{ "schema_version": 1, "concept_key": "foot", "format": "landscape_16_9", "default_duration_seconds": 8, "videos": [ { "video_key": "foot_context_01", "purpose": "model", "duration_seconds": 8, "reference_image": { "asset_key": "foot_isolated_01", "filename": "../images/foot_isolated_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 5-8 second slow reveal and natural interaction with foot, keeping the target in frame.", "setup": { "setting": "plain warm-white studio background", "depiction": "South Asian child's bare left foot in side-three-quarter view", "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 bare left foot in side-three-quarter view. 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 'Foot' (key foot), purpose model. Use the approved reference image foot_isolated_01.png for semantic content and visual continuity, not for identity preservation. Scene: South Asian child's bare left foot in side-three-quarter view 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": [ "Use safe everyday contexts, respectful representation and culturally familiar alternatives; avoid stereotypes and coercion.", "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": "foot_context_02", "purpose": "functional_context", "duration_seconds": 8, "reference_image": { "asset_key": "foot_natural_context_01", "filename": "../images/foot_natural_context_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 6-10 second functional everyday use of foot by a person, without unnecessary spoken language.", "setup": { "setting": "simple enclosed backyard", "depiction": "Black child uses a bare right foot to steady a red ball", "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 uses a bare right foot to steady a red ball. 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 'Foot' (key foot), purpose functional_context. Use the approved reference image foot_natural_context_01.png for semantic content and visual continuity, not for identity preservation. Scene: Black child uses a bare right foot to steady a red ball in simple enclosed backyard; 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": [ "Use safe everyday contexts, respectful representation and culturally familiar alternatives; avoid stereotypes and coercion.", "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": "foot_context_03", "purpose": "generalisation", "duration_seconds": 8, "reference_image": { "asset_key": "foot_unfamiliar_01", "filename": "../images/foot_unfamiliar_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 6-10 second novel setting or instance of foot for generalisation.", "setup": { "setting": "simple home room with face softly behind", "depiction": "older Black man's bare left foot extended toward camera", "people": "one AI-generated older adult", "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 man's bare left foot extended toward camera. 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 'Foot' (key foot), purpose generalisation. Use the approved reference image foot_unfamiliar_01.png for semantic content and visual continuity, not for identity preservation. Scene: older Black man's bare left foot extended toward camera in simple home room with face softly behind; participants: one AI-generated older 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": [ "Use safe everyday contexts, respectful representation and culturally familiar alternatives; avoid stereotypes and coercion.", "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" } ] }