This is an AI video generation application based on SCAIL 2, SAM3 dual-subject tracking, dual-skeleton motion guidance, and loop continuation.
Users only need to upload a dual-subject or dual-person reference image and a dual-person driving video. The system will automatically identify the actions of the two subjects in the driving video and make the two characters in the reference image follow the video to complete motion transfer.
Unlike ordinary single-person image-to-video workflows, this process is specifically designed for dual-person/dual-subject scenarios. It uses SAM3 to track two subjects simultaneously and maintains the left-to-right relationship of the roles, reducing common issues in dual-person videos such as role swapping, missing characters, identity drift, and motion 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 skeletal motion guidance, initial segment generation, loop continuation, overlapping frame processing, color matching, frame sequence merging, and final video output.
The final output is a dual-subject motion video, suitable for dual-person dance, dual-character interaction, dual-person motion transfer, dual-person short plays, dual-character showcases, AI dance videos, animal or anthropomorphic character motion guidance, and packaging for RunningHub video applications.
If packaged as a RunningHub application, the core selling point can be directly expressed as:
Upload a dual-person reference image and a dual-person driving video to generate an AI video with synchronized dual-character motions in one click.


No creations yet

No creations available.