Live Portrait

Transfer expression from a video to a portrait.

Inference$ Commercial useFrom 1 credit per run

About Live Portrait

Transfer expression from a video to a portrait.

expressionanimation

Pricing

A run with the default settings costs 1 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

image_urlfilerequired

URL of the image to be animated

blinknumberdefault: 0

Amount to blink the eyes

eyebrownumberdefault: 0

Amount to raise or lower eyebrows

winknumberdefault: 0

Amount to wink

pupil_xnumberdefault: 0

Amount to move pupils horizontally

pupil_ynumberdefault: 0

Amount to move pupils vertically

aaanumberdefault: 0

Amount to open mouth in 'aaa' shape

eeenumberdefault: 0

Amount to shape mouth in 'eee' position

woonumberdefault: 0

Amount to shape mouth in 'woo' position

smilenumberdefault: 0

Amount to smile

rotate_pitchnumberdefault: 0

Amount to rotate the face in pitch

rotate_yawnumberdefault: 0

Amount to rotate the face in yaw

rotate_rollnumberdefault: 0

Amount to rotate the face in roll

flag_pastebackbooleandefault: true

Whether to paste-back/stitch the animated face cropping from the face-cropping space to the original image space.

flag_do_cropbooleandefault: true

Whether to crop the source portrait to the face-cropping space.

flag_do_rotbooleandefault: true

Whether to conduct the rotation when flag_do_crop is True.

flag_lip_zerobooleandefault: true

Whether to set the lip to closed state before animation. Only takes effect when flag_eye_retargeting and flag_lip_retargeting are False.

dsizeintegerdefault: 512

Size of the output image.

scalenumberdefault: 2.3

Scaling factor for the face crop.

vx_rationumberdefault: 0

Horizontal offset ratio for face crop.

vy_rationumberdefault: -0.125

Vertical offset ratio for face crop. Positive values move up, negative values move down.

enable_safety_checkerbooleandefault: false

Whether to enable the safety checker. If enabled, the model will check if the input image contains a face before processing it. The safety checker will process the input image

output_formatselectdefault: "jpeg"

Output format

Options: jpeg, png

More from Live Portrait

Live Portrait

Transfer expression from a video to a portrait.

expressionanimation

image-to-video

Related image to image models

Nano Banana Pro

Nano Banana Pro is Google's new state-of-the-art image generation and editing model

realismtypography

image-to-image

Nano Banana 2

Nano Banana 2 is Google's new state-of-the-art image generation and editing model

image-to-image

Nano Banana 2.1 Edit

Nano Banana 2.1 Edit by Google transforms reference images using text instructions, with output resolutions up to 4K and optional video or PDF context.

image editingimage to image

image-to-image

GPT Image 2.5 Sunburst Edit

Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.

stylizedtransform

image-to-image

✦ new

GPT Image 2.6 Sunburst Edit

Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.

stylizedtransform

image-to-image

GPT Image 2 API

GPT Image 2, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.

gpt-image-2openai

image-to-image

Birefnet Background Removal V2

bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)

background removalsegmentation

image-to-image

Nano Banana

Google's famous original image generation and editing model

image-editing

image-to-image

GPT Image 2.5 Flare Edit

Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.

stylizedtransform

image-to-image

✦ new

GPT Image 2.6 Flare Edit

Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.

stylizedtransform

image-to-image

Seedream 5.0 Pro Image Editing

Seedream 5.0 Pro is grounded, region-precise image editing model that changes one element while keeping the rest of the frame intact with layer separation, sketch completion, and up to 10 reference images.

realismtypography

image-to-image

SeedVR2

Use SeedVR2 to upscale your images

upscale

image-to-image