{ "schema_version": 1, "concept_key": "play", "format": "landscape_16_9", "default_duration_seconds": 8, "videos": [ { "video_key": "play_context_01", "purpose": "model", "duration_seconds": 8, "reference_image": { "asset_key": "play_isolated_01", "filename": "../images/play_isolated_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 5-8 second close, uncluttered real-world demonstration of play, with a clear start and finish.", "setup": { "setting": "plain warm-white studio background", "depiction": "South Asian child actively stacking colorful wooden blocks", "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": "Establish actor, relevant objects and safe starting state; hold camera steady." }, { "timecode": "1.5-5.5", "story_beat": "Show the complete target action clearly: South Asian child actively stacking colorful wooden blocks. Keep hands, face and affected object visible." }, { "timecode": "5.5-8.0", "story_beat": "Show the natural completion state and hold it long enough to understand the result." } ], "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 'Play' (key play), purpose model. Use the approved reference image play_isolated_01.png for semantic content and visual continuity, not for identity preservation. Scene: South Asian child actively stacking colorful wooden blocks in plain warm-white studio background; 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": "play_context_02", "purpose": "functional_context", "duration_seconds": 8, "reference_image": { "asset_key": "play_natural_context_01", "filename": "../images/play_natural_context_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 6-10 second natural interaction showing play with a different person and setting; no acting exaggeration.", "setup": { "setting": "simple grassy park with bench", "depiction": "Black girl and East Asian boy playing catch with a red ball", "people": "two AI-generated children", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-1.5", "story_beat": "Establish actor, relevant objects and safe starting state; hold camera steady." }, { "timecode": "1.5-5.5", "story_beat": "Show the complete target action clearly: Black girl and East Asian boy playing catch with a red ball. Keep hands, face and affected object visible." }, { "timecode": "5.5-8.0", "story_beat": "Show the natural completion state and hold it long enough to understand the result." } ], "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 'Play' (key play), purpose functional_context. Use the approved reference image play_natural_context_01.png for semantic content and visual continuity, not for identity preservation. Scene: Black girl and East Asian boy playing catch with a red ball in simple grassy park with bench; participants: two AI-generated children. 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": "play_context_03", "purpose": "generalisation", "duration_seconds": 8, "reference_image": { "asset_key": "play_unfamiliar_01", "filename": "../images/play_unfamiliar_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A novel 6-10 second example of play for generalisation, with the target moment visible without narration.", "setup": { "setting": "simple community recreation room", "depiction": "Older South Asian woman and White man playing table tennis", "people": "two AI-generated adults", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-1.5", "story_beat": "Establish actor, relevant objects and safe starting state; hold camera steady." }, { "timecode": "1.5-5.5", "story_beat": "Show the complete target action clearly: Older South Asian woman and White man playing table tennis. Keep hands, face and affected object visible." }, { "timecode": "5.5-8.0", "story_beat": "Show the natural completion state and hold it long enough to understand the result." } ], "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 'Play' (key play), purpose generalisation. Use the approved reference image play_unfamiliar_01.png for semantic content and visual continuity, not for identity preservation. Scene: Older South Asian woman and White man playing table tennis in simple community recreation 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": [ "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" } ] }