missalignment problem

Thanks for opening source such great work! I have a problem about the missalignment between the generated video and the input low quality video. According to the largest_8n1_leq function the length of the low quallity video is 8n+1, while the length of the noise input to the diffusion model is 2n, corresponding to 8n-3 frames of the generated video. Moreover, the first 6 noise takes first 25 frames of low quality video as condition and each subsequent noise corresponds to 4 frames of low-resolution video. 8n+1 frames of low quality video are needed as input to the diffusion model. While when the latents are converted into video by the TCDecoder, only 8n-3 frames of low quality video are needed. Why is there a missalignment between the input video and the generated video?

Trace the frame indexing from largest_8n1_leq in examples/WanVSR/infer_flashvsr_v1.1_tiny.py, then compare it with the TCDecoder call in diffsynth/pipelines/flashvsr_tiny.py. Reproduce the stated 8n+1 versus 8n-3 inputs and determine whether the difference is intentional or an alignment bug. Done means the frame mapping is explained and any required correction is covered by a reproducible check.