{ "schema_version": 1, "concept_key": "mouth", "format": "landscape_16_9", "default_duration_seconds": 8, "videos": [ { "video_key": "mouth_context_01", "purpose": "model", "duration_seconds": 8, "reference_image": { "asset_key": "mouth_isolated_01", "filename": "../images/mouth_isolated_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 5-8 second slow reveal and natural interaction with mouth, keeping the target in frame.", "setup": { "setting": "plain warm-white studio background", "depiction": "South Asian child's mouth in neutral speech-ready position", "people": "one AI-generated child body part", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-1.5", "story_beat": "Begin with the target partly occluded or resting naturally while its context is visible." }, { "timecode": "1.5-5.5", "story_beat": "Reveal or interact with the target slowly and naturally: South Asian child's mouth in neutral speech-ready position. Keep the whole target readable." }, { "timecode": "5.5-8.0", "story_beat": "Hold the target fully visible for recognition and optional pause-frame use." } ], "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": "target, actor hands and relevant reference object", "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 'Mouth' (key mouth), purpose model. Use the approved reference image mouth_isolated_01.png for semantic content and visual continuity, not for identity preservation. Scene: South Asian child's mouth in neutral speech-ready position in plain warm-white studio background; participants: one AI-generated child body part. 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": [ "Avoid invasive close-ups, pain, dental procedures and forced imitation.", "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": "mouth_context_02", "purpose": "functional_context", "duration_seconds": 8, "reference_image": { "asset_key": "mouth_natural_context_01", "filename": "../images/mouth_natural_context_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 6-10 second functional everyday use of mouth by a person, without unnecessary spoken language.", "setup": { "setting": "bright uncluttered therapy room", "depiction": "Black child rounds lips to blow a green pinwheel", "people": "one AI-generated child", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-1.5", "story_beat": "Begin with the target partly occluded or resting naturally while its context is visible." }, { "timecode": "1.5-5.5", "story_beat": "Reveal or interact with the target slowly and naturally: Black child rounds lips to blow a green pinwheel. Keep the whole target readable." }, { "timecode": "5.5-8.0", "story_beat": "Hold the target fully visible for recognition and optional pause-frame use." } ], "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": "target, actor hands and relevant reference object", "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 'Mouth' (key mouth), purpose functional_context. Use the approved reference image mouth_natural_context_01.png for semantic content and visual continuity, not for identity preservation. Scene: Black child rounds lips to blow a green pinwheel in bright uncluttered therapy room; 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": [ "Avoid invasive close-ups, pain, dental procedures and forced imitation.", "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": "mouth_context_03", "purpose": "generalisation", "duration_seconds": 8, "reference_image": { "asset_key": "mouth_unfamiliar_01", "filename": "../images/mouth_unfamiliar_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 6-10 second novel setting or instance of mouth for generalisation.", "setup": { "setting": "plain soft-beige studio background", "depiction": "older Black adult's mouth in neutral speech-ready position", "people": "one AI-generated older adult body part", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-1.5", "story_beat": "Begin with the target partly occluded or resting naturally while its context is visible." }, { "timecode": "1.5-5.5", "story_beat": "Reveal or interact with the target slowly and naturally: older Black adult's mouth in neutral speech-ready position. Keep the whole target readable." }, { "timecode": "5.5-8.0", "story_beat": "Hold the target fully visible for recognition and optional pause-frame use." } ], "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": "target, actor hands and relevant reference object", "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 'Mouth' (key mouth), purpose generalisation. Use the approved reference image mouth_unfamiliar_01.png for semantic content and visual continuity, not for identity preservation. Scene: older Black adult's mouth in neutral speech-ready position in plain soft-beige studio background; participants: one AI-generated older adult body part. 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": [ "Avoid invasive close-ups, pain, dental procedures and forced imitation.", "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" } ] }