✦AI Prompt LibraryAI Prompts with
AI Prompts with
Real Examples
An AI prompt is the exact text that tells a model what to generate. Every prompt below is free to copy and paired with the real photo or video it produced on ZenCreator — video samples play right in the card, so you can see the motion before you generate.
Browse AI prompts
160 prompts
AI Couple Photo Makers
A Close-up photo of Two. The person on the left stands straight, with a slight forward lean. The person on the right is positioned slightly in front and to the right of the other person, also standing straight. The person on the left has their arms wrapped around the other person's torso, with hands clasped. The person on the right has their head tilted slightly towards the person on the left, resting against their head., Both individuals are wearing black turtleneck sweaters, likely made of a knit material., direct seductive gaze into camera. The setting is a simple, dark studio environment. The background is a solid, dark color, creating a minimalist atmosphere. — no mirrors, Canon EOS R5, 85mm, f/1.8, ISO 400, 1/250s. The lighting appears to be artificial, with a soft quality. It is directed from the front, highlighting the front of the figures and creating soft shadows around the edges., skin texture clearly visible. No digital retouching, looks like a candid real-life photo.AI Video Generators
Same sweaty woman in a black sports bra sitting on a yoga mat in a brick fitness studio after a workout. Handheld selfie-style framing with her arm extended toward camera, natural micro-jitter, no gimbal glide. She exhales, lifts her free hand and tucks wet hair behind her ear, then looks straight into the camera and speaks clearly with a soft smile: “That was a really good workout today.” After the line, she gives a small nod and relaxes her shoulders. 24fps, shutter 1/48, mild grain, natural skin texture. No face morphing, no smoothing, no text.AI Video Generators
A girl, is sitting on the bed of her bedroom and standing up, she wears white bikini, her breasts are bouncing, her face is cut off, she is walking into the direction of the moving camera, noisy image quality. A girl, is sitting on the bed of her bedroom and standing up, she wears white bikini, her breasts are bouncing, her face is cut off, she is walking into the direction of the moving camera, noisy image quality.AI Video Generators
Realistic handheld iPhone selfie video on a city street. Front camera at arm’s length, slight natural shake while walking. Late afternoon golden sunlight, red brick buildings and storefronts in the background, light city ambience and distant traffic sounds.
Stylish brunette girl with a sleek high ponytail, defined cheekbones and slightly full lips, wearing black narrow sunglasses, a blue denim jacket over a white fitted top, and loose black pants. She’s holding a clear plastic cup with a bright green smoothie and a straw.
She walks confidently, occasionally taking a sip, speaking in a relaxed, happy tone:
“Guys, it’s finally warm outside! I can’t believe it. I even got a smoothie today instead of hot tea.”
She smiles, glances around at the sunny street:
“I’ve missed this weather so much. I’m already thinking about going to the sea soon.”
She looks back into the camera, playful and curious:
“What about you? How do you feel about the sea?”
Natural vlog style, authentic street vibe, realistic smartphone quality, soft warm sunlight on her face.AI Video Generators
Ultra realistic low-light smartphone video in a cozy bedroom, warm bedside lamp lighting, soft shadows, balanced exposure, slight grain, natural skin texture, visible natural imperfections, authentic intimate home aesthetic.
A young woman lying on a bed with white sheets and a wooden headboard behind her. She is wearing a simple black fitted tank top. Her dark wavy hair spreads naturally over the pillow. Defined cheekbones, subtle natural makeup, expressive eyes, slightly full lips, natural skin with realistic texture.
The video starts in a relaxed selfie angle from slightly above her. Warm ambient light creates soft highlights on her face. Quiet nighttime atmosphere, very subtle room ambience.
She shifts slightly on the pillow, one arm resting above her head. Small natural movements — slow breathing, gentle blinking, relaxed shoulders. She looks directly into the camera with deep, affectionate eye contact.
She speaks slowly, softly, and very sensually — her voice calm, warm, full of tenderness. No rushing, natural pauses between phrases:
“I’m already planning to go to sleep…
I just wanted to tell you good night…
Sleep well, my dear.”
She keeps her gaze steady and loving, her expression intimate and sincere. No exaggerated gestures, no blowing a kiss — just a soft, lingering look and a gentle smile before the video naturally fades.
No cinematic grading, no slow motion — realistic, intimate smartphone nighttime video with authentic emotion and natural pacing.AI Video Generators
Close-up beauty portrait, harsh direct on-camera flash look, glossy skin highlights, wet wavy hair, white marble wall background, shallow depth of field, subtle film grain. The woman looks straight into the camera. She slowly shifts from a neutral expression into a playful smile, then gently bites the tip of her index finger (very light pressure, no aggressive biting, keep lips and teeth natural). After a brief pause, she releases the finger, slightly tilts her head, and blows an air kiss toward the camera: lips purse, soft exhale, cheeks barely move, then a small relaxed smile returns. Keep hand motion smooth and minimal, fingers elegant, no deformation. Micro-details: one slow blink, tiny eye sparkle from flash, subtle breathing in collarbone, a few wet hair strands sway slightly. Camera locked-off, no zoom, only minimal handheld micro-drift. Duration 4–6 seconds, loopable ending on a soft smile. No text, no glitches, realistic anatomy, natural motionAI Video Generators
Seductively touching her right knee and Beautiful woman smiling at the camera, swaying her body rhythmically towards the camera, with small amplitude, showing feminine charm without being too exaggerated. Natural and gentle expressions, movements that follow natural logic and human body structure, fixed camera.AI Lip Sync Generators
Handheld selfie camera shake, slight zoom-in. She smiles, blinks, and nods while talking.AI Video Generators
Vertical iPhone-style video, realistic handheld smartphone footage. Bright sunny outdoor courtyard with brick walls and greenery. Natural daylight, glossy reflections on a black car covered with light soap foam. Slight natural phone movement, no cinematic grading.
A woman stands beside the black car with a sponge and soapy water.
She leans gracefully against the hood, one hip resting lightly on the car. With smooth, controlled movements, she slides the sponge across the windshield in long elegant strokes. Water and foam move naturally down the glass.
She shifts her weight slightly, stretches her arm upward and continues washing the upper part of the window in slow, fluid motions. Her movements are stylish and confident, body posture relaxed and balanced.
Soap bubbles glisten in the sunlight, water drips down the car surface. Natural physics, authentic smartphone look, playful and elegant car-wash vibe.AI Video Generators
Vertical cinematic street portrait in a narrow city alley with red brick walls and fire escapes, soft overcast daylight, realistic handheld phone video vibe, natural skin texture, subtle film grain, shallow depth of field. A young blonde woman stands centered, holding one braid between her fingers near shoulder height. She keeps her posture mostly still, shoulders relaxed, chin slightly raised. She locks eyes with the camera with a bold, provocative gaze. Over 4–6 seconds: she slowly tightens her grip on the braid and gives it a tiny tug, her head tilts a few degrees, one slow blink, then she bites her lower lip gently (no exaggerated mouth stretch), holding it for a beat before easing into a faint smirk. Micro-movements only: subtle breathing, tiny sway of the braid, minimal hair flyaways moving in a light breeze, necklace pendant barely shifts. Camera: locked framing with very slight natural handheld drift, no zoom, no jump cuts. Lighting stays consistent, realistic shadows on face, keep facial identity stable, clean anatomy, no warping, no extra fingers, no text, no artifacts. Loopable ending on the confident lip-bite/smirkAI Video Generators
Luxury cozy bedroom scene, a stylish woman lies elegantly on a bed wearing a green satin robe with feather trim, holding a vintage black telephone to her ear and a coupe glass in her other hand. Warm soft evening lighting, intimate premium atmosphere. She reacts to the phone conversation with a soft flirtatious smile, then lets out a light quiet laugh, natural and effortless. After that, she slowly raises the glass and takes a small delicate sip while keeping a playful relaxed expression. Smooth realistic motion, natural hand movement, subtle facial expression change, soft body movement, no abrupt motion, no exaggerated acting, refined late-night luxury mood, cinematic lifestyle realism. Camera makes a slow subtle push-in, keeping her, the telephone, and the glass beautifully framed.AI Video Generators
Animation prompt (vintage vibe): A young brunette woman stands on a city sidewalk by a crosswalk in harsh midday sun, candid street-photo energy. She squints and scrunches her nose from the bright light, then relaxes into a small, cute smile, keeping the same pose with hands in her jeans pockets. Minimal motion only: subtle head tilt, tiny shoulder shift, natural breathing, a light breeze moving a few strands of hair. Camera handheld but steady, chest-level framing, slight micro-jitter like an old compact camera. Strong direct sunlight and deep shadows, natural lens flare and a bit of overexposure on highlights. Vintage film look: warm color shift, visible grain, soft halation around bright edges, slight chromatic aberration, tiny dust/scratch artifacts, occasional flicker, mild vignetting. No text overlays, no logos added, no stylization into illustrationAI Video Generators
The girls carelessly pour drinks into glasses and moving, drinking sloppily and spilling everything, but they smile.AI Video Generators
Use the provided source image as the first frame. Create an ultra-realistic luxury fashion selfie video of the same person in the same setting as the source image. Keep the exact identity, facial features, hairstyle, outfit, body proportions, lighting, background, pose foundation, and overall composition fully consistent with the original image.
The scene begins almost still, like a premium candid selfie moment captured in real life. After a brief pause, the subject makes a small, natural, fashionable movement: a subtle head tilt, a soft shift in gaze, a delicate change in expression, and a faint warm smile. Add a gentle hair adjustment or a light natural movement near the face, followed by a calm return of eye contact toward the camera. The performance should feel cute, effortless, stylish, and believable, with minimal but expressive motion. Keep the body movement refined and realistic, with slight posture adjustment, soft breathing, and natural timing.
If the source image already suggests a selfie pose, preserve that energy and continue it naturally. If the pose is more static, introduce the movement gradually so it feels like a real person casually filming a short fashion selfie clip. Hair should move slightly with natural motion, and clothing should react subtly and realistically. Keep everything grounded, understated, and true to life.
Camera movement: realistic handheld smartphone-style selfie framing with very subtle natural micro-motion, slight angle drift, soft autofocus breathing, and authentic exposure adaptation. The camera should feel like it is being held by a real person. No dramatic zooms, no cuts, no aggressive movement, no surreal motion, no artificial cinematic tricks.
Style: ultra-photorealistic, strong emphasis on realism, realistic skin texture, natural facial expression, authentic lighting, soft true-to-life shadows, polished but not artificial, premium lifestyle mood, fashion selfie aesthetic, vertical 9:16, shot on iPhone. No body distortion, no extra limbs, no flickering, no warped details, no face changes, no CGI look, no artificial beauty filter.
Audio: clean natural synchronized ambience matching the environment, subtle room tone or soft background atmosphere, delicate fabric movement, light natural breathing, faint realistic motion sounds, no music.AI Video Generators
Top-down close framing, same red-haired woman lying on white sheets in a beige hoodie, sunlit window-shadow pattern across her face. She blinks slowly; a tear runs down her left cheek. She lifts her hoodie sleeve and gently wipes under one eye (single simple motion), then stops and swallows, trying to regain control. Her breathing steadies slightly but eyes stay wet and red. Camera remains steady with subtle hand-held sway. 24fps, shutter 1/48, natural texture, mild grain. No face drift, no warping, no beauty smoothing, no text.AI Video Generators
A stylish young woman in elegant black clothing enters a subway carriage and calmly sits down on the right seat. She adjusts her posture, looks toward the camera with a warm smile, then gently blows a kiss toward the viewer with her hand. The subway wagon has a few passengers in the background, creating a natural city atmosphere, while the space around her remains relatively open. Soft cinematic lighting, fashionable urban aesthetic, smooth natural movements, realistic metro interior, depth of field, high detail, 4K, cinematic camera, slight handheld motion.AI Video Generators
Stylish night car interior scene, a confident blonde woman lounges across the white leather back seat of a luxury car, wearing a denim tube top, red cargo pants, and white sneakers. Blue ambient lighting glows through the interior, city lights blur outside the window. She lazily shifts her legs across legs in a relaxed playful motion, settling deeper into the seat with effortless attitude. Right after it pops, she gives a short playful laugh with a confident mischievous expression. Smooth realistic body motion, natural leg movement, subtle laugh, no abrupt movement, no exaggerated acting, cool luxury street aesthetic, modern Instagram reel energy. Camera makes a slow cinematic handheld push-in, keeping her face, legs, and the glowing car interior beautifully framed.AI Video Generators
The man bends his knees while the girl is on his legs, and then he lifts his legs again.AI Video Generators
The couple kisses, and the girl covers the camera lens with her hand.AI Video Generators
Same scene, crisp winter daylight aesthetic. A girl in a warm beanie and a sporty tracksuit dances playfully near a snowy forest, light snow on the ground and pine trees behind her. She smiles while moving to the rhythm, making small energetic dance steps and casual hand motions. Suddenly a firework bursts in the sky behind her, bright colors reflecting on the snow. She pauses mid-move, turns her head over her shoulder, eyes widening with a surprised, delighted expression as she looks at the fireworks.
Camera: subtle handheld movement with gentle forward drift, slight parallax with the trees, shallow depth of field, cinematic realism, natural body motion, winter atmosphere, soft daylight reflecting off the snow.Loading more prompts…
What is an AI image prompt?
An AI image prompt is the written instruction a text-to-image model uses to build a picture. It names the subject and layers on descriptors — wardrobe, lighting, camera, composition, and style. Models like Seedream, Flux, Midjourney, and Stable Diffusion read that text and translate it, word by word, into pixels.
Two prompts for the same subject can produce wildly different results. That is why a prompt library matters: every prompt below is a tested recipe, shown next to the exact image it generated, so you copy a known-good starting point instead of guessing.
What is an AI video prompt?
An AI video prompt describes a scene in motion: who is in frame, what they do, how the camera moves, and the overall mood. Video engines like Kling 2.6, Seedance Pro 1.5, and WAN 2.7 read that text and generate a 5–10 second clip at up to 1080p.
Motion is harder to describe than a still image, so proven video prompts are even more valuable. Filter the gallery by the video tag — each clip autoplays inside its card, and the prompt next to it is the exact text that produced it, camera directions included.
Anatomy of a great AI image prompt
Strong prompts stack detail in a consistent order. Edit any prompt below by swapping these six parts:
1. Subject
Who or what is in frame — “a young woman”, “a couple”.
2. Descriptors
Age, hair, skin, expression, distinguishing detail.
3. Wardrobe & props
Clothing, accessories, objects held or nearby.
4. Lighting
Golden hour, soft window light, studio softbox, neon.
5. Camera & lens
35mm, 85mm portrait, shallow depth of field, RAW photo.
6. Composition & style
Framing, angle, mood — editorial, cinematic, documentary.
How to use these AI image prompts
- 1Find a look. Search the library or filter by tag — start with "image" or "video", then narrow by subject (portrait, couple, dance, office…) until a sample matches what you want.
- 2Copy the prompt. Tap the copy button on the card. The full prompt — including lighting, camera, and motion details — lands on your clipboard.
- 3Paste into the generator. Open the ZenCreator Text-to-Image or PhotoShoot tool for image prompts, or the Video Generator for video prompts, and paste the text into the prompt box. Or hit "Try this prompt" to open the tool with everything pre-loaded.
- 4Tweak and generate. Swap a few words — subject, wardrobe, lighting, or camera move — to make it yours, then generate. Re-run with small edits until it lands.
Ready to generate? Open the Text-to-Image tool or the PhotoShoot generator for images, or the Video Generator for video prompts, and paste your prompt.
Prompts for every AI image and video model
These prompts are model-agnostic, but each engine has its own strengths. Explore the models and tools behind the samples:
Frequently asked questions
What is an AI image prompt?
An AI image prompt is the written instruction you give a text-to-image model. It describes the subject, style, lighting, and composition you want. The more specific the prompt, the closer the generated image matches your intent — which is why copying a proven prompt beats writing one from scratch.
What is an AI video prompt?
An AI video prompt describes a moving scene: the subject, the action, the camera movement, and the mood. Video models like Kling 2.6, Seedance Pro, and WAN 2.7 turn that text into a 5–10 second clip. Every video prompt below autoplays the exact clip it generated, so you can see the motion before you copy it.
Are these AI prompts free to use?
Yes. Every prompt on this page is free to copy and reuse, with no sign-up required to read them. You only need a ZenCreator account to generate images or videos from them.
Which AI models do these prompts work with?
Image prompts were produced on ZenCreator’s image engines — PhotoShoot, Text-to-Image, and Image Editor. Video prompts ran on Kling 2.6, Seedance Pro 1.5, WAN 2.7, and Grok video engines. The descriptive structure also transfers well to Midjourney, Stable Diffusion, Flux, Sora, and most other generation models.
What is the difference between AI image prompts and AI photo prompts?
The terms are used interchangeably. “AI photo prompts” usually emphasise photorealistic, camera-style results (portraits, lifestyle, editorial), while “AI image prompts” is the broader term covering every style. Every prompt in this library targets photoreal output.
How do I write my own AI image prompt?
Start with the subject, then layer descriptors in order: wardrobe and props, lighting, camera and lens, composition, and finally the overall style or mood. Copy the closest prompt below and swap those parts — it is faster and more reliable than starting from a blank box.
Can I use the generated images commercially?
Yes. Images you generate on ZenCreator are yours to use, including for commercial projects, marketing, and social media. Credits never expire.
Do these prompts work for portraits, couples, and fashion?
Yes. The library is organised by tag — portrait, couple, selfie, office, winter, fashion and more — so you can filter to the exact look you need and copy a prompt that already produced it.
How do I filter between image prompts and video prompts?
Use the "image" and "video" tags at the top of the gallery. The image tag shows prompts paired with still photos; the video tag shows prompts whose sample clip autoplays right in the card. All other tags (girl, couple, dance, selfie…) work across both types.
How often are new prompts added?
The library is refreshed regularly as new ZenCreator templates ship, so the prompt set and sample images stay current with the latest models.
Turn these prompts into your own images and videos
Copy any prompt and generate consistent, photoreal characters and clips for social media, marketing, and creative projects with ZenCreator.
Start Creating