{ "schema_version": 1, "concept_key": "want", "format": "landscape_16_9", "default_duration_seconds": 8, "videos": [ { "video_key": "want_context_01", "purpose": "model", "duration_seconds": 8, "reference_image": { "asset_key": "want_isolated_01", "filename": "../images/want_isolated_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 5-8 second close, uncluttered real-world demonstration of want, with a clear start and finish.", "setup": { "setting": "plain warm-white studio table", "depiction": "South Asian child pointing and reaching toward a red ball beside a blue block", "people": "one AI-generated child", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-2.0", "story_beat": "Establish the everyday situation and communication partner or meaningful cause." }, { "timecode": "2.0-5.5", "story_beat": "Show the target intent or emotion with congruent facial, body and contextual cues: South Asian child pointing and reaching toward a red ball beside a blue block." }, { "timecode": "5.5-8.0", "story_beat": "Show an appropriate partner response or stable emotional aftermath; preserve autonomy and natural expression." } ], "shot_list": [ { "shot": 1, "framing": "wide or medium establishing shot", "movement": "locked-off or very slow push-in", "focus": "context plus target", "duration_seconds": 2 }, { "shot": 2, "framing": "medium close shot", "movement": "locked-off", "focus": "face, hands and communication partner", "duration_seconds": 4 }, { "shot": 3, "framing": "close result or response shot", "movement": "locked-off", "focus": "unambiguous completed meaning", "duration_seconds": 2 } ], "generation_prompt": "Create one 8-second landscape 16:9 realistic clinical-educational video for the language-independent concept 'Want' (key want), purpose model. Use the approved reference image want_isolated_01.png for semantic content and visual continuity, not for identity preservation. Scene: South Asian child pointing and reaching toward a red ball beside a blue block in plain warm-white studio table; participants: one AI-generated child. Begin with a stable establishing view, show one slow natural target action or reveal, then hold the completed meaning for at least two seconds. Keep the target continuously visible, anatomically and physically plausible, safely framed and naturally lit. Use at most one simple camera cut; no fast zoom, montage or dramatic acting. Language-neutral: no necessary speech and no embedded writing. Preserve culturally respectful, disability-inclusive representation.", "negative_constraints": [ "no captions, labels, readable text, letters, numbers, logos, brands or watermark", "no jump cuts, time lapse, fast camera movement, flicker, strobe, looping discontinuity or motion smear", "no extra fingers, fused limbs, changing identity, changing clothing, morphing objects or disappearing props", "no unsafe, frightening, coercive, humiliating or medically distressing behavior", "no target hidden by hands, crop, foreground objects or shallow focus at the teaching moment", "no music as a meaning cue and no speech required to understand the concept" ], "audio_plan": { "production_audio": "quiet natural room tone only", "speech": "none required", "music": "none", "localized_voiceover": "optional separate approved track" }, "accessibility": { "captions": "required if any speech is added", "audio_description": "author from narrative_intent after picture lock", "photosensitivity": "no flashes or rapid cuts", "silent_comprehension": "required" }, "safety_and_semantics": [ "Honor refusal and consent; wanting does not authorize taking or contact.", "Localize from semantic intent rather than translating the English label literally.", "Clinical and native-language/cultural review are required before approval." ], "review_gates": [ "technical continuity", "target clarity", "SLP review", "accessibility review", "cultural review", "rights and releases" ], "status": "prompt_ready_review_required" }, { "video_key": "want_context_02", "purpose": "functional_context", "duration_seconds": 8, "reference_image": { "asset_key": "want_natural_context_01", "filename": "../images/want_natural_context_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 6-10 second natural interaction showing want with a different person and setting; no acting exaggeration.", "setup": { "setting": "home snack table", "depiction": "East Asian child selecting a banana instead of water from a Black adult", "people": "one AI-generated child and one AI-generated adult", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-2.0", "story_beat": "Establish the everyday situation and communication partner or meaningful cause." }, { "timecode": "2.0-5.5", "story_beat": "Show the target intent or emotion with congruent facial, body and contextual cues: East Asian child selecting a banana instead of water from a Black adult." }, { "timecode": "5.5-8.0", "story_beat": "Show an appropriate partner response or stable emotional aftermath; preserve autonomy and natural expression." } ], "shot_list": [ { "shot": 1, "framing": "wide or medium establishing shot", "movement": "locked-off or very slow push-in", "focus": "context plus target", "duration_seconds": 2 }, { "shot": 2, "framing": "medium close shot", "movement": "locked-off", "focus": "face, hands and communication partner", "duration_seconds": 4 }, { "shot": 3, "framing": "close result or response shot", "movement": "locked-off", "focus": "unambiguous completed meaning", "duration_seconds": 2 } ], "generation_prompt": "Create one 8-second landscape 16:9 realistic clinical-educational video for the language-independent concept 'Want' (key want), purpose functional_context. Use the approved reference image want_natural_context_01.png for semantic content and visual continuity, not for identity preservation. Scene: East Asian child selecting a banana instead of water from a Black adult in home snack table; participants: one AI-generated child and one AI-generated adult. Begin with a stable establishing view, show one slow natural target action or reveal, then hold the completed meaning for at least two seconds. Keep the target continuously visible, anatomically and physically plausible, safely framed and naturally lit. Use at most one simple camera cut; no fast zoom, montage or dramatic acting. Language-neutral: no necessary speech and no embedded writing. Preserve culturally respectful, disability-inclusive representation.", "negative_constraints": [ "no captions, labels, readable text, letters, numbers, logos, brands or watermark", "no jump cuts, time lapse, fast camera movement, flicker, strobe, looping discontinuity or motion smear", "no extra fingers, fused limbs, changing identity, changing clothing, morphing objects or disappearing props", "no unsafe, frightening, coercive, humiliating or medically distressing behavior", "no target hidden by hands, crop, foreground objects or shallow focus at the teaching moment", "no music as a meaning cue and no speech required to understand the concept" ], "audio_plan": { "production_audio": "quiet natural room tone only", "speech": "none required", "music": "none", "localized_voiceover": "optional separate approved track" }, "accessibility": { "captions": "required if any speech is added", "audio_description": "author from narrative_intent after picture lock", "photosensitivity": "no flashes or rapid cuts", "silent_comprehension": "required" }, "safety_and_semantics": [ "Honor refusal and consent; wanting does not authorize taking or contact.", "Localize from semantic intent rather than translating the English label literally.", "Clinical and native-language/cultural review are required before approval." ], "review_gates": [ "technical continuity", "target clarity", "SLP review", "accessibility review", "cultural review", "rights and releases" ], "status": "prompt_ready_review_required" }, { "video_key": "want_context_03", "purpose": "generalisation", "duration_seconds": 8, "reference_image": { "asset_key": "want_unfamiliar_01", "filename": "../images/want_unfamiliar_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A novel 6-10 second example of want for generalisation, with the target moment visible without narration.", "setup": { "setting": "calm home living room", "depiction": "Older East Asian woman selecting a lavender blanket instead of water from a Black adult", "people": "two AI-generated adults", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-2.0", "story_beat": "Establish the everyday situation and communication partner or meaningful cause." }, { "timecode": "2.0-5.5", "story_beat": "Show the target intent or emotion with congruent facial, body and contextual cues: Older East Asian woman selecting a lavender blanket instead of water from a Black adult." }, { "timecode": "5.5-8.0", "story_beat": "Show an appropriate partner response or stable emotional aftermath; preserve autonomy and natural expression." } ], "shot_list": [ { "shot": 1, "framing": "wide or medium establishing shot", "movement": "locked-off or very slow push-in", "focus": "context plus target", "duration_seconds": 2 }, { "shot": 2, "framing": "medium close shot", "movement": "locked-off", "focus": "face, hands and communication partner", "duration_seconds": 4 }, { "shot": 3, "framing": "close result or response shot", "movement": "locked-off", "focus": "unambiguous completed meaning", "duration_seconds": 2 } ], "generation_prompt": "Create one 8-second landscape 16:9 realistic clinical-educational video for the language-independent concept 'Want' (key want), purpose generalisation. Use the approved reference image want_unfamiliar_01.png for semantic content and visual continuity, not for identity preservation. Scene: Older East Asian woman selecting a lavender blanket instead of water from a Black adult in calm home living room; participants: two AI-generated adults. Begin with a stable establishing view, show one slow natural target action or reveal, then hold the completed meaning for at least two seconds. Keep the target continuously visible, anatomically and physically plausible, safely framed and naturally lit. Use at most one simple camera cut; no fast zoom, montage or dramatic acting. Language-neutral: no necessary speech and no embedded writing. Preserve culturally respectful, disability-inclusive representation.", "negative_constraints": [ "no captions, labels, readable text, letters, numbers, logos, brands or watermark", "no jump cuts, time lapse, fast camera movement, flicker, strobe, looping discontinuity or motion smear", "no extra fingers, fused limbs, changing identity, changing clothing, morphing objects or disappearing props", "no unsafe, frightening, coercive, humiliating or medically distressing behavior", "no target hidden by hands, crop, foreground objects or shallow focus at the teaching moment", "no music as a meaning cue and no speech required to understand the concept" ], "audio_plan": { "production_audio": "quiet natural room tone only", "speech": "none required", "music": "none", "localized_voiceover": "optional separate approved track" }, "accessibility": { "captions": "required if any speech is added", "audio_description": "author from narrative_intent after picture lock", "photosensitivity": "no flashes or rapid cuts", "silent_comprehension": "required" }, "safety_and_semantics": [ "Honor refusal and consent; wanting does not authorize taking or contact.", "Localize from semantic intent rather than translating the English label literally.", "Clinical and native-language/cultural review are required before approval." ], "review_gates": [ "technical continuity", "target clarity", "SLP review", "accessibility review", "cultural review", "rights and releases" ], "status": "prompt_ready_review_required" } ] }