ductridev
/
animate-diff
Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
Run ductridev/animate-diff 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 |
|---|---|---|---|
| model |
string
(enum)
|
ToonYou
Options: ToonYou, Lyriel, RcnzCartoon, MajicMix, RealisticVision, Tusun, FilmVelvia, GhibliBackground, Genshen Impact-Yoimiya |
Model to run. All model provide at civitai.com text-to-image models
|
| motion_model |
string
(enum)
|
Motion V14 Checkpoint
Options: Motion V14 Checkpoint, Motion V15 Checkpoint |
Model to run. All model provide at civitai.com text-to-image models
|
| additional_model |
string
(enum)
|
None
Options: None, Hold Sign |
Additional model to combine with main model.
|
| init_image |
string
|
Init image
|
|
| prompt |
string
|
anime
|
The prompt or prompts to guide the video generation.
|
| negative_prompt |
string
|
noise, text, nude
|
The prompt or prompts not to guide the video generation.
|
| cfg_scale |
number
|
9
Min: 1 Max: 20 |
Scale for classifier-free guidance (minimum: 1; maximum: 20)
|
| height |
integer
|
512
Min: 512 |
Height of the generated video
|
| width |
integer
|
512
Min: 512 |
Width of the generated video
|
| num_inference_steps |
integer
|
25
Min: 1 Max: 500 |
Number of denoising steps (minimum: 1; maximum: 500)
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| lora_alpha |
number
|
0.6
Min: 0.1 Max: 1 |
scaling factor for the weight matrices
|
| nums_frame |
integer
|
16
Min: 8 |
Number frames of video
|
| fps |
integer
|
24
|
fps for the output video
|
{
"type": "object",
"title": "Input",
"properties": {
"fps": {
"type": "integer",
"title": "Fps",
"default": 24,
"x-order": 13,
"description": "fps for the output video"
},
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 10,
"description": "Random seed. Leave blank to randomize the seed"
},
"model": {
"enum": [
"ToonYou",
"Lyriel",
"RcnzCartoon",
"MajicMix",
"RealisticVision",
"Tusun",
"FilmVelvia",
"GhibliBackground",
"Genshen Impact-Yoimiya"
],
"type": "string",
"title": "model",
"description": "Model to run. All model provide at civitai.com text-to-image models",
"default": "ToonYou",
"x-order": 0
},
"width": {
"type": "integer",
"title": "Width",
"default": 512,
"minimum": 512,
"x-order": 8,
"description": "Width of the generated video"
},
"height": {
"type": "integer",
"title": "Height",
"default": 512,
"minimum": 512,
"x-order": 7,
"description": "Height of the generated video"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "anime",
"x-order": 4,
"description": "The prompt or prompts to guide the video generation."
},
"cfg_scale": {
"type": "number",
"title": "Cfg Scale",
"default": 9,
"maximum": 20,
"minimum": 1,
"x-order": 6,
"description": "Scale for classifier-free guidance (minimum: 1; maximum: 20)"
},
"init_image": {
"type": "string",
"title": "Init Image",
"format": "uri",
"x-order": 3,
"description": "Init image"
},
"lora_alpha": {
"type": "number",
"title": "Lora Alpha",
"default": 0.6,
"maximum": 1,
"minimum": 0.1,
"x-order": 11,
"description": "scaling factor for the weight matrices"
},
"nums_frame": {
"type": "integer",
"title": "Nums Frame",
"default": 16,
"minimum": 8,
"x-order": 12,
"description": "Number frames of video"
},
"motion_model": {
"enum": [
"Motion V14 Checkpoint",
"Motion V15 Checkpoint"
],
"type": "string",
"title": "motion_model",
"description": "Model to run. All model provide at civitai.com text-to-image models",
"default": "Motion V14 Checkpoint",
"x-order": 1
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"default": "noise, text, nude",
"x-order": 5,
"description": "The prompt or prompts not to guide the video generation."
},
"additional_model": {
"enum": [
"None",
"Hold Sign"
],
"type": "string",
"title": "additional_model",
"description": "Additional model to combine with main model.",
"default": "None",
"x-order": 2
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 25,
"maximum": 500,
"minimum": 1,
"x-order": 9,
"description": "Number of denoising steps (minimum: 1; maximum: 500)"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
{
"type": "string",
"title": "Output",
"format": "uri"
}