This page is one Video Prompt from the PromptPix app — Second Ultra-realistic Vertical. Image Prompt (still) and Video Prompt (motion) stay on this card. No other video is mixed in.
This card asks the model to keep an uploaded face or reference. Leave those lock lines in on the first generate.
Copy Image Prompt for a still, or Copy on the Video Prompt for motion. Then open Flow, Gemini, or ChatGPT and paste. The site does not auto-paste.
Second Ultra-realistic Vertical
Video Prompt
Create a 10-second ultra-realistic cinematic vertical 9:16 video using the uploaded character reference image as the Flow Ingredient for the man. HIGHEST PRIORITY — IDENTITY LOCK: Preserve the exact same face, facial structure, skin tone, body build, proportions, height and overall identity from the uploaded reference image throughout the entire video. Do not redesign, beautify, age, de-age, modify or reinterpret the character. Add same face and hair the reference image. Keep his identity perfectly consistent in every frame with zero face drift. CHARACTER & WARDROBE: The man wears a dark navy-blue long-sleeved kurta with matching dark trousers, a grey backward baseball cap, black wayfarer sunglasses and brown suede casual shoes. Keep the outfit, colors and overall appearance consistent with the reference. He remains calm, confident and completely non-speaking throughout the video. No dialogue and no lip-sync. CHAIR — IMPORTANT: The man is seated throughout the entire video on the SAME portable folding camping chair shown in the reference image. The chair must remain clearly visible and physically consistent throughout the scene. It is a simple black/olive fabric folding camping chair with a visible metal folding frame and legs. Do not remove, replace, redesign, hide, duplicate, transform or make the chair disappear. The man's seated position must remain natural and stable on the chair. ENVIRONMENT: An arid countryside field covered with dry golden grass, with distant rolling hills in the background. Warm golden-hour sunset lighting with a low sun angle, long natural shadows, glowing dust particles and a rich cinematic outdoor atmosphere. VISUAL STYLE: Ultra-realistic live-action cinematography, cinematic high-action look, realistic natural skin and fabric texture, subtle cinematic film grain, HDR, sharp focus, warm cinematic color grading, vivid golden tones, deep contrast, realistic black vehicle tones and premium Hollywood-style visual quality. The scene must look like real professional camera footage, not CGI. CAMERA: Stable cinematic medium shot in vertical 9:16 composition. Keep the man, his complete seated position and the folding chair clearly visible in the foreground. The truck action happens dramatically in the background behind him. Maintain natural shallow depth of field while keeping both the man and major vehicle action visually readable. No unnecessary camera shake, no random camera movement and no rapid cuts. TIMELINE — EXACTLY 10 SECONDS: 00:00–00:03: The man sits calmly and confidently, cross-legged on the same folding camping chair in the dry golden grass, facing the camera. His posture remains relaxed and natural. The chair is clearly visible beneath him, including its fabric seat and folding frame. The golden-hour environment, dry grass and distant hills are visible behind him. 00:03–00:04: While remaining seated in exactly the same position on the same chair, the man calmly raises his right hand and snaps his fingers toward the camera. The finger-snap gesture must be clear, natural and perfectly timed. Do not change his facial identity or seated posture. 00:04–00:10: Immediately after the finger snap, a realistic black Toyota pickup truck dramatically launches over the hill directly behind the man. The truck becomes airborne in a powerful jump above and behind him, creating a huge but physically realistic cloud of dust and airborne grass particles. The man remains completely calm and untouched in the foreground, still sitting cross-legged on the SAME folding camping chair. The chair stays firmly on the ground and remains visible throughout the vehicle jump. The truck and dust remain behind him and never collide with, hit or move the man or his chair. Keep the man's face, body, clothing, sitting position and chair stable while the high-action vehicle movement happens dramatically in the background. SOUND DESIGN: A sharp, realistic finger-snap sound occurs exactly at 00:03. Immediately after the snap, introduce a powerful engine roar, deep vehicle launch rumble, realistic tire and suspension sounds, rushing wind and heavy dust movement. Add a rhythmic modern cinematic hip-hop beat that drops precisely on the finger snap at 00:03. MOTION & PHYSICS: Use realistic vehicle weight, suspension movement, airborne momentum, tire movement, dust behavior and environmental interaction. The truck must behave like a real heavy vehicle performing a dramatic jump. Dust and grass particles should react naturally to the vehicle's movement. The man and chair remain physically stable and unaffected. Everything should look like real live-action footage captured with a professional cinema camera. CONTINUITY: Maintain perfect continuity from the first frame to the last frame. The same man, same face, same hair, same sunglasses, same outfit, same body proportions, same chair, same sitting position, same environment and same lighting must remain consistent throughout the entire 10-second video. STRICT NEGATIVE: No face drift, no identity change, no facial distortion, no face morphing, no beautification, no age change, no body deformation, no outfit change, no hair change, no sunglasses change, no missing chair, no disappearing chair, no chair transformation, no chair movement, no floating chair, no standing up, no change of sitting position, no extra people, no duplicated character, no duplicated vehicle, no distorted hands, no unnatural fingers, no extra limbs, no floating objects, no unrealistic vehicle physics, no CGI appearance, no cartoon appearance, no artificial-looking dust, no excessive motion blur, no shaky camera, no random camera movement, no unwanted cuts, no scene change, no text, no subtitles, no watermark, no logo overlay. Do not end before 10 seconds. Generate the complete continuous 10-second sequence.
FAQ
What is this video prompt?
Yes — one card: Second Ultra-realistic Vertical. Same as tapping that video in the PromptPix app.
Should I upload a reference photo?
Yes if the text says to match a face or scene. Add the photo in Flow or Gemini, then paste this prompt without deleting the match lines.
Image Prompt vs Video Prompt on this card?
Image Prompt is for a still in Gemini or ChatGPT. Video Prompt is for motion in Flow or Gemini video. Copy only the block you need.
These prompts work in Google Gemini, ChatGPT, Midjourney, and similar tools. For Image to Prompt from your own photo, use the PromptPix app.