Nodes/ComfyUI-MiniMax-H3-Prompt-Enhancer/MiniMax H3 Prompt Guide Builder
ComfyUI Node

MiniMax H3 Prompt Guide Builder

Build the official MiniMax H3 rewriting instructions without running an LLM. Connect these outputs to QwenVL Prompt Enhancer, a GGUF node, Ollama, LM Studio, or any other text-generation node.

By hyukudan·Created 20 days ago·Updated a day ago· 15
MiniMax H3 Prompt Guide Builder
    • system_prompt
    • user_prompt
    • resolved_mode
    • treatment_warnings
    • width
    • height
    basic_prompt
    modeauto
    duration_seconds5.00
    reference_context
    creative_latitudeenhanced_production
    ambience_foley_policyauto
    background_score_policyfollow_prompt
    instrumental_description
    voice_performanceaudible
    aspect_ratioauto
    media_manifest
    multishot_shot_count0
    frame_count0
    multishot_identity_lock
    multishot_voice_lock
    multishot_setting_lock
    show_advanced_controlsfalse
    creative_treatment_json
    shot_plan_json
    cinematography_json
    instrumental_stylenone
    acoustic_spacenone
    dialogue_coverageoff
    dialogue_languageauto
    visual_style_presetnone
    target_megapixels0.00
    editing_intentnone
    lora_trigger_words
    CategoryMiniMax H3/Prompting

    Inputs (28)

    NameTypeDefaultDescription
    basic_promptSTRING
    modeCOMBOauto7 options: auto, t2va, i2va, fl2va, l2va, ref2va, +1
    duration_secondsFLOAT5.004–1504-150 seconds. H3 was trained around 5-15 seconds; longer generations are experimental and require much more memory.
    reference_contextSTRINGOptional plain-language notes describing referenced pictures, videos, audio, identities, or roles. Usually needed only for Ref2VA.
    creative_latitudeoptCOMBOenhanced_productionHow far beyond your text the writer may go. verbatim_source: none - keep your wording, facts and terseness as written; only reformat into H3 sections, apply the selected style and translate delivery marks. conservative_grounded: only the minimum structure the H3 mode requires. enhanced_production: resolve unspecified production decisions - composition, blocking, lighting, micro-performance. invented_production: treat your text as a premise and build the world around it. Quoted dialogue, reference identities, duration, shot count, ending and gore level stay locked at every level.
    ambience_foley_policyoptCOMBOautoScene sounds other than speech or music: rain, wind, room tone, footsteps, clothing, doors, impacts, engines, breathing, and similar physical sounds.
    background_score_policyoptCOMBOfollow_promptFollow the source, add an instrumental score, or force no non-diegetic music
    instrumental_descriptionoptSTRINGDescribe concrete instrumentation, tempo, rhythm, and dynamics; mood words are translated into audible parameters.
    voice_performanceoptCOMBOaudibleExperimental silent mouth acting is visual best-effort only; exact lip sync and silence are not guaranteed
    aspect_ratiooptCOMBOauto7 options: auto, 21:9, 16:9, 4:3, 1:1, 3:4, +1
    media_manifestoptSTRINGAdvanced alternative to reference notes: structured JSON describing connected media, roles, analysis, subjects, and transcripts.
    multishot_shot_countoptINT00–64Chained multishot only: 0 infers the count
    frame_countoptINT00–3600Leave 0 to use Duration. A nonzero exact count must follow 17 × n + 5. Above about 362 frames (~15 s) is experimental.
    multishot_identity_lockoptSTRING
    multishot_voice_lockoptSTRING
    multishot_setting_lockoptSTRING
    show_advanced_controlsoptBOOLEANfalseShow structured reference metadata and exact frame controls
    creative_treatment_jsonoptSTRINGStable schema-v2 storage for the optional creative-treatment selectors. Legacy v1 remains runtime-compatible; blank is neutral.
    shot_plan_jsonoptSTRINGOptional authoritative shot plan. Schema v1 remains compatible; v2 adds generations, presence, states, environments and start/path/end camera. Blank preserves automatic planning.
    cinematography_jsonoptSTRINGOptional schema-v2 manual color, camera, optics, focus, texture, and motion-rendering controls. Legacy v1 remains runtime-compatible; blank is neutral.
    instrumental_styleoptCOMBOnoneWhen instrumental score is enabled, adapt its arrangement to this musical language while preserving compatible user direction.
    acoustic_spaceoptCOMBOnoneDiegetic sound space for the permitted ambience, foley, and voices. It renders existing sounds; it never adds a source.
    dialogue_coverageoptCOMBOoffKeep every speaking character's mouth and eyes unobstructed, in focus, and framed at medium close-up or tighter for the whole line.
    dialogue_languageoptCOMBOautoTarget dialogue language. 'auto' automatically detects language from prompt context/dialogue.
    visual_style_presetoptCOMBOnoneQuick visual style preset. When selected, automatically applies this visual language unless overridden in creative treatment JSON.
    target_megapixelsoptFLOAT0.00Target resolution in Megapixels (MP), e.g. 0.2, 0.3, 0.5, 0.92 (720p), 2.0 (1080p). Leave 0.0 for standard defaults; Custom accepts any positive finite value.
    editing_intentoptCOMBOnoneQuick video editing intent preset for Ref2VA (Character Swap, Wardrobe Transfer, Voice/Dialogue Swap, Background Change, Motion Transfer, Custom Editing). Automatically enforces video editing summary and retention policies.
    lora_trigger_wordsoptSTRINGTrigger tokens for the LoRAs loaded elsewhere in the graph. Appended verbatim to the end of the description after enhancement and validation, so they never pass through the LLM and survive character for character.

    Outputs (6)

    NameTypeDescription
    system_promptSTRING
    user_promptSTRING
    resolved_modeSTRING
    treatment_warningsSTRING
    widthINT
    heightINT