facefusion/facefusion

Face fusion model that swaps faces from source images onto a target video, producing a video with seamlessly blended facial features.

$1 / request
GPU: A100

Pricing

facefusion/

facefusion

Pricing for Synexa AI models works differently from other providers. Instead of being billed by time, you are billed by input and output, making pricing more predictable.

Output
$1.0000 / video
or
1 videos / $1

For example, generating 100 videos should cost around $100.00.

Check out our docs for more information about how per-request pricing works on Synexa.

ProviderPrice ($)Saving (%)
Synexa$1.0000-
replicate$2.000050.0%

Readme

Given source face images and a target video, the face fusion model automatically detects and replaces faces in the video with faces from the source images. The result is a video where the swapped faces blend naturally with the target video's appearance and lighting.

Limitations:

  • Face contours should be complete without significant occlusion
  • Supports face lateralization up to approximately 30 degrees
  • Face size should be at least 64x64 pixels
  • Face area should not exceed 2/3 of the frame
  • Large differences in face shape between source and target may affect edge blending