How to Create an Underwater Summer Couple Video With AI

An airy summer memory that travels from a waterside walk into turquoise underwater imagery, a musical boat interlude, and a tender ending.

Example image

Underwater Summer 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 Underwater Summer effect

Choose Underwater Summer 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 underwater hands and bodies anatomically natural
Maintain the white-linen and black-halter wardrobe
Use fluid water transitions and gentle romantic music

Full English prompt

Design the first 21.7 seconds as a complete vertical romantic travel montage; any model overrun after 21.7 seconds must be a clean final-frame hold. 0.0-0.3: rear medium-wide shot, the couple walk hand in hand beneath leafy waterside trees. The man wears a loose open white linen shirt over a white vest with dark tailored shorts; the woman wears a flowing black sleeveless halter maxi dress. 0.3-2.8: soft cut underwater to an extreme close-up of their hands reaching and slowly interlacing in clear turquoise water, suspended fabric and tiny bubbles. 2.8-4.3: wide underwater shot, they swim side by side, bodies horizontal, reaching toward each other. 4.3-6.8: dissolve through abstract sunbeams, rippling water, bubbles and blurred silhouettes as a dreamy transition. 6.8-9.1: warm boat-side close-ups; the woman smiles silently toward the man, wind moving her hair. 9.1-10.8: the man plays a natural wood acoustic guitar while seated; her hand gently brushes his hair. 10.8-13.0: rear two-shot of them sitting close and watching sunset over calm water. 13.0-15.0: cut back to a rear walk under trees, linked hands and dappled sun. 15.0-18.8: energetic handheld transition past branches; the man playfully reaches and hangs from a low branch, then the woman steps close and reaches with him. 18.8-20.6: intimate close-ups of linked hands, arms, smiling eyes and near-touching faces around the branch. 20.6-21.7: they walk away, turn toward each other and share one brief natural closed-mouth kiss, then remain embraced. Preserve airy blue-green water, warm cream sunlight, soft film grain, gentle handheld movement and authentic summer tenderness. Preserve the adult man and adult woman identities from the two reference photographs throughout, regardless of upload order. Use only the man in the reference images as the male lead and only the woman in the reference images as the female lead. Keep facial structure, skin tone, hair identity, body proportions, and apparent adult age stable across every shot. Natural anatomy, hands, lips, eye lines, weight transfer, cloth motion, and contact physics. Romantic but tasteful intimacy. Vertical 9:16, photorealistic cinematic lifestyle footage, no captions, text, logos, watermarks, interface, extra people, duplicate bodies, face swaps, morphing, fused limbs, broken fingers, floating props, or abrupt identity changes. Audio: only a gentle romantic instrumental music track; no dialogue, speech, laughter, breathing, moaning, kiss sounds, or other human vocalization.

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.