Nodes/ComfyUI-MiniMax-H3-Prompt-Enhancer/MiniMax H3 Prompt Validator
ComfyUI Node

MiniMax H3 Prompt Validator

Validate a manually authored or enhanced prompt against MiniMax H3's documented audiovisual structure without calling an LLM. Structural validity does not guarantee generation quality.

By hyukudan·Created 20 days ago·Updated a day ago· 15
MiniMax H3 Prompt Validator
    • prompt
    • valid
    • validation_report
    prompt
    modeauto
    duration_seconds5.00
    source_prompt
    reference_context
    ambience_foley_policyauto
    background_score_policyfollow_prompt
    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
    creative_latitudeenhanced_production
    delivery_targetlocal
    instrumental_description
    instrumental_stylenone
    acoustic_spacenone
    dialogue_coverageoff
    dialogue_languageauto
    editing_intentnone
    lora_trigger_words
    CategoryMiniMax H3/Prompting

    Inputs (28)

    NameTypeDefaultDescription
    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.
    source_promptSTRING
    reference_contextSTRINGOptional plain-language notes describing referenced pictures, videos, audio, identities, or roles. Usually needed only for Ref2VA.
    ambience_foley_policyoptCOMBOautoScene sounds other than speech or music: ambience plus physical action sounds such as footsteps, clothing, doors, impacts, and engines.
    background_score_policyoptCOMBOfollow_prompt3 options: follow_prompt, add_instrumental, off
    voice_performanceoptCOMBOaudible3 options: audible, silent_mouth_acting_experimental, none
    aspect_ratiooptCOMBOauto7 options: auto, 21:9, 16:9, 4:3, 1:1, 3:4, +1
    media_manifestoptSTRINGAdvanced structured JSON for connected reference media.
    multishot_shot_countoptINT00–64
    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_jsonoptSTRING
    shot_plan_jsonoptSTRING
    cinematography_jsonoptSTRING
    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.
    delivery_targetoptCOMBOlocalAPI v2 treats the 7000-character text-block limit as a hard error; local mode reports compatibility only.
    instrumental_descriptionoptSTRING
    instrumental_styleoptCOMBOnone26 options: none, cinematic_orchestral, hybrid_orchestral_electronic, action_cinematic, mystery_investigation, suspense_build, +20
    acoustic_spaceoptCOMBOnone7 options: none, small_reflective_interior, large_reverberant_interior, damped_interior, open_exterior, urban_exterior, +1
    dialogue_coverageoptCOMBOoff2 options: off, on
    dialogue_languageoptCOMBOauto18 options: auto, Spanish, English, French, German, Italian, +12
    editing_intentoptCOMBOnone7 options: none, character_swap, wardrobe_transfer, voice_dialogue_swap, environment_background, motion_transfer, +1
    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 (3)

    NameTypeDescription
    promptSTRING
    validBOOLEAN
    validation_reportSTRING