ComfyUI Node
๐ฌ Ultra MiniMax H3 Prompt
MiniMax H3 prompt compiler with default Korean-to-English scene translation and timeline-based multi-person dialogue/action support.
๐ฌ Ultra MiniMax H3 Prompt
- start_image
- end_image
- h3_prompt
- info
โscene_promptโบ
โscene_translateko_to_enโบ
โscene_input_rolescene_actionโบ
โmodeautoโบ
โduration_seconds5โบ
โshot_layoutauto_safeโบ
โvisual_styleautoโบ
โnarrator_voice_descโบ
โcamera_motionautoโบ
โcamera_amplitudedefaultโบ
โcamera_speeddefaultโบ
โcamera_sequence_enabledfalseโบ
โcamera_shot_count2โบ
โcamera_shot_1_targetcurrent_actionโบ
โcamera_shot_1_framingautoโบ
โcamera_shot_2_enabledtrueโบ
โcamera_shot_2_start_seconds0.5โบ
โcamera_shot_2_transitioncutโบ
โcamera_shot_2_targetcurrent_actionโบ
โcamera_shot_2_framingautoโบ
โcamera_shot_2_motionautoโบ
โcamera_shot_2_amplitudeinheritโบ
โcamera_shot_2_speedinheritโบ
โcamera_shot_3_enabledfalseโบ
โcamera_shot_3_start_seconds1.0โบ
โcamera_shot_3_transitioncutโบ
โcamera_shot_3_targetcurrent_actionโบ
โcamera_shot_3_framingautoโบ
โcamera_shot_3_motionautoโบ
โcamera_shot_3_amplitudeinheritโบ
โcamera_shot_3_speedinheritโบ
โcamera_shot_4_enabledfalseโบ
โcamera_shot_4_start_seconds1.5โบ
โcamera_shot_4_transitioncutโบ
โcamera_shot_4_targetcurrent_actionโบ
โcamera_shot_4_framingautoโบ
โcamera_shot_4_motionautoโบ
โcamera_shot_4_amplitudeinheritโบ
โcamera_shot_4_speedinheritโบ
โcamera_shot_5_enabledfalseโบ
โcamera_shot_5_start_seconds2.0โบ
โcamera_shot_5_transitioncutโบ
โcamera_shot_5_targetcurrent_actionโบ
โcamera_shot_5_framingautoโบ
โcamera_shot_5_motionautoโบ
โcamera_shot_5_amplitudeinheritโบ
โcamera_shot_5_speedinheritโบ
โcamera_shot_6_enabledfalseโบ
โcamera_shot_6_start_seconds2.5โบ
โcamera_shot_6_transitioncutโบ
โcamera_shot_6_targetcurrent_actionโบ
โcamera_shot_6_framingautoโบ
โcamera_shot_6_motionautoโบ
โcamera_shot_6_amplitudeinheritโบ
โcamera_shot_6_speedinheritโบ
โreference_fidelitybalancedโบ
โsoundscape_modeautoโบ
โsound_hintโบ
โmusic_modenoneโบ
โmusic_hintโบ
โdialogue_textโบ
โdialogue_languageautoโบ
โdialogue_deliveryon_screenโบ
โperson_count1โบ
โturn_count1โบ
โperson_a_genderunspecifiedโบ
โperson_a_ageunspecifiedโบ
โperson_a_advancedfalseโบ
โperson_a_appearance_presetnoneโบ
โperson_a_appearance_descโบ
โperson_a_clothing_presetnoneโบ
โperson_a_clothing_descโบ
โperson_a_voice_descโบ
โperson_b_genderunspecifiedโบ
โperson_b_ageunspecifiedโบ
โperson_b_advancedfalseโบ
โperson_b_appearance_presetnoneโบ
โperson_b_appearance_descโบ
โperson_b_clothing_presetnoneโบ
โperson_b_clothing_descโบ
โperson_b_voice_descโบ
โperson_c_genderunspecifiedโบ
โperson_c_ageunspecifiedโบ
โperson_c_advancedfalseโบ
โperson_c_appearance_presetnoneโบ
โperson_c_appearance_descโบ
โperson_c_clothing_presetnoneโบ
โperson_c_clothing_descโบ
โperson_c_voice_descโบ
โturn_1_speakerAโบ
โturn_1_elapsed_seconds0.0โบ
โturn_1_actionโบ
โturn_1_dialogue_textโบ
โturn_1_dialogue_languageautoโบ
โturn_1_dialogue_deliveryon_screenโบ
โturn_1_vocal_2_textโบ
โturn_1_vocal_3_textโบ
โturn_2_speakerAโบ
โturn_2_elapsed_seconds0.0โบ
โturn_2_actionโบ
โturn_2_dialogue_textโบ
โturn_2_dialogue_languageautoโบ
โturn_2_dialogue_deliveryon_screenโบ
โturn_2_vocal_2_textโบ
โturn_2_vocal_3_textโบ
โturn_3_speakerAโบ
โturn_3_elapsed_seconds0.0โบ
โturn_3_actionโบ
โturn_3_dialogue_textโบ
โturn_3_dialogue_languageautoโบ
โturn_3_dialogue_deliveryon_screenโบ
โturn_3_vocal_2_textโบ
โturn_3_vocal_3_textโบ
โturn_4_speakerAโบ
โturn_4_elapsed_seconds0.0โบ
โturn_4_actionโบ
โturn_4_dialogue_textโบ
โturn_4_dialogue_languageautoโบ
โturn_4_dialogue_deliveryon_screenโบ
โturn_4_vocal_2_textโบ
โturn_4_vocal_3_textโบ
โturn_5_speakerAโบ
โturn_5_elapsed_seconds0.0โบ
โturn_5_actionโบ
โturn_5_dialogue_textโบ
โturn_5_dialogue_languageautoโบ
โturn_5_dialogue_deliveryon_screenโบ
โturn_5_vocal_2_textโบ
โturn_5_vocal_3_textโบ
โturn_6_speakerAโบ
โturn_6_elapsed_seconds0.0โบ
โturn_6_actionโบ
โturn_6_dialogue_textโบ
โturn_6_dialogue_languageautoโบ
โturn_6_dialogue_deliveryon_screenโบ
โturn_6_vocal_2_textโบ
โturn_6_vocal_3_textโบ
โtimeline_events_jsonโบ
โvariation_seed0โบ
โi2va_preserve_reference_clothingtrueโบ
โultra_scene_validation_gateokโบ
โultra_ui_localeenโบ
โultra_extension_options_json{}โบ
CategoryUltra/MiniMax H3
Inputs (145)
| Name | Type | Default | Description |
|---|---|---|---|
| scene_prompt | STRING | Shared scene/backdrop only: location, mood, lighting, and initial character arrangement. Put changing actions and dialogue in Ordered Steps. Example: A wide meadow in warm late-afternoon light; a woman and a man stand facing each other. Text containing only spaces or line breaks is treated as empty. In T2VA, a completely empty draft remains queueable; the h3_prompt branch waits with status=waiting_for_content instead of becoming a native input error. | |
| scene_translate | COMBO | ko_to_en | Global non-dialogue descriptive-text translation control. Automatic: translate Korean scene/action/profile/reference/sound/music descriptions to English while leaving already-English text unchanged. Off: preserve every descriptive field exactly as entered and make no online translation request. Dialogue is never translated. |
| scene_input_role | COMBO | scene_action | Legacy serialized workflow field retained only for backward-compatible widget alignment. Current runtime always uses Timeline mode and ignores this value. |
| mode | COMBO | auto | Auto follows the actual image connections: none=T2VA, start only=I2VA, end only=L2VA, start+end=FL2VA. Manual T2VA stays T2VA and ignores connected images for prompt-mode resolution. Manual I2VA requires a start image, L2VA requires an end image, and FL2VA requires both; when a required image is missing, the node shows the guidance badge and quietly waits instead of changing to another mode. |
| duration_seconds | INT | 54โ30 | Reference duration for H3 timing. This node accepts 4-30 whole seconds. MiniMax H3 officially supports up to 15 seconds; 16-30 seconds are an advanced/local-use range and may increase generation time and memory use sharply. Match this to the actual H3 video-generation duration. |
| shot_layout | COMBO | auto_safe | Legacy serialized workflow field retained only for backward-compatible widget alignment. Current runtime ignores this value; use Multiple Camera Cuts for explicit shots. |
| visual_style | COMBO | auto | 22 options: auto, cinematic, family_film, warm_cinematic, natural, live_action, +16 |
| narrator_voice_desc | STRING | Optional custom Narrator voice characteristics. This is a normal ComfyUI STRING widget/input and can be connected from an external STRING source. | |
| camera_motion | COMBO | auto | Base camera motion for the shot. In multiple-camera mode, this remains the motion for Shot 1 because Shot 1 begins the video and has no transition-in. Tracking Shot follows the subject smoothly; camera shake emphasizes shake; Handheld Tracking follows the action with natural operator movement and irregular micro-corrections. |
| camera_amplitude | COMBO | default | Single-camera mode: applies to the selected camera motion. Multiple-camera mode: this is Shot 1 amplitude and the inherited default for later Shots whose Camera Amplitude is set to Follow Base Settings. |
| camera_speed | COMBO | default | Single-camera mode: applies to the selected camera motion. Multiple-camera mode: this is Shot 1 speed and the inherited default for later Shots whose Camera Speed is set to Follow Base Settings. |
| camera_sequence_enabled | BOOLEAN | false | Enable explicit H3 shot changes. Shot 1 always exists. When enabled, Shot 2-6 can be enabled in order and each Shot gets its own start time in seconds, independent of Timeline Progress timing. |
| camera_shot_count | INT | 22โ6 | Internal derived active-shot count. The UI derives this from the enabled Shot 2-6 blocks; users do not set it directly. |
| camera_shot_1_target | COMBO | current_action | Shot 1 is the default opening shot and always starts at 0.0 seconds. Choose what the opening shot frames. Its timing is independent of Timeline Progress timing. |
| camera_shot_1_framing | COMBO | auto | Framing for the default Shot 1. Shot 1 always exists even when Multiple Camera Cuts is OFF. |
| camera_shot_2_enabled | BOOLEAN | true | Enable Shot 2. When ON, set Shot 2 Start Time (seconds). Shot timing is independent of Timeline Progress timing. Shots must be enabled in order without gaps. |
| camera_shot_2_start_seconds | FLOAT | 0.50.5โ29.5 | Video time in seconds when Shot 2 starts. Use 0.5-second steps. This timing is independent of Timeline Progress start times; the UI dynamically limits the maximum to video duration minus 0.5 seconds. |
| camera_shot_2_transition | COMBO | cut | Transition used when Shot 2 starts. |
| camera_shot_2_target | COMBO | current_action | What Shot 2 should frame. |
| camera_shot_2_framing | COMBO | auto | Framing for Shot 2. Available choices follow the selected target. |
| camera_shot_2_motion | COMBO | auto | Optional camera movement inside Shot 2 after its transition. |
| camera_shot_2_amplitude | COMBO | inherit | Amplitude for Shot 2 camera motion. Follow Base Settings inherits the top Camera Amplitude; Default ยท Omit suppresses the amplitude phrase for this Shot; Small/Large override it only for this Shot. |
| camera_shot_2_speed | COMBO | inherit | Speed for Shot 2 camera motion. Follow Base Settings inherits the top Camera Speed; Default ยท Omit suppresses the speed phrase for this Shot; Slow/Fast override it only for this Shot. |
| camera_shot_3_enabled | BOOLEAN | false | Enable Shot 3. When ON, set Shot 3 Start Time (seconds). Shot timing is independent of Timeline Progress timing. Shots must be enabled in order without gaps. |
| camera_shot_3_start_seconds | FLOAT | 1.00.5โ29.5 | Video time in seconds when Shot 3 starts. Use 0.5-second steps. This timing is independent of Timeline Progress start times; the UI dynamically limits the maximum to video duration minus 0.5 seconds. |
| camera_shot_3_transition | COMBO | cut | Transition used when Shot 3 starts. |
| camera_shot_3_target | COMBO | current_action | What Shot 3 should frame. |
| camera_shot_3_framing | COMBO | auto | Framing for Shot 3. Available choices follow the selected target. |
| camera_shot_3_motion | COMBO | auto | Optional camera movement inside Shot 3 after its transition. |
| camera_shot_3_amplitude | COMBO | inherit | Amplitude for Shot 3 camera motion. Follow Base Settings inherits the top Camera Amplitude; Default ยท Omit suppresses the amplitude phrase for this Shot; Small/Large override it only for this Shot. |
| camera_shot_3_speed | COMBO | inherit | Speed for Shot 3 camera motion. Follow Base Settings inherits the top Camera Speed; Default ยท Omit suppresses the speed phrase for this Shot; Slow/Fast override it only for this Shot. |
| camera_shot_4_enabled | BOOLEAN | false | Enable Shot 4. When ON, set Shot 4 Start Time (seconds). Shot timing is independent of Timeline Progress timing. Shots must be enabled in order without gaps. |
| camera_shot_4_start_seconds | FLOAT | 1.50.5โ29.5 | Video time in seconds when Shot 4 starts. Use 0.5-second steps. This timing is independent of Timeline Progress start times; the UI dynamically limits the maximum to video duration minus 0.5 seconds. |
| camera_shot_4_transition | COMBO | cut | Transition used when Shot 4 starts. |
| camera_shot_4_target | COMBO | current_action | What Shot 4 should frame. |
| camera_shot_4_framing | COMBO | auto | Framing for Shot 4. Available choices follow the selected target. |
| camera_shot_4_motion | COMBO | auto | Optional camera movement inside Shot 4 after its transition. |
| camera_shot_4_amplitude | COMBO | inherit | Amplitude for Shot 4 camera motion. Follow Base Settings inherits the top Camera Amplitude; Default ยท Omit suppresses the amplitude phrase for this Shot; Small/Large override it only for this Shot. |
| camera_shot_4_speed | COMBO | inherit | Speed for Shot 4 camera motion. Follow Base Settings inherits the top Camera Speed; Default ยท Omit suppresses the speed phrase for this Shot; Slow/Fast override it only for this Shot. |
| camera_shot_5_enabled | BOOLEAN | false | Enable Shot 5. When ON, set Shot 5 Start Time (seconds). Shot timing is independent of Timeline Progress timing. Shots must be enabled in order without gaps. |
| camera_shot_5_start_seconds | FLOAT | 2.00.5โ29.5 | Video time in seconds when Shot 5 starts. Use 0.5-second steps. This timing is independent of Timeline Progress start times; the UI dynamically limits the maximum to video duration minus 0.5 seconds. |
| camera_shot_5_transition | COMBO | cut | Transition used when Shot 5 starts. |
| camera_shot_5_target | COMBO | current_action | What Shot 5 should frame. |
| camera_shot_5_framing | COMBO | auto | Framing for Shot 5. Available choices follow the selected target. |
| camera_shot_5_motion | COMBO | auto | Optional camera movement inside Shot 5 after its transition. |
| camera_shot_5_amplitude | COMBO | inherit | Amplitude for Shot 5 camera motion. Follow Base Settings inherits the top Camera Amplitude; Default ยท Omit suppresses the amplitude phrase for this Shot; Small/Large override it only for this Shot. |
| camera_shot_5_speed | COMBO | inherit | Speed for Shot 5 camera motion. Follow Base Settings inherits the top Camera Speed; Default ยท Omit suppresses the speed phrase for this Shot; Slow/Fast override it only for this Shot. |
| camera_shot_6_enabled | BOOLEAN | false | Enable Shot 6. When ON, set Shot 6 Start Time (seconds). Shot timing is independent of Timeline Progress timing. Shots must be enabled in order without gaps. |
| camera_shot_6_start_seconds | FLOAT | 2.50.5โ29.5 | Video time in seconds when Shot 6 starts. Use 0.5-second steps. This timing is independent of Timeline Progress start times; the UI dynamically limits the maximum to video duration minus 0.5 seconds. |
| camera_shot_6_transition | COMBO | cut | Transition used when Shot 6 starts. |
| camera_shot_6_target | COMBO | current_action | What Shot 6 should frame. |
| camera_shot_6_framing | COMBO | auto | Framing for Shot 6. Available choices follow the selected target. |
| camera_shot_6_motion | COMBO | auto | Optional camera movement inside Shot 6 after its transition. |
| camera_shot_6_amplitude | COMBO | inherit | Amplitude for Shot 6 camera motion. Follow Base Settings inherits the top Camera Amplitude; Default ยท Omit suppresses the amplitude phrase for this Shot; Small/Large override it only for this Shot. |
| camera_shot_6_speed | COMBO | inherit | Speed for Shot 6 camera motion. Follow Base Settings inherits the top Camera Speed; Default ยท Omit suppresses the speed phrase for this Shot; Slow/Fast override it only for this Shot. |
| reference_fidelity | COMBO | balanced | 3 options: strict, balanced, creative |
| soundscape_mode | COMBO | auto | Controls ambience, physical-action sounds, and non-verbal human sounds. 'silent' suppresses those sounds only; dialogue and non-diegetic music remain separate. If both are also absent, overall_soundscape uses N/A for complete silence. |
| sound_hint | STRING | Optional ambience, physical-action sound, or non-verbal human sound. Do not put spoken dialogue or music here. English is recommended; Korean input is translated internally to English before H3 prompt assembly. | |
| music_mode | COMBO | none | 33 options: none, sparse_piano_strings, acoustic_guitar_bass, classical_guitar, soft_light_music, gentle_classical, +27 |
| music_hint | STRING | Optional audience-only non-diegetic music description. Prefer instrumentation, tempo/speed, rhythm, texture, and dynamic changes; avoid abstract mood/emotional-function wording. Korean input is translated internally to English. | |
| dialogue_text | STRING | Legacy serialized workflow field retained only for backward-compatible widget alignment. Current runtime ignores this field; use Timeline dialogue instead. | |
| dialogue_language | COMBO | auto | Legacy serialized workflow field retained only for backward-compatible widget alignment. Current runtime ignores this value; use Timeline dialogue language instead. |
| dialogue_delivery | COMBO | on_screen | Legacy serialized workflow field retained only for backward-compatible widget alignment. Current runtime ignores this value; use Timeline dialogue delivery instead. |
| person_count | INT | 11โ3 | How many main character profiles are available to the ordered action/dialogue steps. |
| turn_count | INT | 11โ6 | Number of timeline events shown in the UI. Each visible row is one real event with one target person/group, one start time, one action, one dialogue field, one dialogue language, and one delivery mode. Final prompt order still follows start time. |
| person_a_gender | COMBO | unspecified | Optional profile detail for Main Character 1. |
| person_a_age | COMBO | unspecified | Optional age group for Main Character 1. Final prompts use natural phrases such as a woman in her thirties. Adult-only built-in presets are selectable only with an explicit age of 20s or older; changing to another age temporarily hides an incompatible preset and restores it when an adult age is selected again. |
| person_a_advanced | BOOLEAN | false | Show or hide advanced per-person profile options for Main Character 1. Hidden values are preserved and restored when shown again or when person count changes. |
| person_a_appearance_preset | COMBO | none | Optional appearance preset for Main Character 1. Combines naturally with Appearance Additional Input when both are used. Adult-only built-in choices are available only with an explicit age of 20s or older. |
| person_a_appearance_desc | STRING | Optional additional appearance/body description for Main Character 1. English is recommended; Korean is translated internally. Prefer concrete body/build, silhouette, hair, or distinctive physical traits over vague beauty adjectives. This is combined with the appearance preset when both are provided. | |
| person_a_clothing_preset | COMBO | none | Optional clothing preset for Main Character 1. Combines naturally with Clothing Additional Input when both are used. Adult-only built-in choices are available only with an explicit age of 20s or older. |
| person_a_clothing_desc | STRING | Optional additional clothing for Main Character 1. English is recommended; Korean is translated internally. Examples: color, material, or a specific garment refinement. This is combined with the clothing preset when both are provided. | |
| person_a_voice_desc | STRING | Optional voice identity for Main Character 1. English is recommended; Korean description is translated internally. Its H3 S ID is assigned at this character's first spoken line and reused afterward. | |
| person_b_gender | COMBO | unspecified | Optional profile detail for Main Character 2. |
| person_b_age | COMBO | unspecified | Optional age group for Main Character 2. Final prompts use natural phrases such as a man in his fifties. Adult-only built-in presets are selectable only with an explicit age of 20s or older; changing to another age temporarily hides an incompatible preset and restores it when an adult age is selected again. |
| person_b_advanced | BOOLEAN | false | Show or hide advanced per-person profile options for Main Character 2. Hidden values are preserved and restored when shown again or when person count changes. |
| person_b_appearance_preset | COMBO | none | Optional appearance preset for Main Character 2. Combines naturally with Appearance Additional Input when both are used. Adult-only built-in choices are available only with an explicit age of 20s or older. |
| person_b_appearance_desc | STRING | Optional additional appearance/body description for Main Character 2. English is recommended; Korean is translated internally. This is combined with the appearance preset when both are provided. | |
| person_b_clothing_preset | COMBO | none | Optional clothing preset for Main Character 2. Combines naturally with Clothing Additional Input when both are used. Adult-only built-in choices are available only with an explicit age of 20s or older. |
| person_b_clothing_desc | STRING | Optional additional clothing for Main Character 2. English is recommended; Korean is translated internally. This is combined with the clothing preset when both are provided. | |
| person_b_voice_desc | STRING | Optional voice identity for Main Character 2. English is recommended; Korean description is translated internally. Its H3 S ID is assigned at this character's first spoken line and reused afterward. | |
| person_c_gender | COMBO | unspecified | Optional profile detail for Main Character 3. |
| person_c_age | COMBO | unspecified | Optional age group for Main Character 3. Final prompts use natural English age wording. Adult-only built-in presets are selectable only with an explicit age of 20s or older; changing to another age temporarily hides an incompatible preset and restores it when an adult age is selected again. |
| person_c_advanced | BOOLEAN | false | Show or hide advanced per-person profile options for Main Character 3. Hidden values are preserved and restored when shown again or when person count changes. |
| person_c_appearance_preset | COMBO | none | Optional appearance preset for Main Character 3. Combines naturally with Appearance Additional Input when both are used. Adult-only built-in choices are available only with an explicit age of 20s or older. |
| person_c_appearance_desc | STRING | Optional additional appearance/body description for Main Character 3. English is recommended; Korean is translated internally. This is combined with the appearance preset when both are provided. | |
| person_c_clothing_preset | COMBO | none | Optional clothing preset for Main Character 3. Combines naturally with Clothing Additional Input when both are used. Adult-only built-in choices are available only with an explicit age of 20s or older. |
| person_c_clothing_desc | STRING | Optional additional clothing for Main Character 3. English is recommended; Korean is translated internally. This is combined with the clothing preset when both are provided. | |
| person_c_voice_desc | STRING | Optional voice identity for Main Character 3. English is recommended; Korean description is translated internally. Its H3 S ID is assigned at this character's first spoken line and reused afterward. | |
| turn_1_speaker | COMBO | A | Target person(s) for this timeline event. This row is one real event. If you want another person to act or speak at a different moment, use the next Timeline row. Combined targets act or speak together. |
| turn_1_elapsed_seconds | FLOAT | 0.00โ29.5 | Approximate start-time target for this timeline event, not a frame-exact trigger. Natural sequential motion and normal playback speed take priority. The UI uses 0.5-second steps and dynamically limits the maximum to video duration minus 0.5 seconds (for example, 10 seconds โ 9.5, 30 seconds โ 29.5). |
| turn_1_action | STRING | Describe what happens at this timeline event. English is recommended. Korean action text is translated internally to English before H3 prompt assembly and always remains an action; dialogue text is never auto-translated. | |
| turn_1_dialogue_text | STRING | Optional spoken line for this step. The original dialogue text is preserved and is never auto-translated. | |
| turn_1_dialogue_language | COMBO | auto | Language tag written inside H3 <d>[Language] ...</d>. Auto prioritizes Korean vs English and also recognizes obvious supported writing systems; choose a language manually when another language needs an exact tag. |
| turn_1_dialogue_delivery | COMBO | on_screen | Choose direct on-screen speech or off-screen voiceover for this line. |
| turn_1_vocal_2_text | STRING | Progress 1 Vocal 2 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_1_vocal_3_text | STRING | Progress 1 Vocal 3 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_2_speaker | COMBO | A | Target person(s) for this timeline event. This row is one real event. If you want another person to act or speak at a different moment, use the next Timeline row. Combined targets act or speak together. |
| turn_2_elapsed_seconds | FLOAT | 0.00โ29.5 | Approximate start-time target for this timeline event, not a frame-exact trigger. Natural sequential motion and normal playback speed take priority. The UI uses 0.5-second steps and dynamically limits the maximum to video duration minus 0.5 seconds (for example, 10 seconds โ 9.5, 30 seconds โ 29.5). |
| turn_2_action | STRING | Describe what happens at this timeline event. English is recommended. Korean action text is translated internally to English before H3 prompt assembly and always remains an action; dialogue text is never auto-translated. | |
| turn_2_dialogue_text | STRING | Optional spoken line for this step. The original dialogue text is preserved and is never auto-translated. | |
| turn_2_dialogue_language | COMBO | auto | Language tag written inside H3 <d>[Language] ...</d>. Auto prioritizes Korean vs English and also recognizes obvious supported writing systems; choose a language manually when another language needs an exact tag. |
| turn_2_dialogue_delivery | COMBO | on_screen | Choose direct on-screen speech or off-screen voiceover for this line. |
| turn_2_vocal_2_text | STRING | Progress 2 Vocal 2 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_2_vocal_3_text | STRING | Progress 2 Vocal 3 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_3_speaker | COMBO | A | Target person(s) for this timeline event. This row is one real event. If you want another person to act or speak at a different moment, use the next Timeline row. Combined targets act or speak together. |
| turn_3_elapsed_seconds | FLOAT | 0.00โ29.5 | Approximate start-time target for this timeline event, not a frame-exact trigger. Natural sequential motion and normal playback speed take priority. The UI uses 0.5-second steps and dynamically limits the maximum to video duration minus 0.5 seconds (for example, 10 seconds โ 9.5, 30 seconds โ 29.5). |
| turn_3_action | STRING | Describe what happens at this timeline event. English is recommended. Korean action text is translated internally to English before H3 prompt assembly and always remains an action; dialogue text is never auto-translated. | |
| turn_3_dialogue_text | STRING | Optional spoken line for this step. The original dialogue text is preserved and is never auto-translated. | |
| turn_3_dialogue_language | COMBO | auto | Language tag written inside H3 <d>[Language] ...</d>. Auto prioritizes Korean vs English and also recognizes obvious supported writing systems; choose a language manually when another language needs an exact tag. |
| turn_3_dialogue_delivery | COMBO | on_screen | Choose direct on-screen speech or off-screen voiceover for this line. |
| turn_3_vocal_2_text | STRING | Progress 3 Vocal 2 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_3_vocal_3_text | STRING | Progress 3 Vocal 3 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_4_speaker | COMBO | A | Target person(s) for this timeline event. This row is one real event. If you want another person to act or speak at a different moment, use the next Timeline row. Combined targets act or speak together. |
| turn_4_elapsed_seconds | FLOAT | 0.00โ29.5 | Approximate start-time target for this timeline event, not a frame-exact trigger. Natural sequential motion and normal playback speed take priority. The UI uses 0.5-second steps and dynamically limits the maximum to video duration minus 0.5 seconds (for example, 10 seconds โ 9.5, 30 seconds โ 29.5). |
| turn_4_action | STRING | Describe what happens at this timeline event. English is recommended. Korean action text is translated internally to English before H3 prompt assembly and always remains an action; dialogue text is never auto-translated. | |
| turn_4_dialogue_text | STRING | Optional spoken line for this step. The original dialogue text is preserved and is never auto-translated. | |
| turn_4_dialogue_language | COMBO | auto | Language tag written inside H3 <d>[Language] ...</d>. Auto prioritizes Korean vs English and also recognizes obvious supported writing systems; choose a language manually when another language needs an exact tag. |
| turn_4_dialogue_delivery | COMBO | on_screen | Choose direct on-screen speech or off-screen voiceover for this line. |
| turn_4_vocal_2_text | STRING | Progress 4 Vocal 2 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_4_vocal_3_text | STRING | Progress 4 Vocal 3 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_5_speaker | COMBO | A | Target person(s) for this timeline event. This row is one real event. If you want another person to act or speak at a different moment, use the next Timeline row. Combined targets act or speak together. |
| turn_5_elapsed_seconds | FLOAT | 0.00โ29.5 | Approximate start-time target for this timeline event, not a frame-exact trigger. Natural sequential motion and normal playback speed take priority. The UI uses 0.5-second steps and dynamically limits the maximum to video duration minus 0.5 seconds (for example, 10 seconds โ 9.5, 30 seconds โ 29.5). |
| turn_5_action | STRING | Describe what happens at this timeline event. English is recommended. Korean action text is translated internally to English before H3 prompt assembly and always remains an action; dialogue text is never auto-translated. | |
| turn_5_dialogue_text | STRING | Optional spoken line for this step. The original dialogue text is preserved and is never auto-translated. | |
| turn_5_dialogue_language | COMBO | auto | Language tag written inside H3 <d>[Language] ...</d>. Auto prioritizes Korean vs English and also recognizes obvious supported writing systems; choose a language manually when another language needs an exact tag. |
| turn_5_dialogue_delivery | COMBO | on_screen | Choose direct on-screen speech or off-screen voiceover for this line. |
| turn_5_vocal_2_text | STRING | Progress 5 Vocal 2 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_5_vocal_3_text | STRING | Progress 5 Vocal 3 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_6_speaker | COMBO | A | Target person(s) for this timeline event. This row is one real event. If you want another person to act or speak at a different moment, use the next Timeline row. Combined targets act or speak together. |
| turn_6_elapsed_seconds | FLOAT | 0.00โ29.5 | Approximate start-time target for this timeline event, not a frame-exact trigger. Natural sequential motion and normal playback speed take priority. The UI uses 0.5-second steps and dynamically limits the maximum to video duration minus 0.5 seconds (for example, 10 seconds โ 9.5, 30 seconds โ 29.5). |
| turn_6_action | STRING | Describe what happens at this timeline event. English is recommended. Korean action text is translated internally to English before H3 prompt assembly and always remains an action; dialogue text is never auto-translated. | |
| turn_6_dialogue_text | STRING | Optional spoken line for this step. The original dialogue text is preserved and is never auto-translated. | |
| turn_6_dialogue_language | COMBO | auto | Language tag written inside H3 <d>[Language] ...</d>. Auto prioritizes Korean vs English and also recognizes obvious supported writing systems; choose a language manually when another language needs an exact tag. |
| turn_6_dialogue_delivery | COMBO | on_screen | Choose direct on-screen speech or off-screen voiceover for this line. |
| turn_6_vocal_2_text | STRING | Progress 6 Vocal 2 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| turn_6_vocal_3_text | STRING | Progress 6 Vocal 3 dialogue. Preserved verbatim and connectable from an external STRING source. | |
| timeline_events_json | STRING | โ | |
| variation_seed | INT | 00โ9223372036854776000 | Legacy serialized workflow field retained only for backward-compatible widget alignment. Current Timeline runtime ignores this value. |
| i2va_preserve_reference_clothing | BOOLEAN | true | I2VA only. Keep clothing, colors, materials, and accessories from the start image stable throughout the entire video. While enabled, per-person clothing presets/free text are preserved in the workflow but ignored for prompt generation. Ordered Steps and shot count never toggle this value. |
| ultra_scene_validation_gate | COMBO | ok | 2 options: ok, missing |
| ultra_ui_locale | COMBO | en | 2 options: en, ko |
| ultra_extension_options_json | STRING | {} | โ |
| start_imageopt | IMAGE | Auto-mode topology signal and the required reference for manual I2VA/FL2VA. Manual T2VA ignores it for prompt-mode resolution. Pixels are never inspected. | |
| end_imageopt | IMAGE | Auto-mode topology signal and the required reference for manual L2VA/FL2VA. Manual T2VA and manual I2VA ignore it for prompt-mode resolution. Pixels are never inspected. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| h3_prompt | STRING | โ |
| info | STRING | โ |