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.
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)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | — | |
| mode | COMBO | auto | 7 options: auto, t2va, i2va, fl2va, l2va, ref2va, +1 |
| duration_seconds | FLOAT | 5.004–150 | 4-150 seconds. H3 was trained around 5-15 seconds; longer generations are experimental and require much more memory. |
| source_prompt | STRING | — | |
| reference_context | STRING | Optional plain-language notes describing referenced pictures, videos, audio, identities, or roles. Usually needed only for Ref2VA. | |
| ambience_foley_policyopt | COMBO | auto | Scene sounds other than speech or music: ambience plus physical action sounds such as footsteps, clothing, doors, impacts, and engines. |
| background_score_policyopt | COMBO | follow_prompt | 3 options: follow_prompt, add_instrumental, off |
| voice_performanceopt | COMBO | audible | 3 options: audible, silent_mouth_acting_experimental, none |
| aspect_ratioopt | COMBO | auto | 7 options: auto, 21:9, 16:9, 4:3, 1:1, 3:4, +1 |
| media_manifestopt | STRING | Advanced structured JSON for connected reference media. | |
| multishot_shot_countopt | INT | 00–64 | — |
| frame_countopt | INT | 00–3600 | Leave 0 to use Duration. A nonzero exact count must follow 17 × n + 5. Above about 362 frames (~15 s) is experimental. |
| multishot_identity_lockopt | STRING | — | |
| multishot_voice_lockopt | STRING | — | |
| multishot_setting_lockopt | STRING | — | |
| show_advanced_controlsopt | BOOLEAN | false | Show structured reference metadata and exact frame controls |
| creative_treatment_jsonopt | STRING | — | |
| shot_plan_jsonopt | STRING | — | |
| cinematography_jsonopt | STRING | — | |
| creative_latitudeopt | COMBO | enhanced_production | How 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_targetopt | COMBO | local | API v2 treats the 7000-character text-block limit as a hard error; local mode reports compatibility only. |
| instrumental_descriptionopt | STRING | — | |
| instrumental_styleopt | COMBO | none | 26 options: none, cinematic_orchestral, hybrid_orchestral_electronic, action_cinematic, mystery_investigation, suspense_build, +20 |
| acoustic_spaceopt | COMBO | none | 7 options: none, small_reflective_interior, large_reverberant_interior, damped_interior, open_exterior, urban_exterior, +1 |
| dialogue_coverageopt | COMBO | off | 2 options: off, on |
| dialogue_languageopt | COMBO | auto | 18 options: auto, Spanish, English, French, German, Italian, +12 |
| editing_intentopt | COMBO | none | 7 options: none, character_swap, wardrobe_transfer, voice_dialogue_swap, environment_background, motion_transfer, +1 |
| lora_trigger_wordsopt | STRING | Trigger 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)
| Name | Type | Description |
|---|---|---|
| prompt | STRING | — |
| valid | BOOLEAN | — |
| validation_report | STRING | — |