SCAIL 2 Multi-reference Character Replacement

This is an AI video generation application based on SCAIL 2, WanAnimatePlus, SAM3 Three-Person Tracking, and Multi-Reference Image Character Replacement.

Users only need to upload a three-person driving video, then upload a main reference image for the three persons, and optionally add multiple supplemental reference images A, B, and a background image. The system will automatically recognize the movements of the three individuals in the driving video and replace them with the characters from the reference images in the corresponding positions.

Unlike ordinary single-image character replacement, this process supports the participation of multiple reference images for character replacement. The main reference image is used to determine the basic identities of the three characters and their left/middle/right correspondence. Supplemental reference images enhance facial features, clothing, body proportions, pose angles, and detail stability. The background image can be used to control the final scene style.

The entire process is automated: driving video reading, video size standardization, three-person main reference image processing, multi-reference image processing, background image processing, SAM3 three-person subject recognition, left-middle-right character mask generation, multi-reference image batching, SCAIL 2 conditional fusion, WanAnimatePlus sampling generation, video decoding, frame interpolation, and final video output.

The result is a three-person character replacement video that inherits the actions, rhythm, and camera structure of the driving video while maintaining the identity, clothing, appearance, and left/right positional stability of the three characters in the reference images as much as possible.

It is suitable for three-person replacement videos, three-person dance videos, multi-character replacement, group digital human videos, AI team showcases, short drama character replacement, advertisement model replacement, group motion transfer, multi-reference character consistency videos, and RunningHub video application packaging.

If packaged as a RunningHub application, the core selling point can be directly expressed as:

Upload a three-person driving video and multiple reference images, and generate a stable three-person character replacement video with one click.