ComfyUI Node
Multishot Advance Prompt Builder
A ComfyUI node in conditioning/minimax with 31 inputs and 8 outputs.
Multishot Advance Prompt Builder
- cartridge_metadata
- script_out
- shot_count_out
- prompt_builder_state
- project_name_out
- global_prompt_out
- reference_subjects_out
- report
- compiled_preview
◄project_nameMy_MultiShot_Advance_Project►
◄project_picker(manual / new project_name)►
◄subject_namethe woman in Picture 1►
◄identity_modesubject_definitions + retention_analysis►
◄prompt_contractauto►
◄task_modeauto►
◄reference_images1►
◄reference_image_groups►
◄reference_image_roleoff►
◄reference_videos0►
◄reference_video_rolevideo_structure_reference►
◄reference_video_audio_rolevoice_timbre_reference►
◄reference_audios0►
◄global_placementevery_shot►
◄style_presetOff►
◄shot_templateOff►
◄camera_presetOff►
◄shot_count0►
◄speech_policyauto►
◄subject_descriptiondefined by her exact facial identity, facial structure, facial features, eyes, nose, mouth, jawline, skin appearance, hair, hairstyle, and overall visual identity. Her face and identity must remain unmistakably identical to <Picture 1> throughout the entire video.►
◄retention_focusher exact identity, face, hair, hairstyle, physical proportions, wardrobe identity, lighting continuity and overall visual consistency►
◄secondary_subjects►
◄global_prompt►
◄style_prompt►
◄soundscape_prompt►
◄music_prompt►
◄shot_script►
◄external_prompt_import_hash►
◄external_prompt_import_payload►
◄external_prompt_input—►
Categoryconditioning/minimax
Inputs (31)
| Name | Type | Default | Description |
|---|---|---|---|
| project_name | STRING | My_MultiShot_Advance_Project | Project name used by the load button and usually wired to Multishot Advance Project.project_name_override. |
| project_picker | COMBO | (manual / new project_name) | Existing Multishot Advance projects. Select one to set project_name without typing, then use Load project prompts to refill this builder from project.json. |
| subject_name | STRING | the woman in Picture 1 | Short human-readable name/role for <Subject 1>. Keep this short; put the detailed identity text in subject_description. |
| identity_mode | COMBO | subject_definitions + retention_analysis | Structured mode writes MiniMax-H3 subject and retention blocks. Plain mode only prepends the description as text. |
| prompt_contract | COMBO | auto | Builder intent only. auto selects full_reference when declared refs exist, otherwise base. The Sampler validates the final contract from actual runtime tensors and references. |
| task_mode | COMBO | auto | Base task intent stored in builder/project state. The Sampler resolves T2VA/I2VA/FL2VA/L2VA from actual first/last-frame tensors. |
| reference_images | INT | 10–16 | How many <Picture N> references the prompt should name. Match the images wired to the sampler. |
| reference_image_groups | STRING | Optional multi-person picture grouping, same format as sampler reference_subjects. Example: '3,3' means pictures 1-3 are <Subject 1>, 4-6 are <Subject 2>. | |
| reference_image_role | COMBO | off | Declared role for <Picture N> items. Identity-only pictures stay inside their <Subject N> source; concrete first/last frame and storyboard roles get standalone definitions. The Sampler validates the actual runtime role and tensor binding. |
| reference_videos | INT | 00–4 | How many <Video N> references the prompt should name. |
| reference_video_role | COMBO | video_structure_reference | Explicit role for declared <Video N> items. Only video_continuation_source produces the video continuation task type. |
| reference_video_audio_role | COMBO | voice_timbre_reference | Audio role independent from reference_video_role. Voice timbre enters only clips with structured or explicit foreground speech; ambience, rhythm and copy roles can condition silent clips. off ignores the paired reference_video_audio signal. |
| reference_audios | INT | 00–4 | How many <Audio N> references the prompt should name. |
| global_placement | COMBO | every_shot | every_shot is best for separate H3 clips. first_shot_only keeps later prompts shorter but identity may drift. |
| style_preset | COMBO | Off | Optional style preset bank. Off means the builder adds no preset text and you stay fully manual. |
| shot_template | COMBO | Off | Optional shot formatting. Off preserves pure manual shot text only when no builder global/identity/silent/anchor guidance is active; otherwise H3 official description sections are used. |
| camera_preset | COMBO | Off | Optional camera preset applied to each effective shot. Off means camera wording is left entirely to shot_script. |
| shot_count | INT | 00–100 | 0 = use the parsed independent clip count. A higher value repeats the last clip; a lower value renders only the first requested clips. |
| speech_policy | COMBO | auto | auto lets shot text decide speech. force_silent adds positive closed-mouth performance and environmental soundscape wording. allow_dialogue keeps explicit dialogue cues active. |
| subject_description | STRING | defined by her exact facial identity, facial structure, facial features, eyes, nose, mouth, jawline, skin appearance, hair, hairstyle, and overall visual identity. Her face and identity must remain unmistakably identical to <Picture 1> throughout the entire video. | Identity description derived from the reference image/video: face, hair, skin, wardrobe, posture, age range, distinctive details. Do not write '<Subject 1> is' here; the builder adds it. |
| retention_focus | STRING | her exact identity, face, hair, hairstyle, physical proportions, wardrobe identity, lighting continuity and overall visual consistency | What the retention_analysis block tells H3 to preserve across clips. Do not write 'retention_analysis:' here; the builder adds it. |
| secondary_subjects | STRING | Optional: one extra subject description per line. They become <Subject 2>, <Subject 3>, ... | |
| global_prompt | STRING | World, location, character rules or continuity notes shared by all shots. | |
| style_prompt | STRING | Cinematography, lens, lighting, colour and motion style shared by all shots. | |
| soundscape_prompt | STRING | Optional overall_soundscape text used by H3 shot templates. Empty uses a conservative automatic soundscape. | |
| music_prompt | STRING | Optional non_diegetic_music text used by H3 shot templates. Empty becomes N/A. | |
| shot_script | STRING | Write one target video clip per --- block. Inside a clip, keep real camera cuts as [Shot 1], [Shot 2], [Shot 3] with official cut timestamps. | |
| external_prompt_import_hash | STRING | Internal one-shot import marker. The frontend keeps this hidden. | |
| external_prompt_import_payload | STRING | Internal lossless External Importer state. The frontend keeps this field hidden; editing any imported Builder field safely disables its stale override. | |
| external_prompt_inputopt | STRING | Optional STRING socket for incomplete/experimental external prompt import. A new connected prompt is imported into editable Prompt Builder fields on the first Run; downstream execution is blocked until the user runs the workflow again. | |
| cartridge_metadataopt | MULTISHOT_ADVANCE_CARTRIDGE_METADATA | Typed metadata from Multishot Advance Cartridge Loader. It supplies label-free identity prose; actual Picture/Audio labels still come from wired runtime references and the central registry. |
Outputs (8)
| Name | Type | Description |
|---|---|---|
| script_out | STRING | — |
| shot_count_out | INT | — |
| prompt_builder_state | MULTISHOT_ADVANCE_PROMPT_BUILDER_STATE | — |
| project_name_out | STRING | — |
| global_prompt_out | STRING | — |
| reference_subjects_out | STRING | — |
| report | STRING | — |
| compiled_preview | STRING | — |