Indicador

REFERENCE HERO VIDEO — FEMALE CHARACTER LOCK (Sora2) — SIDE ANGLE — MATCH FACE DETAILS Create a realistic cinematic podcast-style video in vertical format (9:16). This is a CHARACTER REFERENCE (hero) clip. The goal is to clearly establish ONE consistent female main speaker for future remixes. ON-CAMERA MAIN SPEAKER (must be the only person visible): A young Muslim woman (early–mid 20s) with a soft oval / slightly round face, light olive / fair warm skin tone, smooth cheeks, natural skin texture, large almond-shaped dark brown eyes with long lashes, thick dark full eyebrows (distinct and well-defined, softly arched), a small-to-medium straight nose with a rounded tip, and soft pink lips with a gentle warm smile. Natural makeup only (subtle eyeliner, light blush, natural glow). Hijab: black hijab, smooth matte fabric, fully covering hair and neck, neatly wrapped with consistent folds. Outfit: modest black abaya, loose fit, long sleeves, no logos, no jewelry. She is the ONLY person shown in the video. OFF-CAMERA HOST (audio only, strictly limited): A male host exists ONLY as a quiet off-camera voice. He must NOT speak first. He must NOT say any long sentences. He only gives TWO very short affirmations exactly once each: "صح..." and "فعلاً..." He must NOT take the main speech. SCENE: Minimalist realistic podcast studio with acoustic panels and warm practical lights in soft bokeh. A professional condenser microphone with arm and shock mount is clearly visible near her. Neutral colors, no distractions, no readable text, no logos. CAMERA (match side-angle reference): 3/4 side-profile close-up from her front-right side, framing head and shoulders. She faces toward screen-left (toward the interviewer), not straight to camera. Lens: 85mm portrait look, very shallow depth of field. Microphone appears in the lower-left foreground, slightly out of focus. Stable static framing, no camera shake. LIGHTING: Soft key light on her face with gentle highlights, natural skin texture, cinematic realism, natural tones, no filters. PERFORMANCE: The female speaks the full main dialogue with clear mouth movement matching the Arabic words. Calm authority, expressive but controlled facial reactions, natural eyebrow movement (keep eyebrows thick and defined), warm approachable presence. Eye line mostly toward the interviewer (off-camera), with one brief glance slightly forward as indicated. Natural blinking, breathing, and pauses. Minimal natural hand gestures near the microphone. DIALOGUE (female is the main speaker; male only short adlibs): FEMALE (starts first): "إحنا مش بنسيب الشخص…" MALE OFF-CAMERA (quiet, very short): "صح…" FEMALE: "إحنا بنسيب النسخة القديمة من نفسنا… اللي كانت محتاجة العلاقة دي." FEMALE: "ولما توصل للفهم ده…" (Female briefly glances forward, then back toward the interviewer) FEMALE: "بتعرف إن الهدوء قوة… مش ضعف." MALE OFF-CAMERA (quiet, very short): "فعلاً…" AUDIO DESIGN: Clean studio mic sound, natural room tone, no background music. Female voice is dominant (90–95% of total audio). Male voice is low volume and very brief. STRICT RULES: Only the woman is visible. No male on camera. Do not change identity, facial proportions, eyebrow thickness, eye shape, skin tone, eye color, hijab style/wrap, or outfit. No subtitles, no watermarks, no logos, no readable text. Avoid: identity swap, face morphing, different person, hair showing, heavy beauty filters, cartoon/anime, deformed hands, extra fingers, jittery face.

video

REFERENCE HERO VIDEO — FEMALE CHARACTER LOCK (Sora2) — SIDE ANGLE — MATCH FACE DETAILS Create a realistic cinematic p...

Sora 2video:sora2-text-to-video-standardTexto a video
29 ene 2026, 14:30

Ajustes

proveedor
Sora 2
Modelo
video:sora2-text-to-video-standard
Creada
29 ene 2026, 14:30
Créditos
20
Modo
Texto a video
Relación de aspecto
9:16

Crear algo similar

El generador a continuación preselecciona el modelo utilizado para este registro para que puedas remezclar la idea más rápido.

Las nuevas tareas aparecen aquí después de enviarlas.