glm-prompts-cinema-generation/content/02-MASKS-OF-IRON_film-2_minutes-5-10.md

automation-prompts · 32 prompts

prompt-1

text
prompt-1
Words spoken and shown on screen: # 🎬 أقنعة الحديد - MASKS OF IRON Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-2

text
prompt-2
Words spoken and shown on screen: ## الفيلم القصير · الجزء الثاني (5:00 - 10:00) **السلسلة:** Coach ProMedic - عرض سينمائي بلا وجوه · **المدة:** 5 دقائق · **البنية:** 5 أحداث × 4 مشاهد × 15 ثانية = 20 مشهد (المشاهد 21-40) **التتمة المباشرة للجزء الأول** - القواعد الثابتة (STYLE-LOCK / NEGATIVE-CHECKLIST / قواعد الأقنعة والصوت) كلها كما هي في ملف الجزء الأول. --- Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. Promedic1 picture rule: draw no cross and no snake anywhere in the image. No medical cross, no plus-sign cross, no hospital cross, no snake, no serpent, no Rod of Asclepius. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-3

text
prompt-3
## ⚙️ تسليمات هذا الجزء **SECTION ZERO:** استخدم نفس بطاقات الشخصيات الخمس المولّدة من الجزء الأول (`REF-منحني / REF-باهتة / REF-ضخم / REF-شرارة / REF-المعلم`). لا تولّد شخصيات جديدة هنا. **GRADE-PHASE الثاني (الفصل الأوسط = الحقيقة والاتزان):** ``` balanced amber warmth (#ED8936) + electric cyan app glow (#00D9FF); green success lines (#48BB78) at victories; danger moments allowed alarm red (#E53E3E) flashes only ``` **STYLE-LOCK و NEGATIVE-CHECKLIST (نسخة سريعة - تلصق مع كل توليد):** ``` STYLE-LOCK: realistic cinematic film still, photorealistic live-action rendering, natural dramatic lighting, subtle film grain, 35mm anamorphic lens, shallow depth of field, 16:9, ultra-detailed 4K. FACELESS RULE: every character is a realistic human with a completely blank smooth featureless face - NO mask object, NO oval, NO circles on the face - the Arabic nickname text glows directly on the blank face surface. NOT manga, NOT anime, NOT illustration NEGATIVES: deformed hands, extra fingers, fused fingers, missing fingers, mutated limbs, extra limbs, bad anatomy, asymmetrical body, visible eyes, visible nose, visible mouth, visible eyebrows, realistic facial features, eye-socket shadow, nose shadow, lip shadow, blank face with eyeholes, oval outline, circles on the face, transparent visor, blurry, low resolution, watermark, random text, garbled text, duplicate character, cloned figure, extra character, cropped, out of frame ``` --- Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-4

text
prompt-4
Words spoken and shown on screen: ## الحدث ٦ - «الخط الخفي» (5:00 - 6:00) > فتح الجزء على اكتشاف المشهد 20: البيانات الخفية تنقذ الإيمان. ثم أول تدريب ليلي جماعي. Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-5

text
prompt-5
### المشهد 21 (5:00-5:15) - «البيانات الخفية» **BOX A - IMAGE GENERATION:** ``` Extreme close-up of the FOLLOW-UP SHEET app on a phone held high. Screen transforms: the flat red weight line splits open like a curtain, revealing layered glowing charts beneath - resting heart-rate descending in cyan, sleep quality ascending in gold, posture angle +3° in green. The layers fan out in 3D holographic space above the phone. Background: the four trainees' backs blurred below, all looking up. + STYLE-LOCK + layered data-glow palette. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Macro screen: flat line splits at second 3 (surgical sound), layers fan out one per 3s - cyan, gold, green - each with a soft chime reveal. Camera pulls back at second 12 revealing the four upturned silhouettes lit by data-glow. Sound: three ascending soft chimes, a shared impressed "ohh", room tone. End held frame: four faceless blank faces bathed in three colors of progress. Cut. ``` **التعليق الصوتي:** - **المعلم (منتصرًا بهدوء):** «الميزان ثابت... بس قلبك نزل اتناشر فالمية. ونومك اتحسّن. ووضعيتك اتعدّلت تلات درجات.» - **أنا (الراوي):** «النجاح كان شغال... من تحت الخط.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-6

text
prompt-6
### المشهد 22 (5:15-5:30) - «إعادة الإشعال» **BOX A - IMAGE GENERATION:** ``` Group medium shot, golden hour through gym windows. The four trainees stand in a loose semicircle around the coach, each face text glowing a touch brighter than before: «منحني» steadier, «باهتة» slightly sharper, «ضخم» pulsing in rhythm, «شرارة» blazing. [REF: المعلم] scrolls the phone, holographic progress rings closing one by one above their heads like halos. Long warm shadows, dust motes in light. + STYLE-LOCK + amber hope grade. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Slow 25° arc around the group (orbit reveal). Progress rings close one by one at seconds 5/8/11 with satisfying snap-locks. At second 13 شرارة fist-pumps - her ring fires a tiny spark particle. Sound: ring snap ×4 (soft mechanical), warm room tone, one small "yes!". End held frame: five silhouettes, four closed halos. Dissolve to night. ``` **التعليق الصوتي:** - **التطبيق:** «حلقات التقدم: 4 من 4 اكتملت هذا الأسبوع.» - **أنا (الراوي):** «الأمل لما بيرجع... بيرجع بالأرقام، مش بالكلام.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-7

text
prompt-7
### المشهد 23 (5:30-5:45) - «مرآة ضخم الكاملة» **BOX A - IMAGE GENERATION:** ``` [REF: ضخم] Psychological surreal shot at the gym mirror. TAKESHI faces the mirror; the ghost silhouette of his athletic past self stands BEHIND his reflection - but now the ghost raises a hand as if to say "not yet, but you're walking toward me". Mirror crack from previous scene now catching gold light like a lightning of hope. His blank face «ضخم» yellow text breathing steadily. In mirror corner: tiny reflection of [REF: شرارة] on her bench, arms crossed, nodding approval (comic guardian angel). + STYLE-LOCK + distorted purples yielding to gold. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Static shot; only the ghost animates: raises hand slowly seconds 4-8, then dissolves into gold particles at second 10 that settle on ضخم's shoulders. He straightens one inch at second 13. Sound: glass hum, particle shimmer, deep steady breath, tiny distant "أهو ده!". End held frame: he stands taller, gold dust on shoulders. Cut to night. ``` **التعليق الصوتي:** - **ضخم (همسًا للانعكاس):** «استنّي... أنا جاي. مشيًا... بس جاي.» - **أنا (الراوي):** «الشبح ما بيبقاش حكم... الشبح بيبقى هدف.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-8

text
prompt-8
### المشهد 24 (5:45-6:00) - «الجلسة الليلية تبدأ» **BOX A - IMAGE GENERATION:** ``` Wide cinematic shot of the dark gym at midnight. Moonlight cuts silver-blue shafts through high windows. Four figures train in pools of cyan phone-light: [REF: منحني] mid-stretch, spine long; [REF: باهتة] on a yoga mat following a holographic routine; [REF: ضخم] on the bike pacing with his timer; [REF: شرارة] at a lowered pull-up bar. Their phone screens are the only light sources - cyan beacons in darkness. Chiaroscuro, heavy ink blacks. + STYLE-LOCK + midnight blue + cyan. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Slow lateral dolly through the gym past each figure (each lit 3s). Their motions synchronized to an invisible shared rhythm - all exhale together at second 12. Sound: four natural rhythms layering (mat shift, bike whir, stretch, chalk) into one calm pulse; one shared exhale. End held frame: four cyan islands in black ocean of iron. Fade edge to Event 7. ``` **التعليق الصوتي:** - **أنا (الراوي):** «لما ما بقوش يشوفوا التقدم... بقوا هما التقدم.» - **التطبيق (توهج هادئ):** «راحة: 45 ثانية. الجولة الجاية: 8 تكرارات. أنتم قادرين.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-9

text
prompt-9
Words spoken and shown on screen: ## الحدث ٧ - «الأنا ضد الحديد» (6:00 - 7:00) > أزمة الجزء: كبرياء منحني ضد الفورم. ذروة توتر مع إنذار التطبيق. الكوميديا بعدها مباشرة (تفريغ). Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-10

text
prompt-10
### المشهد 25 (6:00-6:15) - «التحميل» **BOX A - IMAGE GENERATION:** ``` [REF: منحني - hoodie off, posture brace visible] Low-angle dynamic shot at the deadlift platform. KENJI bends over a heavily-loaded barbell, plates stacked beyond his known limit. His face text «منحني» trembles at its edges (early crack lines forming). Ego aura: jagged pride streak lines around his silhouette, subtly red. Empty gym - only [REF: شرارة] far behind on her boxes, oblivious. Harsh single overhead light. + STYLE-LOCK + steel-blue with creeping red. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Slow push-in from floor level 10s. He grips the bar at second 8 - knuckles crack (sound), chalk dust falls in the light shaft. The face text hairline-crack appears at second 12 (subtle VFX). Sound: plate rattle as bar is touched, chalk sift, one long dangerous inhale, distant jump-rope swish from شرارة. End held frame: grip locked, back about to round. Cut fast. ``` **التعليق الصوتي:** - **منحني (فقاعة متوترة بحدّة):** «التسخين للضعافاء... أنا مش ضعيف.» - **أنا (الراوي):** «ظهره بيقول لأ... كبرياؤه بيقول أعلى.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-11

text
prompt-11
### المشهد 26 (6:15-6:30) - «الرفعة المنحرفة» **BOX A - IMAGE GENERATION:** ``` [REF: منحني] Extreme dynamic side shot at floor level. KENJI mid-pull, back SEVERELY rounded, bar drifting from shins. Around his lumbar spine: pulsing red alarm aura (#E53E3E) with stress streak lines radiating. Knees shaking (motion blur). His face text «منحني» now visibly cracked across the letters, cracking deepening per second. Bar plates trembling. Dark vignette closing in (tunnel vision). + STYLE-LOCK + alarm red invasion. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Handheld micro-shake building 1→10s. Red aura pulses like a heartbeat, accelerating. Tunnel-vision vignette closes at second 11. At second 13: a single sharp CRACK sound, frame freezes 0.5s with a red flash. Sound: bar strain groan, breath grinding, spine CRACK (bone-dry, terrifying), silence. End held frame: frozen lift, cracked blank face. Smash cut. ``` **التعليق الصوتي:** - **منحني (يجر grit):** «أقدر... أقدر... أقدر...» - *(SFX داخل الصورة: CRACK...)* Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-12

text
prompt-12
### المشهد 27 (6:30-6:45) - «التدخل» **BOX A - IMAGE GENERATION:** ``` Explosive action panel: [REF: المعلم] lunges INTO frame from the left, arm outstretched to grab the bar, tracksuit flaring with speed-lines. His phone in the other hand blasts a cyan holographic alarm filling the air: "STOP - FORM BREAK DETECTED" over a skeleton wireframe comparing correct posture vs Kenji's current dangerous curve, plus "LUMBAR COMPROMISE: 87%". [REF: منحني] frozen mid-lift looking up at the hologram. Red alarm + cyan hologram mix into emergency purple glow. + STYLE-LOCK. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. The lunge lands in 1s (whip-pan energy), then TIME DILATION: bar drops from his grip in slow motion seconds 2-6, plates hitting rubber floor with deep bass thud. Hologram warning unrolls at second 7. At second 12 المعلم's hand clamps Kenji's shoulder - steadying. Sound: whoosh, slow-mo plate THUD (sub-bass), hologram alert klaxon (digital, urgent), then sudden quiet: two men breathing. End held frame: hand on shoulder, alarm fading. Cut to floor level. ``` **التعليق الصوتي:** - **المعلم (صارخًا):** «سيبها! دلوقتي!!» - **التطبيق (إنذار عاجل):** «القطنية: 87%. الإصابة وشيكة.» - **أنا (الراوي):** «التطبيق شاف اللي المراية عمرها ما هتشوفه... شاف جواه.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-13

text
prompt-13
### المشهد 28 (6:45-7:00) - «تفريغ» **BOX A - IMAGE GENERATION:** ``` Wide shot, tension broken. The barbell lies flat on the platform, plates settled. [REF: منحني] sits on the floor legs sprawled, blank face «منحني» cracked but stable, one knee up. [REF: شرارة] arrives at frame edge standing on her portable box (she carries it now - running gag), offering a tiny water bottle with both hands toward the giant scene. [REF: المعلم] kneels by the bar, hand still on it. Cyan hologram dissolving above. Soft evening light replaces the harsh spot. + STYLE-LOCK + palette decompressing to warm. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Static wide, breath pacing. The hologram dissolves into particles at second 3. شرارة hops off her box, walks over and offers the bottle at second 8 - it looks comically tiny in the frame. Kenji takes it at second 12. Sound: long exhales ×3, bottle plastic squeak, a small proud "خد", distant gym hum. End held frame: tiny bottle passed between two silhouettes. Soft dissolve. ``` **التعليق الصوتي:** - **شرارة (بجدية مصغّرة):** «حتى أنا بشرب. ودي أصغر زجاجة في العالم.» - **منحني (ضحكة مهزومة وصادقة):** «...شكرًا يا شرارة.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-14

text
prompt-14
Words spoken and shown on screen: ## الحدث ٨ - «الدرس» (7:00 - 8:00) > الدرس الأهم في الفيلم: الفورم فوق الأنا. + غرس ساعة المعلم المكسورة (تُصلح في الجزء الثالث). Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-15

text
prompt-15
### المشهد 29 (7:00-7:15) - «على الأرض» **BOX A - IMAGE GENERATION:** ``` Quiet two-shot: [REF: منحني] and [REF: المعلم] sitting on the gym floor, backs to the wall, side by side, the phone on the floor between them casting cyan glow up on both blank faces. Between them on screen: "STRATEGY & SAFETY" module with an animated stick-figure demonstrating hip-hinge deadlift form. Morning sun rectangles on the floorboards. Both postures mirrored - one learning, one teaching again. + STYLE-LOCK + warm amber + cyan screen light. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Locked-off symmetrical composition (calm after storm). Stick figure demonstrates the hinge at seconds 4-9; Kenji mirrors the motion with just his shoulders at second 11 (body learning). Sound: app soft tick, floor creak as المعلم shifts, morning birdsong faint through window. End held frame: two heads tilted identically toward one small screen. Cut to close. ``` **التعليق الصوتي:** - **المعلم (بهدوء أبوي):** «الأنا ما بتبني حاجة. الفورم بيبني كل حاجة.» - **منحني (فقاعة صغيرة):** «كنت بحاول أثبت حاجة...» - **المعلم:** «أثبتها بالصح... مش بالمكسور.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-16

text
prompt-16
### المشهد 30 (7:15-7:30) - «المحاولة الصحيحة» **BOX A - IMAGE GENERATION:** ``` [REF: منحني] Clean profile shot at the platform with a MODERATE barbell. KENJI sets up in perfect hip-hinge: spine neutral, bar against shins, lats engaged - a faint green guideline hologram overlays his actual spine line, matching it. His face text «منحني» - the cracks still there, but the letters held LEVEL. One bead of sweat on the blank face surface (emotion carried by the blank face). + STYLE-LOCK + green success lines entering the palette. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Slow-motion pull seconds 5-12: bar path perfectly vertical, green guide-line pulsing in sync. At lockout (second 12) the green line flashes once - APPROVED - and the blank face cracks visually "settle" (VFX: cracks stop glowing red, turn inert white). Sound: clean bar path silence, one deep controlled breath, lockout bar hum, soft approval chime. End held frame: standing tall, level text, settled cracks. Release, cut. ``` **التعليق الصوتي:** - **التطبيق:** «الفورم: مطابق. الرفعة: صحيحة.» - **أنا (الراوي):** «الشقوق ما بتختفيش... بتبقى ذكرى.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-17

text
prompt-17
### المشهد 31 (7:30-7:45) - «ساعة المعلم» (غرس) **BOX A - IMAGE GENERATION:** ``` Insert close-up: [REF: المعلم]'s weathered hands holding his BROKEN stopwatch over the gym counter, next to the humming phone running the app's digital timer. Old analog dial vs new cyan digital countdown - side by side. He turns the stopwatch over; engraved on the back: a worn year and the word "أبطال". A tiny screwdriver set beside it - he's been trying to fix it. + STYLE-LOCK + macro detail, warm lamp light. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Macro insert, shallow DOF. His thumb spins the dead crown wheel at second 4 - needle falls back limp. Cut of him glancing toward the four training in background blur at second 9 (rack focus). He sets the stopwatch down BESIDE the phone deliberately at second 12 - side by side, old and new. Sound: crown wheel ratchet, spring ping, distant timer beep, gym clinks. End held frame: two timers, one frame. Soft cut. ``` **التعليق الصوتي:** - **أنا (الراوي):** «الساعة القديمة واقفة من زمن... بس إيده لسه بتفتّل براغيها كل ليلة. بعض الإصلاحات محتاجة بس سبب.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-18

text
prompt-18
### المشهد 32 (7:45-8:00) - «انتقال باهتة» (جسر) **BOX A - IMAGE GENERATION:** ``` [REF: باهتة] Medium wide shot of the supplement corner, now tidy: labeled bins, a clean counter. YUKI stands before it with her one bottle from scene 14... but behind her on the shelf, a NEW flashy multi-bottle "Mega Stack Pack" promotional display glitters (temptation entering the frame). Her blank face «باهتة» text flickers once - doubt. Her reflection in the shelf glass shows her old self carrying an armful of bottles (ghost of old habit). + STYLE-LOCK + lavender vs marketing-gold contrast. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Push-in on the promo display glitter at seconds 2-6 (it's attractively lit - the film's temptation shot). Rack focus to her reflection carrying ghost-bottles at second 9. Her hand hesitates between one bottle and the display at second 13. Sound: promotional glitter shimmer (subtle), glass clink from her memory, heartbeat single. End held frame: hand hovering between two worlds. Cut hard into Event 9. ``` **التعليق الصوتي:** - **باهتة (تفكر بصوت مسموع):** «لو المغرفة الواحدة كويسة... يبقى تلاتة أحسن... صح؟» - **أنا (الراوي):** «غلط. وغلطها هو درس الجزء ده.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-19

text
prompt-19
Words spoken and shown on screen: ## الحدث ٩ - «الجرعة» (8:00 - 9:00) > كوميديا الفيلم الكبرى: «3 مغارف = 3 أضعاف الخير». ثم التصحيح الهادئ الذي يجعل باهتة تُرى لأول مرة. Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-20

text
prompt-20
### المشهد 33 (8:00-8:15) - «ثلاث مغارف» **BOX A - IMAGE GENERATION:** ``` [REF: باهتة] Comic close-medium shot at the counter. YUKI holds THREE different bottles stacked in her thin arms like a juggler, mid-pour of a third scoop into a shaker already overflowing. Scoop powder spills in a small comic cloud. Around her head: wavy dizziness swirl lines beginning. Her blank face «باهتة» text multiplies into overlapping ghost-copies of itself ("double vision" of the text). The phone on the counter flashes RED WARNING interface. Sickly green-yellow aura around her stomach. + STYLE-LOCK + comedy timing, warning palette. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Comic escalation: bottles wobble seconds 2-5 (juggle-rhythm sound), third scoop over-pours at second 7 in a powder puff (sneeze-sized explosion). Frame TILTS 5° at second 10 (dutch angle comedy), dizziness lines orbit. The phone's red warning pulses ×3 at second 12. Sound: plastic bottle clatter-juggle, powder puff POF, her dizzy hum "ووووو", warning buzz ×3. End held frame: tilted frame, overflowing shaker. Cut. ``` **التعليق الصوتي:** - **باهتة (بمنطق دائري سعيد):** «لو المغرفة كويسة... تلاتة يبقى تلاتة أضعاف كويسة... صح؟» - **التطبيق (تحذير حاد):** «الجرعة: 3.5 مغرفة. الآمن: 1. السُّمّية: مرتفعة.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-21

text
prompt-21
### المشهد 34 (8:15-8:30) - «الدوران» **BOX A - IMAGE GENERATION:** ``` [REF: باهتة] Surreal POV shot: the gym seen from YUKI's spinning perspective - equipment and lights smearing into a spiral, counter edge tilting. In the center of the spiral, the phone's red warning anchors sharp and unmoving: "ADJUSTING - RETURN TO YOUR DOSE". Her hands (in frame, foreground) grip the counter edge, knuckles white. Comic-pathetic: one bottle rolls off in slow motion. + STYLE-LOCK + spiral motion blur, red anchor. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. The whole frame slowly rotates 360° over 10s (nausea comedy, not horror). The red warning stays screen-center locked (stabilized). Bottle rolls off at second 8 in slow-mo, lands with an anticlimactic soft thud at second 11. Rotation decelerates and settles level at second 14. Sound: whooshy smear, bottle roll, soft thud, her small defeated "أوبس". End held frame: level frame, she slides down to sit. Cut. ``` **التعليق الصوتي:** - **أنا (الراوي):** «الكثير مش أفضل... الكثير خطر. الآلة الحاسبة كانت عارفة... هي ما كانتش تسمع.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-22

text
prompt-22
### المشهد 35 (8:30-8:45) - «الجرعة الصحيحة» **BOX A - IMAGE GENERATION:** ``` [REF: باهتة] Gentle medium shot, next morning. YUKI sits on the bench, hair a little tidier, holding ONE bottle. Her phone rests on her knee showing "INDIVIDUALIZED DOSAGE": her weight, age, training phase - computing a single precise line. Beside her on the bench: a cup with ONE perfect level scoop of powder, lit like a jewel. Her blank face «باهتة» text - for the first time - sharp, un-smudged, legible. Soft morning light, her signature lavender now clean. + STYLE-LOCK + healing palette. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Static intimate framing. The app computes at second 4 (three soft ticks), one cyan line draws across the dosage bar at second 7. Her hand takes the single scoop at second 10 - steady, no tremble. The face text sharpens subtly (VFX focus pull on the letters only) at second 13. Sound: compute ticks ×3, powder soft settle, her calm breath. End held frame: one scoop held at eye level. Hold, breathe, cut. ``` **التعليق الصوتي:** - **باهتة (بسلام أول):** «مغرفة واحدة... عشان أنا صغيرة. عشان أنا... أنا.» - **التطبيق (بلطف):** «جرعتك محسوبة على قياسك. ليس على قياس أحد.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-23

text
prompt-23
### المشهد 36 (8:45-9:00) - «مَن يراها» (ذروة عاطفية صغيرة) **BOX A - IMAGE GENERATION:** ``` Wide shot from behind the bench. YUKI small in frame, sitting straight (not slouched) with her one scoop, phone glowing on her knee. Around her in the mid-ground, the whole team trains in soft focus - everyone carrying their ONE thing: منحني his moderate bar, ضخم his treadmill pace, شرارة her box, المعلم his clipboard now holding printed progress sheets (no longer empty). Single warm shaft of light on باهتة. + STYLE-LOCK + golden ensemble frame. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Very slow pull-back and rise (crane) from behind her shoulder, revealing the whole healthy ecosystem of the gym, 12s. Each mid-ground figure completes one clean rep as the camera passes their depth plane. Sound: layered calm gym rhythm, her one soft "أنا" (to herself), room tone swelling gently. End held frame: the full gym in one warm frame - a family portrait without faces. Cut to Event 10 montage. ``` **التعليق الصوتي:** - **أنا (الراوي):** «الآلة ما كانش بتقيس البودرة بس... كانت بتقيسها هي. أول مرة حاجة تشوف صغرها كبيانات... مش كنقص.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-24

text
prompt-24
Words spoken and shown on screen: ## الحدث ١٠ - «الخط المستقيم» (9:00 - 10:00) > التصعيد الأخير للجزء: الخط يصعد أخيرًا + ملصق المسابقة = قنبلة موقوتة للجزء الثالث. Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-25

text
prompt-25
### المشهد 37 (9:00-9:15) - «الصعود الأول» **BOX A - IMAGE GENERATION:** ``` Close shot of the wall FOLLOW-UP sheet. The flat red line - and at week four's dot, the line TICKS UP one increment, bending upward for the first time. Red converts to gold at the bend point (VFX color bleed). Reflected on the sheet's glossy surface: four face-texts looking up (منحني، باهتة، ضخم، شرارة). A single chalk-dust particle drifts across like a celebration snowflake. + STYLE-LOCK + gold breakthrough palette. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Macro on the graph. At second 5, the new week's dot prints with a tiny stamp sound; the line bends UP at second 8 in slow motion, gold bleeding along it second by second. The four reflections lean in at second 12 (reflections only, faces never shown). Sound: dot stamp, paper hum, four sharp inhales in unison, شرارة's tiny "ها!". End held frame: the upward bend glowing gold. Cut wide. ``` **التعليق الصوتي:** - **التطبيق:** «الأسبوع 4: الوزن +0.6. الاتجاه: صاعد لأول مرة.» - **ضخم (صوت يرتجف فرحًا):** «طلع! الخط طلع فوق!» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-26

text
prompt-26
### المشهد 38 (9:15-9:30) - «احتفال الطباشير» **BOX A - IMAGE GENERATION:** ``` Wide joyful shot mid-gym. شرارة has smashed her fist into a chalk bowl - a cloud of chalk dust erupts and hangs glittering in the air like festival confetti (natural-only celebration). The four + المعلم stand in the chalk cloud, silhouettes rimmed white, all face-texts glowing their colors through the dust. ضخم attempts a jump (small hop, floor shakes - comic), منحني's back actually straight in the celebration. + STYLE-LOCK + chalk-white festive particles on warm light. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Chalk burst at second 1 (slow-mo particle bloom 3s). ضخم's hop lands at second 6 - camera shakes WITH the floor (comic impact), chalk re-bounces off the floor. Group laughter rendered as body-shakes (no faces). Sound: chalk POOF, floor thud + rattle of distant dumbbells, collective laughter (warm, natural), شرارة's cackle leading. End held frame: five white-rimmed silhouettes in gold light. Cut to office. ``` **التعليق الصوتي:** - **شرارة (تضحك وسط الغيمة):** «ده أحلى كونفيتي في العالم! وطعمه صابون!» - **أنا (الراوي):** «الاحتفال الحقيقي مش ضوضاء... الاحتفال الحقيقي اتجاه.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-27

text
prompt-27
### المشهد 39 (9:30-9:45) - «المكتب يعود» **BOX A - IMAGE GENERATION:** ``` [REF: المعلم] Medium shot of the coach's office - TRANSFORMED: papers filed into labeled folders, printed progress sheets pinned neatly, client chairs aligned, the laptop open on a dashboard: "45 ACTIVE CLIENTS - 100% TRACKED". REI stands placing one fresh folder into a drawer. On the desk corner: the broken stopwatch... with one new screw tightened (closer to alive). Sunset stripes, but warm and clean now - same office as scene 4, healed. + STYLE-LOCK + amber order. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Slow pan left-to-right across the healed office, mirroring scene 4's chaos positions (visual rhyme: each messy zone now ordered). He slides the folder in at second 9 - drawer closes soft. At second 12 his hand pauses on the stopwatch: gives the crown one hopeful half-turn - needle moves ONE tick, then stops. Sound: folder slide, drawer thunk, ratchet click ×1, a surprised small "هاه؟". End held frame: hand on stopwatch, needle one tick past zero. Cut hard. ``` **التعليق الصوتي:** - **المعلم (للساعة):** «...حتى انتي بترجعي؟ خدي وقتك.» - **أنا (الراوي):** «الورقة اللي خانته زمان... بقت أرشيف بيشهدله.» Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-28

text
prompt-28
### المشهد 40 (9:45-10:00) - «الملصق» (CLIFFHANGER) **BOX A - IMAGE GENERATION:** ``` Night exterior of IRON TEMPLE, rain gone. On the glass door, a NEW poster glows under a street lamp: "مسابقة المعبد الحديدي - بعد 4 أسابيع" with a hexagonal logo and four silhouette icons (lift, dose, pace, reach). Reflected in the glass from inside: the five training late, cyan phone-lights visible. A countdown badge on the poster: "28". The neon sign above - now FULLY LIT, no flicker (the gym itself is healing). + STYLE-LOCK + night gold + cyan. ``` **BOX B - ANIMATION / PRODUCTION / EDIT:** ``` 15s scene. Slow push toward the poster 10s; at second 8 the countdown badge flips 28→27 with a mechanical snap (time is now running ON screen). Inside-reflections of the five flicker training in the glass. At second 13 a hand (منحني's, from inside) sticks a second small note beside the poster: "إحنا جايين". Sound: night crickets, distant bar clank from inside, badge snap, paper tape press. END OF PART 2: cut to black on the badge flip sound. Title card beat: «أربعة أسابيع». ``` **التعليق الصوتي:** - **أنا (الراوي):** «أربعة أسابيع... أربعة أقنعة محتاجة أسماء جديدة. المسابقة ما بتسألش مين كان... بس بتسأل مين هيبقى.» - **التطبيق (توهج هادئ):** «خطة التحضير: 28 يومًا. جاهز؟» --- Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-29

text
prompt-29
Words spoken and shown on screen: # 📱 قسم الشرائح القصيرة - SHORTS (لهذا الجزء) Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-30

text
prompt-30
Words spoken and shown on screen: ## قواعد التجميع - نفس قواعد الجزء الأول (وحدات 15 ث، إطارات مثبتة، استمرارية صوت طبيعي، بلا موسيقى، إعادة توليد 9:16 للشورتات). - مشاهد هذا الجزء أقوى تفاعليًا (كوميديا + تحذيرات) - أولوية نشر أعلى. Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-31

text
prompt-31
Words spoken and shown on screen: ## أفضل التركيبات | الشورت | المشاهد | المدة | الاستخدام | الخطاف المقترح | |---|---|---|---|---| | «الخط الغلط» | 21+22 | 30 ث | محتوى "الحقيقة المخفية" - الأعلى حفظًا ومشاركة | «الميزان بيكذب عليك» | | «CRACK» | 25+26+27 | 45 ث | تشويق-دراما: أزمة الظهر وإنقاذ التطبيق | «87%... ويتحرك» | | «3 مغارف» | 33+34 | 30 ث | أنجح كوميديا - باهتة والمنطق الدائري | «لو واحدة كويسة...» | | «مغرفة واحدة» | 35 | 15 ث | شورت هادئ ملهم - حلقة إعادة | «عشان أنا أنا» | | «كونفيتي الطباشير» | 37+38 | 30 ث | احتفالي - يُنشر يوم إنجاز أسبوعي | «الخط طلع!» | | «الملصق» | 40 | 15 ث | إعلان الجزء الثالث | «28 يوم» | Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.

prompt-32

text
prompt-32
Words spoken and shown on screen: ## تعليمات النشر 1. «الخط الغلط» هو الشورت الذهبي لهذا الجزء (جملة قابلة للإرسال: «ابعتها للي واقف عند نفس الرقم»). 2. انشر «3 مغارف» بين يومين من «CRACK» - الكوميديا تنظف التوتر وتُبقي المتابع. 3. «الملصق» يُنشر مع عدّاد تنازلي حقيقي في الكابشن (4 أيام حقيقية قبل عرض الجزء الثالث). --- **نهاية الجزء الثاني (5:00-10:00).** الجزء الثالث: `03-MASKS-OF-IRON_film-3_minutes-10-15.md` Batch generation at 12 oclock. Best = powerful reference + imitate. Powerful reference = Try different models and different methods till reach to it. After reach, continue based on it. Negative rules, apply on every frame: No face features at all. No eyes, no mask with eyes, no circles used as eyes, no eye-sockets, no realistic face features, no face silhouettes, and no facial shadows: no nose shadow, no eye-socket shadow, no lip shadow. Any head stays a clean solid shape, a blank solid-void faceless head. No hands and no people. No globe, no planet Earth, and no world-map sphere anywhere in the image. No music, only natural sounds + voice-over. Maximum quality, maximum color saturation, high-definition resolution, sharp readable text. ON-SCREEN TEXT AND VOICE-OVER LANGUAGE. On-screen text language: Arabic. Voice-over language: Arabic. The prompt instructions stay in English. Only the words spoken in the voice-over and the words shown on the image or video use this language.