open-mmlab/pia

Personalized Image Animator

Capabilities

Reference ImagesNegative PromptSeed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`image`*	string(uri)	Input image	`—`	—
`prompt`*	string	Input prompt.	`—`	—
`animation_length`	integer	Length of the output	`16`	min: 8, max: 24
`guidance_scale`	number	Scale for classifier-free guidance	`7.5`	min: 1, max: 20
`ip_adapter_scale`	number	Scale for classifier-free guidance	`0`	min: 0, max: 1
`max_size`	integer	Max size (The long edge of the input image will be resized to this value, larger value means slower inference speed)	`512`	5125766407047688328969601024
`motion_scale`	integer	Larger value means larger motion but less identity consistency.	`1`	min: 1, max: 3
`negative_prompt`	string	Things do not show in the output.	`"wrong white balance, dark, sketches,worst quality,low quality, deformed, distorted, disfigured, bad eyes, wrong lips, weird mouth, bad teeth, mutated hands and fingers, bad anatomy,wrong anatomy, amputation, extra limb, missing limb, floating,limbs, disconnected limbs, mutation, ugly, disgusting, bad_pictures, negative_hand-neg"`	—
`sampling_steps`	integer	Number of denoising steps	`25`	min: 10, max: 100
`seed`	integer	Random seed. Leave blank to randomize the seed	`—`	—
`style`	string	Choose a style	`"3d_cartoon"`	3d_cartoonrealistic

imagerequiredstring

Input image

promptrequiredstring

Input prompt.

animation_lengthinteger

Length of the output

Default: 16min: 8, max: 24

guidance_scalenumber

Scale for classifier-free guidance

Default: 7.5min: 1, max: 20

ip_adapter_scalenumber

Scale for classifier-free guidance

Default: 0min: 0, max: 1

max_sizeinteger

Max size (The long edge of the input image will be resized to this value, larger value means slower inference speed)

Default: 512

5125766407047688328969601024

motion_scaleinteger

Larger value means larger motion but less identity consistency.

Default: 1min: 1, max: 3

negative_promptstring

Things do not show in the output.

Default:

"wrong white balance, dark, sketches,worst quality,low quality, deformed, distorted, disfigured, bad eyes, wrong lips, weird mouth, bad teeth, mutated hands and fingers, bad anatomy,wrong anatomy, amputation, extra limb, missing limb, floating,limbs, disconnected limbs, mutation, ugly, disgusting, bad_pictures, negative_hand-neg"

sampling_stepsinteger

Number of denoising steps

Default: 25min: 10, max: 100

seedinteger

Random seed. Leave blank to randomize the seed

stylestring

Choose a style

Default: "3d_cartoon"

3d_cartoonrealistic

Version: 7a673cec329eUpdated: 7/25/2026103.5K runs