glm53-plans.html · part 2

prompt-1
Cinematic vertical 9:16 video. Extreme low angle wide shot of a tall old metal filing cabinet in a pitch-dark storage room, lit by a single swinging amber bulb, the cabinet looming enormous like a horror movie antagonist, dust particles floating in the light beam. Horror atmosphere, deep shadows, 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-2
Cinematic vertical 9:16 video. Macro shot inside an open file drawer: fingers flip past hanging folders, pull one out, and the folder slips and drops into the black gap behind the drawer, swallowed by darkness. Single amber bulb lighting, horror mood, photorealistic, film grain, shallow depth of field, slight slow motion. Hands only, 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-3
Cinematic vertical 9:16 video. Locked-off shot of a dark storage room as thick layers of dust gradually accumulate on the filing cabinet and floor in slow eerie timelapse, a spider web slowly forming in the corner, the amber bulb flickering weakly. Horror time-passing mood, 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-4
Cinematic vertical 9:16 video. Frantic handheld shot in a dark storage room: a flashlight beam whips across file drawers, hands yank folders out and papers fly everywhere, breathless urgent searching, chaotic camera shake. Horror panic mood, amber bulb and flashlight lighting, photorealistic, heavy film grain. Hands and flashlight only, 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-5
Cinematic vertical 9:16 video. A tablet glows brightly in the dark storage room, held by two hands, the screen casting clean white light that pushes back the darkness around it, a soft red medical alert glow pulsing gently on the display. Relief-after-horror mood, photorealistic, film grain, shallow depth of field. Hands only, no faces, abstract alert 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-6
Cinematic vertical 9:16 video. Backlit silhouette of a woman standing at a window in golden evening light, head bowed with exhaustion, framed from the shoulders down. A faint ring of golden light hovering above her head flickers, slips, and falls slowly past her shoulders, fading out. Magical realism, emotional cinematic mood, photorealistic, film grain. Silhouette only, no visible 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.

prompt-7
Cinematic vertical 9:16 video. One continuous overhead shot of a pair of tired female hands working non-stop across a kitchen table: closing a laptop, sorting papers, wiping the table, stacking a child's notebooks - fluid, tireless, continuous labor. Warm dim evening home lighting, bittersweet mood, photorealistic, film grain. Hands only, 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. Medium shot of a woman seated at a table, cropped below the chin, her hand slowly reaching out mid-air toward nothing and then pausing there, hovering, uncertain. Soft window light, melancholic quiet mood, shallow depth of field, photorealistic, film grain. 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-9
Cinematic vertical 9:16 video. Side view of a woman training with dumbbells in a home gym at dawn, filmed as an elegant backlit silhouette with golden rim light, strong controlled movements, focused posture exercises, dust floating in the light beam. Rising empowerment mood, photorealistic, film grain. Framed neck-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-10
Cinematic vertical 9:16 video. Backlit silhouette of a woman standing tall at a window in golden light, shoulders square and head high, framed from the shoulders down. A ring of golden light descends slowly from above and settles steadily above her head, glowing brighter and locking into place with a soft radiant flare. Triumphant magical realism, emotional cinematic mood, photorealistic, film grain. No visible 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.

prompt-11
Cinematic vertical 9:16 video. Slow patient pan across a dark gym late at night, empty machines resting in half-light like sleeping animals in a jungle, cold moonlight through high windows, dust hanging motionless in the air. Nature documentary establishing-shot aesthetic, mysterious calm mood, 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-12
Cinematic vertical 9:16 video. Slow push-in on a man sitting motionless on a gym bench in near-total darkness, filmed from the chest down, the only light source his phone screen glowing up onto his still body and hands, his thumb making tiny scrolling twitch movements. Deadpan nature-documentary observation mood, dark comedic stillness, photorealistic, film grain. No face visible, no readable phone content, 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
Cinematic vertical 9:16 video. Fixed shot of a gym rack area where an athlete in silhouette performs a complete set of exercises in fast timelapse motion - lifting, racking, moving with urgency - while in the soft-focus background a phone glow stays constant and unmoving on a distant bench. Nature documentary contrast mood, photorealistic, film grain. Athlete framed neck-down, 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. A fit athlete training in the bright zone of a gym, filmed as a strong silhouette exercising with metronome-like precision: one clean set, a precise pause, the next set - disciplined rhythmic motion, clean rim lighting. Nature documentary admiration mood, photorealistic, film grain. Framed neck-down, 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-15
Cinematic vertical 9:16 video. [SHOT TYPE: extreme close-up / overhead top-down / low angle wide / POV / slow push-in / locked-off] of [SUBJECT with wardrobe descriptor] , [ONE clear continuous action in present tense] , [LIGHTING: single lamp / fluorescent / backlit golden hour / phone glow in darkness] , [MOOD: tense / somber / triumphant / deadpan] , photorealistic, film grain, shallow depth of field. 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-16
Write a 12-18s 9:16 faceless episode for [APP]. Machine: [HxH vow | JJK named curse | Conan 3-clues | Dr.Stone 1 invention]. Universe: ielts.fast · promedic1.com · coach.promedic1.com · dentist.promedic1.com. Must include: hook line on screen in first 1.3s, 3 visual beats, signature sound, end card URL. No faces. Hands / UI / objects / diagrams only. Output: shot table 0:00-end, overlay text, sound, thumbnail line, caption, first comment. 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: 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.