16 KiB
Executable File
| name | description |
|---|---|
| h3-plan-gate | Turn a story idea into a validated plan_json_input JSON for the MiniMax H3 Production Plan node (ComfyUI-MiniMaxH3-Context-Loop). Use when the user wants to plan scenes/shots for H3 video generation, write or extend a scene plan, regenerate one scene, or validate an existing H3 plan JSON. The skill lives in the h3-plan-gate folder of the project; all commands run from the project root with the project's Python. |
H3 Plan Gate — agent procedure
Goal: produce plan.json, the JSON pasted into the Production Plan node's plan_json_input,
in five moves: the user gives a story and a scene count → you build a scene guide
(outline.json) and show it for approval → with the approved guide you compose the
scenes one at a time (about 10 seconds each), each turn existing so that ONE scene can
be composed from every element of a good scene composition, never to fill a word count
→ the scripts verify the continuity across the whole chain → build_plan.py puts all
the scenes together at the end. Never deliver a plan that did not pass --check, and
never compose a scene from a guide the user has not approved.
Paths and Python (read first — these exact forms prevent most errors)
- Work from the project root: the folder that contains
h3-plan-gate/. Every path below is relative to it. Do not cd intoh3-plan-gate, and do not cd out of the project root. - Write generated files into the project root:
outline.json,scene_01.json,scene_02.json, … ,plan.json. - Python command: on Windows run
.venv\Scripts\python.exe; if the project has no.venv, usepythoninstead. (macOS/Linux:.venv/bin/pythonorpython.) The scripts need only the Python standard library — nothing to install. - Start every task by running the smoke test under "Before you start". If it fails because
h3-plan-gateis missing files, stop and tell the user the folder is incomplete.
Before you start (smoke test)
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py
.venv\Scripts\python.exe h3-plan-gate/build_plan.py --check h3-plan-gate/h3_agent_workflow_examples/plan.json
Expect the suite to pass and the second command to print
PLAN OK with total delivered: 1042 frames = 43.42s.
Step 1 — Build the scene guide (outline)
The user gives you a story and how many scenes they want. Read
h3-plan-gate/h3_scene_agent_system_prompt.md (PROMPT A and its WORKED EXAMPLE are the
quality bar) and write outline.json — the guide for every scene — in exactly this
shape:
{
"title": "short_snake_case_name",
"defaults": { "duration_seconds": 10, "steps": 20 },
"style_and_cast": {
"subjects": ["<Subject 1> — who they are; wardrobe head to toe; build; hair"],
"style": "one consistent look: photoreal or otherwise, lighting, palette, camera feel",
"soundscape_seed": "the base ambient sound carried across all scenes"
},
"scenes": [
{ "index": 1, "id": "scene_one_name", "duration_seconds": 10,
"beat": "one sentence: what happens AND where the scene ends",
"dialogue": [] }
]
}
3–12 scenes unless the user names a count (hard max 128). Ids unique lowercase snake_case,
never renamed later. Durations whole seconds 2–15 — about 10 seconds unless the user says
otherwise. Copy the user's quoted speech EXACTLY into the right scene's dialogue array;
if the story has no quoted speech, every dialogue array stays []. Only the last
scene's beat may come to rest. The subjects array is the cast inventory: collect the
full head-to-toe look there once — when writing scenes it is spent by weaving it into
each scene's [Shot 1] body, never parked in subject_definitions (a refmod subject is
the one exception: its verbatim identity/voice text is spent exactly once, in
subject_definitions, and the body references only <Subject N>). If the story's script
carries a characters: block with refmod entries — sam:&identity: <identity text>; voice: <voice text>& — copy the identity and voice text verbatim into that subject's
inventory string (the & marks are delimiters, never content); the scene turns must carry
them into subject_definitions untouched.
Step 2 — Present the guide for approval (do not skip)
Show the user the finished guide in plain language — one line per scene: number, id,
duration, what happens and where it ends, any dialogue — plus the cast and style block.
Then STOP and wait for their reply. The user approves it or asks for changes; apply
every change to outline.json (scene count, ids, durations, beats, dialogue, cast,
style) and, if anything changed, show the changed rows again. Start Step 3 only after
an explicit approval. The approved guide is the contract: scenes are composed from it,
ids and durations are never silently altered, and new story ideas from the user go
through the guide first — never straight into a scene file.
Step 3 — Compose the scenes one at a time
Work only from the approved guide. Before writing scene 1, read the PROMPT B section of
h3_scene_agent_system_prompt.md — its SCENE COMPOSITION checklist (subject anchor,
style anchor, continuity anchor, blocking, camera, performance, physical texture, exit
state) is what each turn is for. Then, in story order: compose ONE scene file, validate
it, fix it until it passes, and only then move to the next scene. Since you wrote the
previous file yourself, open it and reuse its _handoff as the opening state of the
next scene. Rewrite a scene as many times as it takes for every element to be present
and concrete — the validator has no word band, only a thin-scene floor, so never pad
and never summarize.
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py fragment scene_01.json --index 1 --total 5
.venv\Scripts\python.exe h3-plan-gate/verify_plan_rules.py fragment scene_02.json --index 2 --total 5 --prev scene_01.json
(--total is the scene count from the outline; --prev chains the previous file.)
Each fragment is exactly this shape:
{
"id": "from the outline row",
"duration_seconds": 15,
"prompt": [
"subject_definitions:",
"<Subject 1> ...one of the three definition forms (see craft rules below)...",
"summary:",
"[reference generation]",
"retention_analysis:",
"<Subject 1>: fully_preserved",
"detailed_description:",
"...1-2 style sentences from the guide's style...",
"[Shot 1] ...the full scene composition...",
"overall_soundscape:",
"...the sound the scene itself makes...",
"non_diegetic_music:",
"N/A"
],
"_handoff": { "end_state": "...", "soundscape": "...", "dialogue_used": [] }
}
Step 4 — Verify the continuity, put it all together at the end
Once every scene file passes, the merge is the continuity check: build_plan.py
re-walks the whole _handoff chain — every scene after the first must open inside the
previous scene's real end_state, every soundscape must continue the previous audio bed,
every id, duration, and spoken line must match the approved guide — and only then does
it write the ONE plan JSON. Never write the plan JSON by hand and never edit fragment
prose during the merge. Run:
.venv\Scripts\python.exe h3-plan-gate/build_plan.py outline.json scene_01.json scene_02.json scene_03.json -o plan.json
.venv\Scripts\python.exe h3-plan-gate/build_plan.py --check plan.json
The merger strips _handoff, injects "prompt_prefix": [""] and defaults, validates
everything, and writes the single deliverable: plan.json — "prompt_prefix": [""],
defaults, and one self-sufficient shot per scene, exactly the shape the single-pass
system prompt emits. Report the delivered frames/seconds it prints.
Step 5 — Deliver (the node makes the multi-clip video)
The user pastes the full contents of plan.json into the Plan node's plan_json_input
and queues ONCE. The node renders each shot as its own clip and chains the clips through
the H3 context loop — scene 2 continues from scene 1's final frames, scene 3 from scene
2's — producing one continuous multi-clip video. Every scene after the first loses about
1 second to the fixed overlap trim that stitches the clips together.
Resolution, context length, audio mode, and base_seed stay on the node's widgets — the
JSON cannot set them; the width/height outputs must be wired into the conditioning node
and sampler latent or the video can come out square.
Craft rules for every fragment (violations fail the validator)
- Raw JSON only: first char
{, last char}, no markdown fences, no prose, double quotes, no trailing commas, no raw line break inside a string. - The
promptarray carries the six native H3 ref2va sections in canonical order —subject_definitions:/summary:/retention_analysis:/detailed_description:/overall_soundscape:/non_diegetic_music:— one line per element, headers on their own line;summaryis exactly[reference generation]; every scene is its own single H3 generation, so the bracket number is always[Shot 1]. - The full look is re-stated in EVERY scene, and it lives in the [Shot 1] body —
subject_definitions only anchors identity, in exactly one of three forms per line:
a character with NO reference image gets physical traits only ("<Subject 1> is a
20 year old woman with blonde hair, blue eyes and a medium build" — age, hair,
eyes, build; never clothing, never a nude/bare state); a character WITH a
reference image gets "<Subject 1> binds to <Image 1> : what the image actually
shows" (the writing LLM is multimodal — look at it); and a user
refmod (
sam:&identity: ...; voice: ...&in the story's characters block) is carried through VERBATIM as "<Subject 1> identity: ...; voice: ..." — never rewritten, never trimmed, exempt from every defs limit; the refmod text lives ONLY in subject_definitions, and the [Shot 1] body references that subject by its<Subject N>label alone — never restating the refmod's identity, voice, or look. For a no-image or binds subject, weave the head-to-toe look into the action as the scene exposes it — hair, build, and face as they move, each garment where the action touches it, footwear where steps land — nothing is shared between scenes or from a prefix. Name every body part the clothing leaves uncovered and call uncovered skin "nude", never "bare", where the scene shows it ("a man wearing a white tank-top with nude arms"). - Scene composition, not word count: the [Shot 1] body must carry every element —
subject anchor (
<Subject 1>referenced; the full look woven in — a refmod subject needs only its label), style anchor, continuity anchor (opens inside the previous end_state), blocking, one camera idea, performance beats, physical texture (wardrobe behavior, weather on skin and fabric, lighting), and a concrete mid-action exit state. Never pad to a length and never hand in a thin one-liner — a scene with every element is long enough on its own. The validator only trips a thin-scene floor (about 100 words); there is no target band. - Decompose every action into body mechanics: never a single outcome verb ("picks up the ball", "crosses her legs") — write the ordered joint-level sequence ("bends his knees, grabs the ball with his left hand, then stands back up"; "raises her left leg and places it across her right leg"), naming the hand or limb for each step. Every movement and motion of every character is this detailed, large or small. H3 plays back only what is stated; a compressed verb leaves gaps the model fills by guessing, and guessed motion drifts off intent.
- Show common actions, never just mention them: an action named without its steps is a report, not a render — H3 displays only what the description displays. The common everyday actions are the worst offenders, and each is written as its ordered on-screen steps: unbuttoning a shirt (pinch the button, push it through the buttonhole, pull the plackets apart, work down one at a time), changing a diaper (undo the waist tabs, fold the panel down, lift the ankles, slide the old one out, wipe, lay the fresh one under, press each tab closed), turning on a lamp (flip the switch with one finger, hold still while the bulb flickers and settles), opening a door (press the lever down, pull the door toward you, step through), buckling a strap (pull it across, click the tongue home, tug the free end to tighten), handing over an object (lift it, hold it out, wait for the other hand to close, release).
- Spell out every change and movement step by step — not only the subject's actions. Camera, lighting, weather, background, wardrobe, and any transformation each get their own ordered sequence of visible stages ("the camera pushes in one slow step, then another, until his hands fill the lower frame"); never a summarized change ("the lights dim"). H3 plays back only what is stated; a summarized change or movement is a gap the model fills by guessing.
- Open by continuing the previous
_handoffend_state ("Continue the same stride", "without resetting the motion", "keep the incoming camera direction"); scene 1 sets the opening. End mid-action except the final scene. No camera cuts inside a scene. - Never compress a change into a stated outcome: a line like "<Subject 1> is now an 18 year old man" is FORBIDDEN. Show every transformation (age, wardrobe, weather, lighting, location, size) as a continuous on-screen progression while motion and camera keep flowing.
- Soundscape: one or two dense clauses matching the picture, continuing the previous audio
bed ("the same rain on glass continues"); diegetic music always named with its in-scene
source;
non_diegetic_music: N/Aunless the user asked for a score; sung/spoken words are dialogue and never live in the soundscape line. - Dialogue: silence is the default. Spoken words come only from the outline row or the
story, reproduced word for word inside case-sensitive
<d>[English] words</d>(one space after the marker; other real languages allowed), inside the [Shot 1] body only, with a "silently with mouth {position}" cue before and after every span. Mirror each span in_handoff.dialogue_used(words only, no marker); empty array when silent. _handoffmust be truthful:end_statedescribes the real final frame (2–3 sentences: pose, motion in progress, camera state);soundscapecopies the soundscape content line (the element after theoverall_soundscape:header) character for character.- Keys are exactly
id,duration_seconds,prompt,_handoff; addstepsorseedonly when the user explicitly asked. Every duration 2–15 s.
Revising after approval
- Guide-level change (durations, beats, dialogue, scene count): update
outline.jsonfirst, show the changed rows, then rewrite only the affected scenes against it. - One scene reads badly: rewrite that
scene_NN.json(keep its id and duration from the guide), re-validate it with the fragment command, then re-run the Step 4 merge soplan.jsonrefreshes. Never patchplan.jsondirectly.
Short stories (2–4 scenes)
You may use the single-pass prompt instead — read
h3-plan-gate/h3_plan_json_system_prompt.md, have its rules govern one turn that writes
the whole plan, then run --check on the file. Use the full workflow for long stories,
per-scene iteration, or when the user wants to revise single scenes or the guide.
If you cannot run Python
Fall back to h3-plan-gate/h3_plan_assembler_system_prompt.md for the merge, copy fragment
text verbatim, and say plainly that the result skipped script validation.