This is an AI video generation application based on SCAIL 2 SAM3 Dual-Subject Tracking Dual-Skeleton Guiding Dual-Character Replacement Long-Video Loop Writing.
Users only need to upload a dual-subject reference image and a dual-subject driving video. The system will automatically identify the actions of the two characters in the driving video and replace them with the two characters from the reference image in the corresponding positions in the driving video.
Unlike ordinary single-character replacement or image-to-video generation, this process is specifically designed for dual-character videos. It uses SAM3 to simultaneously track two subjects and maintains left-to-right identity correspondence, reducing common issues in dual-character videos such as replacing only one character, losing the second character, swapping left and right identities, character drifting, and action misalignment.
The entire process is automated: driving video reading, reference image size unification, driving video size unification, dual-subject recognition, dual-mask generation, SCAIL 2 dual-character replacement, initial segment generation, loop writing, overlapping frame processing, color matching, frame sequence merging, original video audio integration, and final video output.
The final output is a long dual-character replacement video that not only inherits the actions, rhythm, and shot structure of the driving video but also strives to maintain the identities, appearances, clothing, and left-right relationships of the two characters in the reference image.
If packaged as a RunningHub application, the core selling point can be directly expressed as:
Upload a dual-subject reference image and a dual-subject driving video, and generate a long dual-character replacement video with one click.


No creations yet

No creations available.