variable (per frame) IP Adapter weights in video

is there a (planned or existing) way to have variable IP Adapter weights for videos (e.g. with AnimateDiff)?
that means setting different values for different frames, as both scaling and masking currently seem to work with the whole generation at once (be it video or still image).

The issue names no files, tests, or entry points; begin by checking the existing IP Adapter scaling and masking paths used with AnimateDiff video generation. Done would require determining whether per-frame weights are supported, or defining the implementation scope if they are not.

Vom Indexierungsmodell aus dem Issue-Text verfasst.