glm53-plans.html · part 1

prompt-1
face, eyes, mouth, facial features, readable text, letters, numbers, captions, subtitles, watermark, logo, brand name, extra fingers, deformed hands, morphing, warping, glitch, low quality, blurry, cartoon, anime 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: English. Voice-over language: English. 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
Cinematic vertical 9:16, photorealistic, shallow depth of field, professional color grading, subtle film grain, high dynamic range, professional cinematography. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Extreme close-up of a round white wall clock on a pale green hospital wall, hands pointing a few minutes before 8:00. Harsh fluorescent light flickers softly overhead. A doctor's hand in a dark green scrub sleeve enters frame from below and taps the clock face twice, a nervous gesture. Shallow depth of field, subtle handheld sway, tense clinical atmosphere, photorealistic, film grain, teal-green color grade. No faces, no text, no logos. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Top-down overhead shot looking straight down at a cluttered hospital desk covered in patient charts and scattered papers. A hand in dark green scrubs slams a thick paper chart onto the desk dead center; the surrounding papers jump slightly from the impact. Harsh fluorescent lighting, teal-green clinical grade, photorealistic, shallow depth of field, film grain. No faces, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Top-down overhead shot of a hospital desk as dozens of yellow sticky notes multiply rapidly across the surface in fast timelapse motion, spreading like growing mold over patient charts. A hand writes on notes in accelerated motion. Fluorescent clinical lighting, teal-green grade, photorealistic, film grain. No faces, handwriting illegible, no readable text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Macro overhead shot in extreme slow motion: a white paper coffee cup tips over on a cluttered hospital desk, dark coffee spilling and spreading in glossy slow-motion waves across scattered charts and yellow sticky notes. Dramatic side lighting, teal-green clinical grade, photorealistic, 35mm film grain, shallow depth of field. No faces, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Medium shot in slow motion: a tall tilting tower of paper charts and files tips over and collapses onto a hospital desk, pages fanning out beautifully as they fall. A second pair of hands in white coat sleeves reaches out too late to catch the tower. Fluorescent hospital lighting, teal-green grade, photorealistic, film grain. No faces, no readable text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Extreme macro close-up of a ballpoint pen tip hovering and trembling slightly over a chaotic desk covered in crossed-out calculations and yellow sticky notes. The pen shakes with fatigue, refusing to write. Harsh desk lamp light from one side, teal-green clinical grade, very shallow depth of field, photorealistic, film grain. No faces, no readable text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. A smartphone lies flat on a dark hospital desk in near-total darkness. The screen suddenly lights up, casting a soft cool white glow that illuminates two hands in dark green scrubs holding it gently. Moody, calm, high-contrast lighting, subtle rim light on the fingers, photorealistic, film grain, shallow depth of field. No faces, screen glows blank with no text, no logos. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Medium close-up of two doctors' hands meeting in a firm handshake at the center of frame, cropped at the elbows - one hand in dark green scrubs, one in a white coat sleeve. Behind them, softly blurred, a round white wall clock. Warm morning light replacing the fluorescent tone, calm resolution mood, photorealistic, film grain, shallow depth of field. No faces, no text. 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: English. Voice-over language: English. 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
Stylized cinematic animation, vertical 9:16. A weather radar map shaped like a human body silhouette seen from the front, glowing green radar sweep rotating slowly across the form, isobar lines and pressure gradients flowing over the body like a meteorological forecast, dark navy background with subtle scan lines. Mysterious documentary graphics aesthetic, slow ominous motion. No faces, no text, no letters. 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: English. Voice-over language: English. 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
Stylized cinematic animation, vertical 9:16. Camera zooms toward the head region of a human body weather map where a massive swirling cyclone of glowing red and orange clouds rotates over the brain area, lightning flickering inside the storm, pressure gauge needles falling, dark stormy navy background. Dramatic weather documentary aesthetic, accelerating ominous motion. No faces, no text. 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: English. Voice-over language: English. 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
Stylized cinematic animation, vertical 9:16. Wide view of a human body weather map as a bright white and gold calm front sweeps from left to right across the silhouette like a luminous curtain, storm clouds dissolving behind it, warm sunlight flooding over the heart region of the body-map, gentle rays of light. Hopeful weather documentary aesthetic, smooth healing motion. No faces, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Abstract dark screen with a glowing green ECG heart-monitor line drawing itself from left to right in smooth continuous motion, each heartbeat pulse bright and clean, subtle screen glow and faint scanline texture, medical monitor aesthetic, minimalist, high contrast. No text, no letters, no faces. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. A glowing green ECG line on a black medical monitor screen becomes perfectly flat and continues drawing one long continuous flat line to the edge of the screen, the glow dimming slightly, subtle screen flicker. Empty, uncomfortable stillness. No text, no faces. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Overhead top-down shot of a desk holding a blank exam answer sheet as small red plastic evidence flags drop from above and land on the page one by one in slow motion, each landing with a tiny bounce. Cool desaturated blue-grey lighting, clinical mood, photorealistic, film grain, shallow depth of field. No faces, no readable text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Overhead shot of two hands pressing two rounded medical paddle electrodes firmly onto a thick stack of practice test books on a desk, energy building with a growing glow on the paddle handles, then a bright white flash and the books jolt upward slightly. Cool blue-grey clinical lighting, dramatic, photorealistic, film grain. No faces, no readable text, no logos. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Slow overhead shot: two hands gently and wearily set down two medical paddle electrodes on a desk beside an untouched stack of test books, then the hands rest flat and completely still. Cool desaturated blue-grey light, somber exhausted mood, photorealistic, film grain. No faces, no readable text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Dark screen with a glowing green ECG line recovering from flatline into strong steady heartbeats, each pulse growing brighter, the line gradually rising upward across the frame like a climbing graph. Clean medical monitor aesthetic, high contrast, subtle glow bloom. No text, no faces. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Extreme macro slow push-in on a paper medical intake form filled with messy handwriting on a clinical desk, focus slowly racking from blurred toward sharper on the middle of the page. Fluorescent dental clinic lighting, cold steel-blue grade, tense clinical thriller mood, photorealistic, film grain, very shallow depth of field. No faces, handwriting illegible, no readable text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Top-down overhead shot of a stainless steel dental tray as a gloved hand places polished instruments onto it one by one, each tool clicking precisely into alignment. Clinical cold lighting with steel reflections, ASMR precision mood, photorealistic, film grain. Gloved hands only, no faces, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. POV shot from a dental patient's perspective lying back in a chair: a bright examination light swings toward the camera and blooms into a blinding white flare filling the frame. Slight disorienting dutch angle, sterile cold grade, photorealistic, film grain. No faces, no people, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Extreme macro crash zoom onto one blurred handwritten word in the middle of a messy paper medical form, as a glowing red circle annotation draws itself around the word stroke by stroke, red light bleeding softly onto the paper. Ominous alarm mood, cold clinical lighting, photorealistic, film grain. No faces, word unreadable, no other text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Close-up of a gloved hand holding a tablet in a dental clinic, the screen flashing a soft red warning glow that pulses gently and rhythmically, the cold steel-blue lighting contrasted by warm red screen glow on the glove. Tense but controlled mood, photorealistic, film grain, shallow depth of field. Gloved hand only, no faces, abstract warning graphics on screen, no readable text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Low angle wide shot of a person walking slowly along an empty morning street, strongly backlit by low golden sun so they appear as a pure dark silhouette with no visible features. Their posture is deeply hunched - rounded shoulders, dropped head, body curved like a question mark. A long dramatic shadow stretches toward the camera. Melancholic mood, photorealistic, 35mm film grain, shallow depth of field. Face never visible, pure silhouette, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Static shot from a low angle of a tall old doorway on a city street, a hunched dark silhouette of a person standing small and curved beneath it, completely dwarfed by the frame, backlit by grey morning light. Moody, melancholic, photorealistic, film grain. Face not visible, silhouette only, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Dark gym interior, side view of a person performing a seated cable row filmed as a backlit silhouette against a bright window, rounded shoulders pulling the cable with effort, dust particles floating in the light beam. Dramatic rim lighting, rising motivational mood, photorealistic, film grain. Framed from the chest down, no face visible, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. A dark human shadow cast on a textured gym wall from strong raking side light; the shadow's spine slowly straightens from a hunched curve into an upright tall posture, from bottom to top, in one continuous graceful motion. Minimalist, cinematic, high contrast, photorealistic, film grain. No faces, no people in frame, only the shadow, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Low angle wide shot of a person walking tall through an empty morning street, strongly backlit by golden sun as a pure dark silhouette, shoulders square, head high, body perfectly straight like an exclamation mark, long confident shadow, subtle lens flare. Triumphant mood, photorealistic, film grain. Face never visible, silhouette only, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. First-person POV handheld shot at the bottom of a concrete apartment stairwell, looking up a long steep flight of stairs that seems to stretch upward forever, slight wide-angle distortion exaggerating the height, dim yellowish light from above, claustrophobic oppressive atmosphere. Subtle camera sway with a heavy breathing rhythm. Photorealistic, film grain. No people visible, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. POV shot climbing concrete stairs, a hand gripping a worn metal handrail in the foreground, each step heavy and effortful, noticeable camera shake and sway in rhythm with labored breathing, dim stairwell lighting, sweat glistening on the hand. Strenuous claustrophobic mood, photorealistic, film grain. No faces, no text. 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: English. Voice-over language: English. 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
Cinematic vertical 9:16 video. Smooth tracking shot moving along a gym floor at ankle-to-waist height: running shoes on a treadmill, then dumbbells lifting, then a kettlebell swinging, steady forward camera glide with rhythmic energy, warm motivational lighting with deep shadows, dust glowing in light beams. Photorealistic, film grain. Framed below the shoulders only, no faces, no text. 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: English. Voice-over language: English. 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-33
Cinematic vertical 9:16 video. Smooth stabilized gimbal shot gliding effortlessly up a concrete apartment stairwell, camera rising fluidly past the steps, bright daylight now streaming from a window above, airy confident atmosphere, subtle lens flare. Photorealistic, film grain. No people, no text. 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: English. Voice-over language: English. 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-34
Cinematic vertical 9:16 video. Close tracking shot from behind at knee height of strong legs in running shoes bounding up concrete stairs two steps at a time, light effortless stride, bright daylight from above, confident energetic mood. Photorealistic, film grain. Framed below the shoulders, no faces, no text. 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: English. Voice-over language: English. 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-35
Cinematic vertical 9:16 video. Wide shot of a dark empty gym at night, a single overhead lamp creating one pool of light on a flat bench and barbell, everything else dissolving into blackness, a gym bag drops into the pool of light from off-frame. Film noir chiaroscuro style, dramatic, photorealistic, heavy film grain. No people, no text. 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: English. Voice-over language: English. 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-36
Cinematic vertical 9:16 video. Extreme close-up side view of a barbell on a rack as a large black weight plate slides onto the bar and settles heavily, then another plate follows, then another. Dark gym, single overhead spotlight, deep shadows, film noir lighting, photorealistic, film grain. Hands only, no faces, no text. 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: English. Voice-over language: English. 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-37
Cinematic vertical 9:16 video. Slow motion side view of a bench press: small hands press a heavily loaded barbell upward, the bar wobbles and tilts unevenly mid-lift, arms visibly shaking with strain. Dark gym lit by one overhead lamp, film noir style, dramatic tension, photorealistic, film grain. Framed chest-down, no face visible, no text. 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: English. Voice-over language: English. 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-38
Cinematic vertical 9:16 video. Static still-life shot on a dark table: a black wrist brace lying beside a slowly melting ice pack and a wall calendar, calendar pages detaching and fluttering down one by one in slow timelapse. Somber grief mood, single cold window light, photorealistic, film grain. No people, no readable text. 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: English. Voice-over language: English. 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-39
Use BOX 2 played backward - plates unload themselves, light steadies. 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: English. Voice-over language: English. 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-40
Cinematic vertical 9:16 video. Slow motion side view of a perfect bench press: confident hands press a moderately loaded barbell smoothly and vertically, controlled and strong. Dark gym with a single overhead lamp now glowing warmer and steadier, redemption mood, film noir softened with warm light, photorealistic, film grain. Framed chest-down, no face, no text. 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: English. Voice-over language: English. 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.