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

zsxkib /animate-diff-scene-assembler:90c322f1

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
"0" :"a (chrome:1.1) cyborg robot dance (white science lab:1.1)", "70" :"a (chrome:1.1) cyborg robot dance(red led blinksp:1.1) (white science lab:1.1)"
Input prompt
negative_prompt
string
embedding:easynegative, (worst quality, low quality: 1.3), zombie, horror, distorted, photo, nfsw
Input Negative Prompt
first_num_inference_steps
integer
15

Min: 1

Max: 50

Number of denoising steps
first_guidance_scale
number
7.5

Min: 1

Max: 50

Scale for classifier-free guidance
second_num_inference_steps
integer
22

Min: 1

Max: 50

Second pass, for video interoplation. Number of denoising steps
second_guidance_scale
number
8.5

Min: 1

Max: 50

Second pass, for video interoplation. Scale for classifier-free guidance
pose_video
string
Video of a subject doing something fun or interesting, this video will be used to track any people and their pose estimations for the final video
subject_image
string
An image of what the subject should look like in the final video
subject_controlnet_strength
number
0.2

Max: 1

Strength of the controlnet for the subject/character image
background_image
string
An image of what the background should look like in the final video
background_controlnet_strength
number
0.6

Max: 1

Strength of the controlnet for the background image
return_temp_files
boolean
False
Return any temporary files, such as preprocessed controlnet images. Useful for debugging.
randomise_seeds
boolean
True
Automatically randomise seeds (seed, noise_seed, rand_seed)

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'}