BFS H3 Duet Conditioning (prompt writer)

MiniMax H3 duet conditioning for your own sampler. The panel (the source clip) is pinned beside the video. The prompt: yours if you write one; otherwise a connected VLM writes it in the duet format from the task and instruction, looking at the clip and the references; otherwise a draft. Outputs positive + latent (with the panel's noise mask) + model (RoPE shift applied in shifted mode) + panel_info for BFS H3 Side Panel Crop. How to refer to the side panel in the prompt: the panel has NO tag (it is not <Picture n> or <Video n>; the text encoder never sees it). Name it by its place: 'the LEFT half is the kept footage' (write {layout} to insert that sentence for the current size and side). Describe only the generated part: never describe the panel's performer, clothes or room, even to contrast them; what you leave undescribed is copied from the panel. Restate the new identity in every shot ('her face from <Picture 1>' plus two or three face, hair or outfit words). Give exact times for cuts ('[Shot 2] At 00:03.708, both halves cut together to ...'). Credits: the initial idea for this H3 node came from TSC's latent-pin duet (the source pinned beside the video with a noise mask). BFS had already used the same principle on LTX (a green side panel holding the reference) and implemented the virtual sidecar approach (reference tokens placed beside the frame in RoPE). New here: the shifted RoPE layout (the video keeps its own grid and the panel sits past its edge, with an optional gap), dynamic references, task prompts and the shot-loop node.