{ "schema_version": 1, "concept_key": "therapist", "format": "landscape_16_9", "default_duration_seconds": 8, "videos": [ { "video_key": "therapist_context_01", "purpose": "model", "duration_seconds": 8, "reference_image": { "asset_key": "therapist_isolated_01", "filename": "../images/therapist_isolated_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 5-8 second slow reveal and natural interaction with therapist, keeping the target in frame.", "setup": { "setting": "plain warm-white studio background", "depiction": "South Asian female speech-language therapist standing with blank clipboard", "people": "one AI-generated adult", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-2.0", "story_beat": "Begin with a wider contextual view that establishes role or place through ordinary activity." }, { "timecode": "2.0-5.5", "story_beat": "Move or cut once to the key identifying evidence: South Asian female speech-language therapist standing with blank clipboard." }, { "timecode": "5.5-8.0", "story_beat": "Hold a natural stable view; avoid posed gestures, uniforms or symbols as the sole cue." } ], "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 'Therapist' (key therapist), purpose model. Use the approved reference image therapist_isolated_01.png for semantic content and visual continuity, not for identity preservation. Scene: South Asian female speech-language therapist standing with blank clipboard in plain warm-white studio background; participants: 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": [ "Avoid white-coat stereotyping, restraint, forced compliance or identifiable clinical records.", "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": "therapist_context_02", "purpose": "functional_context", "duration_seconds": 8, "reference_image": { "asset_key": "therapist_natural_context_01", "filename": "../images/therapist_natural_context_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 6-10 second functional everyday use of therapist by a person, without unnecessary spoken language.", "setup": { "setting": "calm therapy room with tabletop mirror", "depiction": "Therapist guiding child through feather blowing", "people": "one AI-generated adult and one AI-generated child", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-2.0", "story_beat": "Begin with a wider contextual view that establishes role or place through ordinary activity." }, { "timecode": "2.0-5.5", "story_beat": "Move or cut once to the key identifying evidence: Therapist guiding child through feather blowing." }, { "timecode": "5.5-8.0", "story_beat": "Hold a natural stable view; avoid posed gestures, uniforms or symbols as the sole cue." } ], "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 'Therapist' (key therapist), purpose functional_context. Use the approved reference image therapist_natural_context_01.png for semantic content and visual continuity, not for identity preservation. Scene: Therapist guiding child through feather blowing in calm therapy room with tabletop mirror; participants: one AI-generated adult and 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 white-coat stereotyping, restraint, forced compliance or identifiable clinical records.", "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": "therapist_context_03", "purpose": "generalisation", "duration_seconds": 8, "reference_image": { "asset_key": "therapist_unfamiliar_01", "filename": "../images/therapist_unfamiliar_01.png", "usage": "semantic_and_composition_reference" }, "narrative_intent": "A 6-10 second novel setting or instance of therapist for generalisation.", "setup": { "setting": "inclusive calm therapy room", "depiction": "Muslim female therapist guiding object-to-picture matching", "people": "one AI-generated adult and one AI-generated child", "continuity_lock": [ "participant identity", "clothing", "target instance", "background layout", "lighting direction" ] }, "story_beats": [ { "timecode": "0.0-2.0", "story_beat": "Begin with a wider contextual view that establishes role or place through ordinary activity." }, { "timecode": "2.0-5.5", "story_beat": "Move or cut once to the key identifying evidence: Muslim female therapist guiding object-to-picture matching." }, { "timecode": "5.5-8.0", "story_beat": "Hold a natural stable view; avoid posed gestures, uniforms or symbols as the sole cue." } ], "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 'Therapist' (key therapist), purpose generalisation. Use the approved reference image therapist_unfamiliar_01.png for semantic content and visual continuity, not for identity preservation. Scene: Muslim female therapist guiding object-to-picture matching in inclusive calm therapy room; participants: one AI-generated adult and 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 white-coat stereotyping, restraint, forced compliance or identifiable clinical records.", "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" } ] }