Enforce Scene Rules

Post-LLM cleanup pass that mirrors Andy's three reels-generator enforcers (normalize_solid_bg_color + enforce_collage_min_duration + enforce_scene_composition). Caps solid narration to ≤7 words, collapses consecutive solids, trims trailing solid clusters to the CTA, bumps ai_2/ai_3 to ≥0.4s/rect, and keeps at most 2 videos as ai_1 (rest → ai-asset-fullscreen + speed_ramp). Wire between scene_def_generator and scenes_to_tts so TTS audio reflects the corrected narration.

Try Enforce Scene Rules in the playground

Last updated View as MarkdownAgent setup

Enforce Scene Rules

Node type: utility:enforce_scene_rules
Category: Scene Pipeline

Description

Enforce Scene Rules is a post-LLM cleanup pass for your scene list in the Scene Pipeline: connect your scenes text to the required Scenes JSON port, and the fixed list comes out of Corrected Scenes as JSON. It caps solid narration to 7 words or fewer, collapses consecutive solids, trims trailing solid clusters to the CTA, bumps ai_2 and ai_3 to at least 0.4s per rect, and keeps at most 2 videos as ai_1, turning the rest into ai-asset-fullscreen with speed_ramp. Wire it between scene_def_generator and scenes_to_tts so the TTS audio reflects the corrected narration. The node has no sidebar config fields, so the scenes you wire in are its only input.

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
scenes Scenes JSON TEXT (required)

These render as form fields in the right-side config panel when the node is selected.

No sidebar config fields.

Outputs

ID Label Type
scenes Corrected Scenes JSON

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.