Flow AI Realistic Café Coffee Drinking Video Prompt

# GOOGLE FLOW AI VIDEO PROMPT — NATURAL CAFÉ LIFESTYLE CINEMATIC REEL

**VIDEO FORMAT:** 10 seconds, vertical 9:16, ultra-realistic live-action video, professional cinematic lifestyle filmmaking, natural human movement, realistic coffee-drinking action, cozy café atmosphere, three distinct shots, smooth transitions, beautiful background music.

## 1. STRICT ORIGINAL IDENTITY PRESERVATION

Use the uploaded reference photograph as the definitive identity reference for the woman. She must remain the exact same recognizable person throughout the entire video.

Preserve her original facial structure, face shape, forehead, eyebrows, eyes, nose, cheeks, cheekbones, jawline, chin, lips, ears, skin tone, natural skin texture, and apparent age.

Preserve her original hairstyle, hairline, hair color, hair length, texture, volume, and parting. Preserve her natural physique and body proportions.

Do not replace, regenerate, beautify, reshape, slim, enlarge, mature, or de-age her. No face swapping, identity drift, skin whitening, artificial makeup, or beauty filters.

Keep her original clothing unchanged for this café scene. Her identity, hairstyle, age, body proportions, and clothing must remain consistent in every shot.

## 2. CRITICAL OPENING — DO NOT REPEAT THE INPUT PHOTOGRAPH

**The uploaded photograph is an identity reference, not the opening frame of the finished video.**

Do not display the original photograph unchanged at the beginning. Do not begin with a frozen copy, a still-image hold, or a simple zoom into the reference image.

Generate a newly composed, moving live-action café scene from frame one. Start with a medium-wide three-quarter view filmed from a slightly different camera position, showing the woman seated at a café table beside a large window.

Reconstruct the same woman naturally in the café environment while preserving her exact identity and original appearance. The opening framing must be visibly different from the reference photograph.

From the first frame, include subtle natural motion: breathing, a gentle eye movement, a normal blink, and a small, relaxed movement of her hand near the coffee cup. The camera should already be moving gently, and the background should have realistic depth.

**Do not show the input photo as a static first frame, even briefly.** The video must begin as newly generated moving footage, not as an animated copy of the photograph.

## 3. LOCATION AND VISUAL STYLE

The scene takes place inside a cozy, stylish café with a large window, natural daylight, a wooden tabletop, a ceramic coffee cup, and a softly blurred background.

Use warm natural light mixed with subtle indoor lighting. The café should feel authentic, comfortable, and lived-in—not an artificial luxury showroom.

Keep the same table, window, cup, and general café environment consistent across all three shots. Use realistic shadows, reflections, natural skin tones, and restrained cinematic color grading.

The woman is the main subject. The coffee-drinking action must be clear and believable.

## 4. SCENE 1 — NATURAL CAFÉ OPENING (0:00–0:03)

Start with a newly generated medium-wide shot of the woman seated at the café table. Use a three-quarter camera angle that is visibly different from the original photograph.

The coffee cup is placed on the table within comfortable reach of her hand. She looks peacefully toward the window for a brief moment, then naturally shifts her gaze toward the cup.

The camera gently slides sideways while making a subtle push-in. The woman's breathing, eye movement, and small hand movements should be visible and natural.

She begins reaching toward the cup near the end of this shot. Her hand approaches the handle in a physically realistic way, preparing for the coffee-drinking action in the next shot.

**Important:** Do not hold the original photograph as the opening. Do not freeze her in the original pose. The first scene must immediately look like a real moving video.

## 5. SCENE 2 — PICK UP THE CUP AND ACTUALLY DRINK THE COFFEE (0:03–0:06.5)

This is the most important action in the entire video.

Continue naturally from Scene 1. The woman reaches for the ceramic coffee cup, grips its handle securely with one hand, and lifts it smoothly from the tabletop.

She brings the cup toward her mouth with a natural, controlled movement. She gently tilts the cup just enough to take **one clearly visible, realistic sip of coffee**.

The rim of the cup makes natural contact with her lips. She holds the cup at her mouth briefly, takes the sip, and then lowers it away from her lips. Her hand, wrist, fingers, head, and cup must move together with believable human coordination.

**She must actually drink the coffee. Do not skip the sip. Do not merely lift the cup, pose with it, or lower it without drinking.**

After the sip, she pauses briefly with a relaxed expression and moves the cup back toward the table. The drinking action must be completed before the shot ends.

Use a medium close-up that clearly shows her hand holding the cup and the cup reaching her lips. A brief natural cut to a closer angle is acceptable only if the drinking action remains visually continuous and easy to understand.

Keep her face recognizable. The cup must not merge into her face, pass through her lips, or cover her face unnaturally. Her fingers must hold the handle correctly, with no extra fingers or distorted hands.

Her expression remains subtle and natural. No exaggerated sipping, fake chewing, exaggerated swallowing, or artificial smile.

## 6. SCENE 3 — PLACE THE CUP BACK ON THE TABLE (0:06.5–0:10)

Continue directly from the completed sip.

The woman gently lowers the cup from her mouth and returns it to the tabletop. Show the cup moving downward until its base makes clear contact with the table.

**The sequence must happen in this exact order: lift the cup → bring it to the lips → take a sip → move the cup away from the lips → place it securely on the table.**

Do not make her put the cup down before drinking. Do not make the cup disappear, teleport, or land without contact with the tabletop.

After placing the cup down, she releases the handle naturally, rests her hand comfortably near the cup, and turns her gaze back toward the window. She settles into a peaceful, thoughtful expression.

The camera gently drifts sideways and finishes with a beautifully composed three-quarter portrait. Warm window light illuminates her face, and the softly blurred café background creates natural cinematic depth.

End with a calm, stable composition. Keep her lips naturally relaxed. No speaking, singing, or lip-syncing.

## 7. CAMERA WORK AND CINEMATIC EFFECTS

Use professional live-action cinematography with realistic camera movement.

* Scene 1: medium-wide three-quarter shot, gentle sideways slide, subtle push-in.
* Scene 2: medium close-up that clearly captures the complete coffee-drinking action.
* Scene 3: smooth lateral drift into a natural portrait composition.
* Make the scene changes visibly different in framing while maintaining spatial continuity.
* Use realistic depth of field, soft background bokeh, and natural window reflections.
* Keep the woman's face sharp whenever it is the main subject.
* Use warm, restrained cinematic color grading without altering her skin tone.
* Ensure the cup, handle, fingers, lips, and tabletop remain physically consistent.
* Use subtle slow motion only for a brief cinematic moment, never so much that it makes drinking look unnatural.
* Keep camera movement smooth and believable.

**Action accuracy is more important than complicated camera effects.** If necessary, simplify the camera movement to show the sip and cup placement clearly.

## 8. BACKGROUND MUSIC ONLY

Play one beautiful, soft Hindi romantic or mellow café-style song continuously in the background for the entire 10-second video. Use an appropriately licensed track.

The music should match the cozy café atmosphere and support the visual storytelling without overpowering the scene.

The woman must remain silent throughout the video.

* No singing by the woman.
* No dialogue or speaking.
* No humming or whispering.
* No lip-syncing.
* No mouth movements imitating lyrics.
* No voice-over.

Her mouth may move only as naturally required for the physical coffee sip. She must not imitate singing or speak.

If Flow cannot generate suitable music without introducing unwanted singing or speech, generate the video without audio and add the music separately during editing.

## 9. STRICT NEGATIVE CONSTRAINTS

No unchanged input photograph as the first frame, no frozen opening, no static-image hold, no slideshow, and no simple photo zoom.

No identity drift, no face replacement, no age change, no hairstyle change, no altered skin tone, no body reshaping, no artificial beauty filters, and no clothing changes.

No skipped sip, no fake drinking, no cup hovering near the mouth without contact, no cup disappearing, no premature cup placement, and no cup teleporting onto the table.

No distorted fingers, extra fingers, fused hands, warped cup, incorrect cup handle, cup passing through the face, unnatural wrist movement, or broken object continuity.

No sudden pose changes, unnatural facial expressions, exaggerated slow motion, excessive blur, abrupt camera jumps, captions, text overlays, logos, or watermarks.

No singing, lip-syncing, dialogue, humming, whispering, or voice-over.

## FINAL GENERATION PRIORITY

Create a natural, professional 10-second café lifestyle video featuring the exact same woman from the uploaded reference photograph.

Generate new moving footage from the very first frame. Do not show the original photograph directly as the opening shot.

The essential action must be clear and complete: the woman picks up the coffee cup, brings it to her lips, takes one genuine-looking sip, then places the cup securely back on the table. Only after completing the sip should she return to a relaxed window-side pose.

Use three distinct cinematic shots, realistic human movement, a consistent café environment, and one beautiful background song. The woman must never sing or speak.

**Highest priorities: newly generated opening footage, exact identity preservation, a clearly visible and complete coffee sip, physically correct cup placement, natural acting, and professional café cinematography.**