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

ailoov /video_postpro_v2:cf0e94b4

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
face_detector_model
None
yolo_face
Model face detector
face_selector_mode
None
one
Face selector mode
face_selector_order
None
large-small
Face selector order
pingpong
None
no
Mode pingpong video (no=tanpa pingpong, short=1x pingpong, long=loop minimal 30 detik)
uid
string
UID unik untuk penamaan file sementara (opsional)
source
string
Source image (wajah yang akan di-swap ke target)
target
string
Target image atau video yang akan diproses
upscale
boolean
False
Upscale akhir video ke 1080x1920 (Lanczos). Jika False, hanya re-encode ke H.264 tanpa ubah resolusi.
rembg_hex
string
#00b140
Hex color untuk background replacement (kosongkan untuk transparent background)
processors
string
face_swapper
Processors yang akan digunakan (comma-separated: face_swapper,expression_restorer,face_enhancer)
rembg_enabled
boolean
False
Aktifkan background removal menggunakan Inspyrenet Rembg
face_mask_blur
number
0.8

Max: 1

Face mask blur (0.0-1.0)
face_mask_types
string
box,occlusion,region
Face mask types (comma-separated: box,occlusion,area,region)
output_image_scale
number
1

Min: 0.1

Max: 2

Output image scale
face_detector_score
number
0.5

Max: 1

Face detector score threshold
face_enhancer_blend
integer
80

Max: 100

Face enhancer blend (0-100)
face_enhancer_model
string
gpen_bfr_512
Model face enhancer (default: gpen_bfr_512, preloaded)
face_swapper_weight
number
1

Max: 1

Weight untuk face swapper (0.0-1.0, default: 1.0 untuk swap penuh)
face_enhancer_weight
number
0.5

Max: 1

Face enhancer weight (0.0-1.0)
output_image_quality
integer
80

Max: 100

Output image quality (0-100)
reference_face_distance
number
0.6

Max: 1

Reference face distance threshold
reference_face_position
integer
0
Reference face position
expression_restorer_areas
string
upper-face,lower-face
Expression restorer areas (comma-separated: upper-face,lower-face)

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}