How to Create a Villa Kiss Video With AI

A polished Southern European romance that moves between black-and-white memories and warm golden-hour color before ending in a gentle kiss.

Example image

Villa Kiss two-person example

This is the visual reference for the effect. The generated video follows its two-person composition, wardrobe direction, lighting, body language, and romantic atmosphere.

What you need

One clear photo of an adult man
One clear photo of an adult woman
Front-facing or three-quarter faces with natural lighting
No heavy beauty filters, sunglasses, face obstruction, or tiny faces

Upload order may vary. The prompt identifies the man and woman by the people visible in the reference images rather than by image number.

Step 1: Open the Villa Kiss effect

Choose Villa Kiss in AI Video. This effect is designed for two-person reference-to-video generation in a vertical cinematic format.

Step 2: Upload the two portraits

Upload one portrait for each person. Use photos with clear facial structure, visible hair, and similar image quality. The source photos provide identity only; the effect creates the wardrobe, environment, camera movement, transitions, and actions described below.

Step 3: Generate the video

Start generation and allow the effect to build the complete sequence. Keep both people visible when the scene calls for a two-shot. If a result has identity drift, merged hands, unstable lips, or an incomplete ending, regenerate with clearer portraits.

Key details to protect

Keep the navy suit and ivory gown consistent
Preserve the monochrome-to-warm-color transition
Use restrained body language and a natural final kiss

Full English prompt

Create a 15-second, 9:16 vertical, photorealistic cinematic romance film with one clearly adult man and one clearly adult woman. Use the adult man visible in the reference images as the sole identity reference for the male lead and the adult woman visible in the reference images as the sole identity reference for the female lead. The reference images preserve identity only; they are not opening or ending frames. Keep both faces, ages, skin tones, hairstyles, and body proportions stable. Never blend, swap, or duplicate them.

Wardrobe is continuous in every shot. The man wears a tailored dark-navy single-breasted blazer with brass buttons and white pocket square, a pale blue-and-white fine-striped open-collar shirt, cream high-waisted straight-leg trousers, a narrow black leather belt, and black thick-soled leather shoes. The woman wears an ivory bias-cut floor-length gown with an asymmetrical one-shoulder draped neckline, a very low V-shaped open back with two fine straps, delicate necklace, small earrings, and bracelet. Preserve realistic seams, folds, fabric weight, and motion; never change either outfit.

Mood and setting: an intimate Southern European summer memory around pale stucco villas, shutters, terracotta roofs, greenery, stone lanes, and a small courtyard. Alternate high-contrast black-and-white memory shots with warm present-time color. Color shots use low late-afternoon sun, soft white-wall bounce, golden rim light on hair and shoulders, creamy restrained tones, subtle film grain, soft highlights, and realistic skin texture. Use elegant handheld fashion-film framing, shallow depth of field, low angles, short hard cuts, match cuts on hands and body motion, and natural foreground occlusion. No flashy transition effects.

Shot order: 0.0-1.5s, black-and-white low-angle waist-up close shot: he holds her waist, she supports his lower back and leans toward his cheek; their faces almost touch and they smile softly without kissing. 1.5-2.1s, black-and-white rear medium shot: they walk hand in hand and glance back, clearly showing her low open back and full gown. 2.1-3.6s, black-and-white extreme close-up: she wraps an arm behind his neck, palm on his nape, while he lowers his face beside her cheek and hair; intimate but no lip contact. Cut on movement into color. 3.6-4.8s, warm frontal tracking shot: they walk toward camera holding hands, look at each other, then forward. 4.8-5.8s, she passes close to lens, her red hair and draped gown creating natural occlusion; he follows half a step behind, still holding her hand. 5.8-6.6s, reverse low-angle shot from behind her: joined hands below waist, he faces her and smiles. 6.6-8.0s, full-body shot: he raises their joined hands and guides one clockwise turn; her hair swings first, then the weighted skirt, and she finishes facing him. 8.0-9.4s, golden backlit close-up: she cradles and gently strokes his cheek; he lowers his eyes, their noses almost touch, and the camera slowly pushes in. 9.4-10.5s, low rear full-body editorial pose: they stand close and turn their heads back together. 10.5-11.7s, warm extreme close-up: they exchange a quiet, restrained look of attraction and anticipation. 11.7-12.7s, low-angle side-by-side medium close-up beneath shuttered architecture, shoulders touching and gazes gradually aligning.

12.7-14.3s, added warm profile kissing close-up: she places her palm on his cheek while he wraps an arm naturally around her waist. Foreheads and noses touch first; they close their eyes and share one soft, realistic closed-mouth kiss, holding natural lip contact for about 0.8 seconds, then remain in a gentle embrace. Use a subtle push-in and do not cross the axis. 14.3-15.0s, hard cut to black-and-white close-up after the kiss: they look at each other and form quiet natural smiles, then fade briefly to black. Do not loop.

Audio is background music only: gentle instrumental piano, warm strings, and extremely light acoustic guitar, elegant and romantic, rising slightly for the turn, softening during the cheek caress, reaching a restrained peak during the kiss, and fading in the final second. No dialogue, laughter, breathing, kissing sounds, footsteps, clothing sounds, ambience, singer, humming, narration, vocal samples, or lyrics.

Avoid identity drift, face blending, age drift, a third lead, outfit changes, short gown, dark trousers, fused lips, open-mouth kissing, visible tongue, malformed teeth, extra fingers, broken hand contact, intersecting arms, fabric clipping, distorted limbs, explicit behavior, violent camera shake, nighttime, interiors, neon, text, subtitles, logos, or watermarks.

Quality checklist

Exactly one adult man and one adult woman remain recognizable
Faces, ages, skin tones, hairstyles, and body proportions stay stable
Wardrobe and scene changes follow the timeline in the prompt
Hands, embraces, turns, lifts, and kisses have believable contact physics
The final kiss is natural, closed-mouth, tasteful, and free of facial distortion
No duplicate people, extra limbs, text, subtitles, logos, interface, or watermark

Pro tip

Use portraits with neutral expressions and clean lighting. The effect already defines the emotion and body choreography, so simpler source photos usually preserve identity more reliably than dramatic poses or heavily edited selfies.