frames output."
},
"sample_method": {
"enum": [
"ddim",
"eulerdiscrete",
"ddpm"
],
"type": "string",
"title": "sample_method",
"description": "Choose a scheduler for sampling base video output.",
"default": "ddpm",
"x-order": 1
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 7,
"x-order": 5,
"description": "Scale for classifier-free guidance"
},
"super_resolution": {
"type": "boolean",
"title": "Super Resolution",
"default": false,
"x-order": 9,
"description": "Super resolution 4x when set to True."
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 50,
"x-order": 4,
"description": "Number of denoising steps"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "string",
"title": "Output",
"format": "uri"
}