Director — Story-to-Video Production Pipeline

Director — Story-to-Video Production Pipeline

Overview

The Director skill runs a complete short film production from a text story. It breaks the story into scenes, generates start/end frames for each, creates video clips from frame pairs, and concatenates everything into a final video.

The pipeline runs Story Planning → Z-Image Hero + Character Refs → Qwen Edit Chain (all frames) → WAN 2.2 FLF Video Clips → ffmpeg Concatenation.

Key architectural decisions:

• 1 hero frame + edit chain for character consistency (NEVER independent Z-Image per scene)
• Inter-scene frame continuity. Scene N's end frame IS Scene N+1's start frame (same image file, no edit gap)
• Character reference images fed into Qwen Edit's extra image slots
• State file persists to disk for context compaction survival
• Each scene is independently retryable without affecting others
• clear_vram between every model family switch

CRITICAL: Inspect modes + verify every output

This pipeline drives the user's live canvas across many stages, so two habits are non-negotiable:

• Inspect node modes before each render. After loading any pack/template/subgraph and before panel_run, check each node's mode (panel_graph_outline marks [bypass]/[mute]; panel_query_graph detail rows carry it). A bypass node is skipped (passes input through); a mute node and everything downstream don't execute. If the path, branch, or switch you need is bypassed or muted, enable it with panel_set_node_mode (set the wanted node active, the unwanted one bypass/mute). Never assume a switch or route is already active.
• Verify the output matches before moving on. Every Phase-N render is a gate. Look at the produced frame or clip (view it) and confirm it matches the intent BEFORE advancing or reporting progress. If it's wrong, diagnose (wrong prompt path? a bypassed/muted builder or switch? wrong widget? wrong ref image?), fix, and rerun. Do NOT declare a phase done or report progress you haven't verified.
• Confirm VIDEO renders via the filesystem, not /history. For a VHS_VideoCombine / LTX / WAN clip, do NOT rely on get_history / queue (action:"status") to confirm it exists. VHS-style video nodes write the .mp4 but frequently do NOT register an output in ComfyUI's /history (prompt shows done, empty outputs, no error). Confirm the file with get_image (action:"list_outputs") (now lists videos too, tagged kind: "video") by filename_prefix + fresh mtime, then chain it forward with upload_image (action:"stage").
• Bypass completed stages before queuing the next one. If you build the multi-stage pipeline on ONE canvas (e.g. Krea2 → LTX → WAN) rather than running each phase in isolation, once a stage has run and its output is captured/staged, panel_set_node_mode(mode:"bypass") that stage's nodes BEFORE you panel_run the next stage. Otherwise panel_run re-executes the whole graph and you pay for and wait on already-finished work, a real and costly failure mode. Keep only the active stage live; feed the prior output forward with upload_image (action:"stage") (bypass the producer, feed its captured output to the consumer's loader).

CRITICAL: Character Consistency

Independent Z-Image generations per scene produce different-looking characters. This was the #1 problem discovered during testing. The solution:

1. Generate ONE hero frame with Z-Image. It establishes the main character, setting, and lighting
2. Generate character reference images: close-up portraits of each character, key props, and the background
3. Create ALL other scene frames via the Qwen Edit chain from the hero, with character refs in extra image slots
4. This keeps the same face, clothing, and environment across every frame

8-Phase Pipeline

Phase 1: Story Planning       → Break story into scenes (Claude reasoning, no ComfyUI)
Phase 2: Hero + Refs          → Z-Image: 1 hero frame + character ref portraits + background ref
Phase 3: Hero Review          → Visual verify hero and refs, user approves