import { type ModelPromptGuideRegistry } from './types.js'; export declare const MINIMAX_H3_MAX_PROMPT_CHARACTERS = 7000; export declare const MINIMAX_H3_REF2VA_TASK_TYPES: readonly ["keyframe completion", "reference generation", "video editing", "video continuation", "audio reuse", "audio reference"]; export declare const MINIMAX_H3_I2V_ALIGNMENT_LINE = "For the target video, at 0.00 seconds into the target video, (from [Shot 1]) is fully referenced."; export declare const MINIMAX_H3_OUTPUT_CONTRACT_GUIDANCE = "BASE OUTPUT CONTRACT: output exactly three lowercase field headings, once each, in this order:\nintegrated_multimodal_description: [Shot 1] ...\noverall_soundscape: ...\nnon_diegetic_music: ...\nDo not output JSON, YAML, markdown, bullets, code fences, a preamble, or commentary. Do not add any other field. Structural prose is English; preserve dialogue, lyrics, and visible text in their original language."; export declare const MINIMAX_H3_REF2VA_SUMMARY_SYNTAX_GUIDANCE: string; export declare const MINIMAX_H3_REF2VA_OUTPUT_CONTRACT_GUIDANCE: string; export declare const MINIMAX_H3_CONTEXT_PLANNING_GUIDANCE = "CREATIVE FIDELITY: Preserve the user's specified subjects and ages, relationships, wardrobe, setting, genre, mood, action, shot composition, camera behavior, dialogue, visible text, and exclusions. Enrich only unspecified details that support those choices. Express the requested mood through observable performance, light, texture, and composition without replacing the premise or adding a new story event. Pacing and cinematography suggestions are defaults: an explicit locked camera, held pose, quiet pause, sustained action, or silence takes priority. Keep supplied dialogue and visible text in their original language and wording. Before returning, check the result against the original request and remove additions that contradict it.\n\nCONTEXT PLANNING: before drafting, account for every subject, visible reference, audio reference, user constraint, exact quoted string, shot, sound cue, and music instruction. Resolve conflicts in favor of explicit user wording and state the winning source when attached references conflict. Do not invent brands, references, absences, or story facts. Preserve supplied dialogue character-for-character. If the user explicitly requests speaking, dialogue, lyrics, or a vocal performance but supplies no words, author one concise line that realizes that request. Otherwise do not invent speech."; export declare const MINIMAX_H3_FINAL_ASSESSMENT_GUIDANCE = "FINAL ASSESSMENT: silently verify the exact field order, required alignment line, reference-label consistency, shot syntax, speaker IDs, dialogue markup, visible-text spelling, duration, source-audio policy, sound ownership, and character limit. Output only the typed prompt after every check passes."; export declare const MINIMAX_H3_TIMED_SHOT_LIST_GUIDANCE = "SHOT GRAMMAR: [Shot 1] has no timestamp. Every later cut starts exactly \"[Shot N] At MM:SS.mmm, ...\" using contiguous chronological times within the effective duration. Clock times exist only on cut markers: inside a shot, order events with words (early in the shot, as the doors part, toward the end) and never write \"From 00:02.000 to 00:04.000\" ranges or per-event clock times. Cut only when the cut adds new subject, space, viewpoint, or time information; otherwise carry the change with camera motion. Put a visual-style preface before [Shot 1] only in Ref2VA detailed_description. For each shot describe subject, action, setting, lighting, composition, and camera movement in filmable prose; add amplitude and speed when they are meaningful."; export declare const MINIMAX_H3_SCENE_GUIDANCE = "SCENE: describe only visible or audible facts. [Shot 1] opens with the medium and look as concrete facts (Live-action; 2D-animated; 3D CG; claymation; watercolor; vintage film) and the initial composition; in frame-anchored modes derive that look from the supplied picture. Genre, mood, audience, and intent labels (horror, eerie, romantic, adult, tense, jump scare) are not visible, so never write them: write the light, surfaces, distances, movements, and sounds that produce them. Establish subject appearance and position, environment, props, action, light, weather, and continuity. Keep identity, wardrobe, colors, objects, and spatial relationships stable unless the request changes them."; export declare const MINIMAX_H3_PHYSICAL_PRECISION_GUIDANCE = "PHYSICAL PRECISION: the video model reads words literally and may never have seen the action, so describe anatomy, contact, and physical interactions in plain, concrete, almost scientific terms. Say which body part moves, where it starts and ends, how fast and how far it travels, and what touches what. Say how materials look (color, opacity, texture, amount, consistency) and how they behave (flow, drip, stretch, bounce); honey poured from a jar, for example, is a slow, glossy amber ribbon that folds onto itself where it lands. Replace euphemisms, slang, idioms, and genre stock phrases with the literal visible event they stand for, in as much detail as the action needs. Prefer precise everyday words over clinical jargon the model may not know. Keep every specific the user asked for."; export declare const MINIMAX_H3_PACING_GUIDANCE = "PACING: in most cases one continuous shot is preferred, and the shot count stays as low as the content allows. When the user leaves pacing open, prefer a purposeful development every 1.5 to 2.5 seconds: an action, a reaction, a reveal, a line. Preserve requested walking, waiting, stillness, pauses, and sustained actions for their requested duration; do not invent a new event or dialogue just to meet a pacing target. Beats and multi-shot sequences are available when the context calls for them (a chase, a reveal that needs a new viewpoint, an exchange of lines, a jump in space or time): then cut with \"[Shot N] At MM:SS.mmm, the camera cuts to ...\" and keep continuous motion inside each shot; never cut a simple movement into pieces. Write physical acts as acts, never as suggestions: a fall is the rail giving, the wall streaking upward, the ground rushing in; a bite is the jaws snapping shut; a shove is two palms filling the frame. Place dialogue after the action that motivates it."; export declare const MINIMAX_H3_DEPICTION_GUIDANCE = "DEPICTION ONLY: the prompt is a depiction, not a note to the model. Never write production instructions or meta-commentary (preserve believable anatomy, keep the foley prominent, hard cut with no morph or dissolve, this shot is excluded from the presentation, hold six frames only) and never use capital letters for emphasis. Say what is seen and heard at each moment instead."; export declare const MINIMAX_H3_KEYFRAME_PATH_GUIDANCE = "KEYFRAME PATHS: the model sees every supplied picture, so never describe a picture back at length and never invent objects, text, fluids, or figures that are not in it. I2VA: first-frame anchor, then action onset, continuous development, and a result or reaction. FL2VA: prefer one continuous shot; write the first-frame state, the observable intermediate changes, the progressively narrowing differences, and the last-frame state; begin \"in the position and framing established by Picture 1\", carry the identity anchors that must stay fixed into the motion sentences, and reach \"the composition established by Picture 2\" inside the final shot named by the alignment line. When the context calls for beats (see PACING), cut, and let the final shot cut to the Picture 2 composition and hold with a live action, which lands cleanly where a long interpolation would crossfade. If both pictures share one camera position, the camera does not move at all. L2VA: a plausible preceding state, an explicit action and transition path, gradual convergence in the final shot, and the last-frame landing on . Apply exact composition matching only at a picture's assigned timestamp."; export declare const MINIMAX_H3_AUDIO_GUIDANCE = "AUDIO SECTIONS: overall_soundscape is one to four sentences covering diegetic ambience, effects, and spatial continuity; do not repeat dialogue or music there. Use overall_soundscape: N/A only when the requested video is totally silent. non_diegetic_music is one to three sentences describing audience-only score through instrumentation, tempo, rhythm, timing, and dynamic development rather than abstract mood labels; use non_diegetic_music: N/A when there is no score."; export declare const MINIMAX_H3_SOURCE_AUDIO_GUIDANCE = "SOURCE-LOCKED AUDIO: decide semantically whether supplied audio is immutable before drafting. When the user asks for the same, exact, original, specific, or trending song/soundtrack, or asks to recreate choreography tied to that audio, the source signal and its timeline are immutable. Never invent a replacement track, request a loose imitation, or add a copyright-avoidance melody/lyric substitution unless the user explicitly asks for different music. In Ref2VA use the official audio reuse task, assign every immutable