A detailed prompt for nano-banana-pro (referred to as 'banana pro' in the tweet) that transforms a static portrait into a realistic snapshot of an unexpected event occurring. It instructs the model to maintain identity while adding dynamic reactions and physical interactions with a customizable surprise element.
[Unexpected Event Requirement]
{argument name="event" default="Fill in a sudden event here, e.g., 'a bird suddenly flies past the camera', 'a tiger appears from behind the subject', etc. If left blank, the model will design a reasonable sudden event based on the original scene."}
Maintain the identity, appearance, hairstyle, clothing, environment, scene structure, and overall visual style consistent with the original image.
Reconstruct the ordinary static photo into a **realistic snapshot capturing the '0.1 second after a sudden event occurs'**.
1 | The unexpected event must actually happen
Strictly execute the event defined in [Unexpected Event Requirement].
The event must exist realistically in the final image; it cannot be implied solely through facial expressions or body language.
The position, size, direction of movement, and perspective relationships of the event must comply with real photography logic and have natural spatial relationships with the original environment.
If the event involves motion, clearly express the direction and sense of speed.
The event can be located in:
Foreground of the lens
Near the subject
To the side of the subject
Behind the subject
Background area
Crossing between the subject and the lens
Choose the most visually impactful position freely based on the nature of the event.
2 | The subject must react instinctively to the event
The subject is not posing but making a real, unprepared instinctive reaction at the moment the event occurs.
Automatically design movements compliant with human biomechanics based on the event's position, speed, danger level, and direction of movement, such as:
Sudden lateral evasion, leaning back, leaning forward, turning around, crouching low, jumping away, losing balance, emergency stop, striding to dodge, reaching out to block, arms protecting the body, grabbing nearby objects to maintain balance, etc.
Do not limit actions to just "dodging backward."
Redesign the direction of the subject's body reaction based on the position and trajectory of the sudden event.
3 | Actions must have a complete kinetic chain
The subject's movement must form a complete dynamic transfer from feet → legs → hips → torso → shoulders → arms → head.
Clearly show:
Shift in center of gravity
Difference between supporting leg and moving leg
Counter-rotation of hips and shoulders
Head quickly turning toward the event
Arms performing protective, blocking, grabbing, or balancing actions
Natural inertial movement of clothes, hair, and body
Avoid static poses like standing straight with feet together and hands casually placed, like a model.
4 | Facial expressions must causally relate to the event
The expression must be the immediate reaction after seeing the sudden event.
Automatically match emotions based on the event:
Surprise, shock, alertness, fear, confusion, helpless laughter, astonishment, instinctive dodging, sudden realization of danger, being startled, etc.
Do not deliberately make exaggerated comedic expressions.
The focus is to capture the moment of "What just came?!"
5 | Clear spatial relationship between event and subject
Enhance the spatial depth of foreground, midground, and background.
If the event passes by the subject, let it enter the foreground to create obvious occlusion, motion trails, and visual impact.
If the event appears from behind the subject, ensure the subject's head, shoulders, or body are turning towards it.
If the event enters rapidly from the side, shift the subject's center of gravity in the opposite direction for an immediate dodge.
If the event is large in volume, adjust the scale between the subject and the event according to perspective relationships.
The reason for the subject's movement must be directly visible from the image.
6 | Event takes priority over subject action
The final image is not:
"A person performing a dodge action."
But rather:
"A real event is happening, and the camera captures the subject's immediate reaction to it."
The event itself must become the secondary visual center of the frame.
There must be clear causal, directional, and spatial relationships between the subject's actions and the event.
7 | Photographic effects
Realistic photography, high shutter speed, instant snapshot.
Preserve natural inertial movement but avoid severe motion blur.
The image should possess:
Strong sense of immediacy + spatial depth + dynamic direction + foreground/background relationship + unpredictability.
Both the subject and the event must comply with real-world lighting, shadows, perspective, scale, occlusion, and laws of motion.
The final effect should look like a photographer happened to press the shutter to capture a previously unpredictable moment.
No static posing, no studio feel, no theatrical feel, no deliberately manufactured disasters.
Core goal: Viewers should first see "what happened," and only then notice "how the subject dodged."
Still from a Hollywood sci-fi movie. Over-the-shoulder shot of the man in image 1. He is on the left side of the frame in the foreground. The woman from image 2 is on the right side of the frame in focus. The setting is a different angle of image 3. Use image 4 as the influence for the color grade, lighting, style, and film stock type.
Create a key visual for a magical girl anime. Finish it as an attractive poster design that includes the title logo.
Generate image of 3d golden text "{argument name="text" default="Mahalakshmi"}" and golden goddess Mahalakshmi is sitting and adjusted over that text. Black background. 1:1 ratio 8k resolution
Use the uploaded reference image as the exact facial identity reference. Preserve her face, facial structure, eyes, eyebrows, nose, lips, jawline, skin tone, hairstyle, and identity exactly — no identity drift or facial alteration. Create an ultra-photorealistic colorful luxury fashion portrait of the same woman reclining elegantly inside a luxurious white freestanding bathtub. She wears a deep emerald-green satin floor-length gown with elegant draping and long black opera gloves. Add layered diamond necklaces, sparkling earrings, and refined luxury jewelry. She holds a crystal wine glass filled with rich red wine in one hand, while her other gloved hand rests gracefully near her head. Her hair is sleek and polished, with a confident, mysterious expression and direct eye contact with the camera. Luxurious cream-and-gold marble bathroom, warm champagne lighting, subtle reflections, rich emerald, burgundy and gold color palette, cinematic shadows, glowing highlights, realistic satin texture, natural skin pores, realistic jewelry sparkle, high-fashion editorial photography, sophisticated Hollywood cinematography, 85mm lens, shallow depth of field, ultra-detailed, photorealistic, elegant and glamorous. Vertical 4:5, full-body composition, cinematic luxury editorial, realistic colors, no AI look. Negative prompt: different face, identity drift, altered facial features, plastic skin, over-retouching, distorted hands, extra fingers, bad anatomy, CGI, cartoon, blurry, low quality, watermark, text, logo.
Create a photorealistic luxury fashion editorial of an elegant young woman standing confidently in front of a glossy brown luxury sports sedan, parked on a sophisticated European-style city street. She wears a tailored chocolate-brown blazer, matching high-waisted trousers, a silky brown blouse, and pointed brown heels. Long softly wavy brown hair, natural flawless skin, subtle luxury makeup, confident expression. Warm beige historic architecture with tall arched windows and boutique entrance in the background, cinematic golden-hour lighting, shallow depth of field, realistic reflections on the car, premium fashion campaign aesthetic, full-body composition, vertical 4:5, ultra-detailed, realistic photography, no text, no watermark, no distorted hands or face.
Use the uploaded image as the primary visual reference. Create a high-end photorealistic beauty portrait of the same woman, preserving her facial features, face shape, skin tone, eyes, nose, lips, and overall identity. She has dark brown hair styled in a messy elegant updo with loose wavy strands framing her face. Soft natural makeup, warm brown eyeshadow, subtle eyeliner, long lashes, glossy deep-red lips, and realistic glowing skin. She wears an elegant deep burgundy sheer long-sleeve outfit with a high neckline. Her hand rests gracefully near her neck, showing delicate gold rings and detailed burgundy-and-gold nail art. Pose is slightly turned toward the camera with a soft, confident expression. Warm golden-orange cinematic lighting, strong soft rim light around the hair, cozy dark beige background, shallow depth of field, realistic skin texture, fine hair details, professional beauty photography, 85mm portrait lens, soft bokeh, cinematic color grading, ultra-detailed, photorealistic, 8K. No text, watermark, or logo.
Use the uploaded image as the exact visual and facial reference. Preserve the woman’s facial identity, facial proportions, hairstyle, and overall appearance with zero identity drift. Create a photorealistic cinematic luxury evening portrait of the same woman standing beside a calm infinity pool overlooking a modern waterfront city skyline at blue hour/night. She wears an elegant floor-length silver-white couture gown with delicate crystal embellishments, thin straps, a fitted embellished bodice, flowing pleated skirt, and a subtle train. Add matching sparkling silver high heels. Keep the same graceful side-profile pose as the reference: body slightly turned sideways toward the camera, shoulders relaxed, one arm naturally resting beside her body, elegant posture, soft confident gaze directly toward the camera. The pool should reflect the surrounding city lights naturally. In the background, show a sophisticated modern skyline with tall illuminated towers, softly blurred for cinematic depth of field. Include a realistic, naturally sized full moon in the upper sky — not oversized — with subtle moonlight illuminating the scene. Gentle evening breeze moves a few strands of her hair and the gown slightly. Lighting: realistic moonlight mixed with soft ambient architectural lighting, subtle highlights on the silver dress, natural skin tones, realistic shadows, cinematic contrast, soft atmospheric haze. Camera: full-body composition, eye-level camera, 85mm portrait lens, shallow depth of field, realistic bokeh, sharp subject, detailed fabric texture, natural skin pores. Style: high-end luxury fashion editorial, cinematic photography, ultra-photorealistic, sophisticated, elegant, realistic proportions, natural skin texture, no artificial AI appearance. Negative prompt: identity change, face drift, different person, altered facial features, oversized moon, plastic skin, excessive retouching, distorted hands, extra fingers, warped body, unnatural pose, cartoon, CGI look, oversaturated colors, excessive glow, duplicate person, blurry face, watermark, text, logo.
Studio portrait of one smiling person holding a Cheetos Crunchy orange chips bag close to the camera, both the bag and the person’s head in the foreground. Captured with an ultra-wide fisheye lens for a playful, youthful, energetic feel. The model wears a glossy bright orange puffer jacket over a white t-shirt. Background in a vibrant orange gradient with light yellow accents, bold and fun. Soft cinematic lighting, juicy highlights, slight saturation boost, modern snack-ad editorial style. Expressive smile, fun street-commercial aesthetic.
Some prompts are collected from creators on X. Copyright belongs to the original authors.