Nodes/ComfyUI-H3-Planner/H3 Story Planner
ComfyUI Node

H3 Story Planner

A ComfyUI node in H3 Planner with 25 inputs and 3 outputs.

By AIJigyasa·Created 2 days ago·Updated 2 days ago· 1
H3 Story Planner
  • project
  • cast
  • timeline
  • beat_sheet
  • report
idea
total_seconds30.0
min_segment_seconds5.0
max_segment_seconds10.0
formatcinematic ad
dialogueauto
audio_roleperformed on camera
window4
single_call_max8
chain_first_framesfalse
providerOllama (Local)
ollama_urlhttp://127.0.0.1:11434
ollama_modelqwen3-vl:8b
temperature0.35
reuse_existingtrue
seed0
style_prefix_override
api_key
api_model
max_output_tokens8192
num_ctx16384
keep_alive10m
request_timeout900
CategoryH3 Planner

Inputs (25)

NameTypeDefaultDescription
projectH3_PROJECT
ideaSTRINGthe whole brief: what happens, who is in it, what it is for
total_secondsFLOAT30.02–600
min_segment_secondsFLOAT5.00.5–15shortest clip the planner may ask for. Longer clips cost less per second of video, because the fixed per-run overhead is amortised.
max_segment_secondsFLOAT10.01–15longest clip your card can render. A ceiling, not a target — the planner varies length to suit each beat.
formatCOMBOcinematic ad7 options: auto, short film, cinematic ad, ugc, product, explainer, +1
dialogueCOMBOautowhether anyone speaks on camera. 'spoken lines' makes the planner write the actual script and render it as H3 <d>[English] ...</d> dialogue with speaker IDs; 'auto' decides from the brief; 'none' keeps it picture only.
audio_roleCOMBOperformed on camerawhat the connected audio IS. The first three treat it as the soundtrack, reused exactly: 'performed on camera' when a visible subject raps or sings it. 'voice sample' is the opposite and is the one for an ad: the audio is only a timbre, the dialogue is written here and generated in that voice. Ignored with no audio in the cast.
windowINT41–12segments written per prose call once the piece is too long for one reply. Each window sees the previous window's closing state.
single_call_maxINT81–40at or below this many segments the whole video is written in ONE prose call, which is what makes it consistent. Above it, windows are used.
chain_first_framesBOOLEANfalsestart each segment from the previous one's last frame, within a scene. Hard visual continuity at the joins, but artifacts compound across a long chain — leave off unless you need it.
providerCOMBOOllama (Local)1 options: Ollama (Local)
ollama_urlSTRINGhttp://127.0.0.1:11434
ollama_modelSTRINGqwen3-vl:8b
temperatureFLOAT0.350–1.2
reuse_existingBOOLEANtruekeep segments already written from the same brief
seedINT00–4294967295change to replan the whole video
castoptH3_CAST
style_prefix_overrideoptSTRING
api_keyoptSTRING
api_modeloptSTRING
max_output_tokensoptINT8192256–32768
num_ctxoptINT163842048–131072
keep_aliveoptSTRING10m
request_timeoutoptINT90030–3600

Outputs (3)

NameTypeDescription
timelineH3_TIMELINE
beat_sheetSTRING
reportSTRING