Kenerate AI

Prompt Library

AI Prompt Library

Curated image, video and web design prompts from creators around the world. Copy any prompt, swap the subject or style, and generate with the latest models.

15,630 prompts · Updated daily · 100% free

123 prompts

Ultra-Realistic Cinematic Night Street Selfie During a High-Speed Escape
GPT Image 1.5

Ultra-Realistic Cinematic Night Street Selfie During a High-Speed Escape

"Ultra-realistic cinematic night street selfie with a confident, stylish person in the reference photo leaning out of a car window in a rainy city during a high-speed escape.", "pose": { "arm": "extended toward the camera holding the phone", "head": "slightly tilted back", "attitude": "fearless, playful" }, "face\_and\_skin": { "identity": "100% preserved, no changes to facial structure, proportions, or unique features", "skin": "smooth, luminous with glossy streetlight highlights", "cheekbones": "softly sculpted", "lips": "glossy,", "eyes": "expressive, partially hidden behind narrow black rectangular sunglasses", "texture": "realistic, natural skin texture, visible pores, reflections" }, "hair": { "style": "long, flowing, wind-blown by speed and night air", "volume": "natural" }, "outfit\_and\_details": { "coat": "bold {argument name="coat pattern" default="leopard-print"} faux-fur draped luxuriously over the shoulders", "manicure": "glossy {argument name="manicure color" default="red"}", "jewelry": "minimal silver rings", "glass": "elegant martini glass with a clear cocktail and green olives, catching sharp reflections" }, "environment": { "setting": "wet asphalt night city street", "motion": "intense, high-speed, with a police car chasing behind", "lights": { "headlights": "blurred, aggressive light streaks", "street\_lights": "golden sodium street lamps creating large dramatic bokeh circles", "police\_lights": "blue and red siren flashes creating reflections" }, "mood": "rebellious, playful, glamorous chaos; adrenaline-fueled nightlife energy", "aesthetic": "fashion-editorial crime style" }, "lighting": { "contrast": "high, dynamic mix of warm sodium streetlights, cold blue police lights, and red siren flashes", "reflections": "glossy on skin, glass, car body, and rain-soaked street" }, "camera\_and\_style": { "perspective": "wide-angle smartphone selfie", "depth\_of\_field": "shallow", "background": "strong motion blur with light streaks", "detail": "ultra-high, realistic film grain", "color\_grading": "cinematic", "vibe": "modern luxury runaway" }, "body": { ": { "size": "slightly larger and elongated" } }, "ratio": "9:16"

@K
Reasoning and Instruction Following Puzzle Prompt
GPT Image 1.5

Reasoning and Instruction Following Puzzle Prompt

"Show me 4 realistic objects on a table. The objects are related in some way, this is a puzzle. Add title text across the top, "{argument name="title text" default="What do these objects have in common?"}" And very small upside down text on the bottom which reveals the way in which they are related."

@Joe ⭕ Dot ⭕ Average
VTuber Gaming Thumbnail Creation Prompt
GPT Image 1.5

VTuber Gaming Thumbnail Creation Prompt

Maintain the character's style and outfit, change the scene to them intensely gripping a game controller, and create a thumbnail image in the style of a fictional VTuber's game stream. They look a bit too robust, so please make them more delicate and cute. Also, the bust size should be more modest, and the sleeves should be long sleeves. Fix the collapsed 'Ge' in the top left corner.

@rei@AI art
Cinematic Contact Sheet Generation from Reference Image Prompt
GPT Image 1.5

Cinematic Contact Sheet Generation from Reference Image Prompt

Study the uploaded image carefully and fully internalize the scene: the subject’s appearance, clothing, posture, emotional state, and the surrounding environment. Treat this moment as a single frozen point in time. Create a cinematic image set that feels like a photographer methodically explored this exact moment from multiple distances and angles, without changing anything about the subject or location. All images must clearly belong to the same scene, captured under the same lighting conditions, weather, and atmosphere. Nothing in the world changes — only the camera position and framing evolve. The emotional tone should remain consistent throughout the set, subtly expressed through posture, gaze, and micro-expressions rather than exaggerated acting. Begin by observing the subject within the environment from afar, letting the surroundings dominate the frame and establish scale and mood. Gradually move closer, allowing the subject’s full presence to emerge, then narrowing attention toward body language and facial expression. End with intimate perspectives that reveal small but meaningful details — texture, touch, or eye focus — before shifting perspective above and below the subject to suggest reflection, vulnerability, or quiet resolve. Across the sequence: Wider views should emphasize space and atmosphere Mid-range views should emphasize posture and emotional context Close views should isolate feeling and detail Perspective shifts (low and high angles) should feel purposeful and cinematic, not decorative Depth of field must behave naturally: distant views remain mostly sharp, while closer frames introduce shallow focus and gentle background separation. The final result should read as a cohesive 3×3 cinematic contact sheet, as if selected from a single roll of film documenting one emotional moment from multiple viewpoints. No text, symbols, signage, watermarks, numbers, or graphic elements may appear anywhere in the images. Photorealistic rendering, cinematic color grading, and consistent visual realism are mandatory.

@Ayyoub Ai
Hyper-Realistic Cinematic Action Scene from Reference Image
GPT Image 1.5

Hyper-Realistic Cinematic Action Scene from Reference Image

Using the uploaded image as the primary visual reference, transform the subject into a hyper-realistic cinematic action scene. The man is leaping forward onto a city crosswalk while emerging from a glowing circular dimensional portal behind him. The portal emits intense swirling neon energy in electric {argument name="portal color 1" default="blue"}, {argument name="portal color 2" default="violet"}, and {argument name="portal color 3" default="magenta"}, with sparks, lightning arcs, particle debris, and visible energy-distortion effects in the air. The subject is captured mid-motion in a powerful running leap, expression focused and intense. His original clothing from the reference image is naturally adapted for dynamic motion, with realistic fabric flow, folds, and physics, without changing his identity. Footwear and outfit subtly reflect the neon portal light. Preserve the subject’s original facial structure, skin texture, hairstyle, beard (if present), and body proportions exactly as in the reference image. The environment is a modern urban city street with cinematic perspective. The background is slightly motion-blurred to emphasize speed and action. The road surface appears wet, showing subtle reflections of the glowing portal and neon light streaks. Dramatic cinematic lighting, volumetric light rays, shallow depth of field, ultra-sharp details, high contrast, realistic physics, sci-fi atmosphere, professional action-movie poster composition, cinematic color grading, ultra-high resolution, 8K quality.

@புல்லட் வண்டி 😈🧛
Glitter-Bomb Pro-Wrestling Idol Recasting Prompt
GPT Image 1.5

Glitter-Bomb Pro-Wrestling Idol Recasting Prompt

Using [subject image] as reference, recast them as a glitter-bomb pro-wrestling promo idol, every natural feature intact. Skin glows under body-oil sheen; eyes fierce behind electric-blue eye-black. Power-stance on turnbuckle, championship belt bedazzled with sequined lightning bolts. Wardrobe: spandex singlet in {argument name="singlet color" default="hot-magenta gradients"}, fringe epaulettes, knee-high star boots. Lighting: arena spotlights with red-white-blue gels, lens-flare pyro sparks. Background: smoky ramp plus green-screened crowd waving foam fingers. Color grade in oversaturated VHS chroma, slight scan-line filter. Accessories: oversized mirrored shades, feather boa, mic in hand, restraint kept so the camp feels idol, not caricature. Final vibe: larger-than-life entrance—bold, patriotic, unmistakably them.

@Matthew Berman
Cinematic Dual-Tone Portrait from Uploaded Photo
GPT Image 1.5

Cinematic Dual-Tone Portrait from Uploaded Photo

"A cinematic studio portrait of the person in the uploaded photo, framed from the chest up, facing the camera with a calm, confident presence. Dramatic dual-tone lighting with cool teal and warm golden tones creating a modern, cinematic mood. Natural skin texture, sharp focus on the eyes, soft shadows, and smooth color transitions. Hair styled naturally, wearing a minimal dark outfit with a contemporary aesthetic. Clean studio background with subtle gradients. Professional photography, shallow depth of field, cinematic color grading, ultra-realistic, high detail, 4K quality. Aspect ratio: 3:4 "

@✨ Pulikesi✨
Chinese Fantasy Digital Art Prompt Template
GPT Image 1.5

Chinese Fantasy Digital Art Prompt Template

{ "meta_info": { "title": "Ethereal Hanfu Spirit", "style_category": "Chinese Fantasy / Abstract Digital Art", "aspect_ratio": "3:1" }, "visual_elements": { "subject": { "description": "Silhouette wearing attire determined by the character", "pose": "Pose determined by the character, floating in mid-air", "composition": "Centered ethereal figure with flowing trails extending to the sides" }, "atmosphere": { "lighting": "Bioluminescent glow, volumetric lighting, rim lighting", "effects": "Flowing smoke, light particles, holographic dispersion, silk-like energy trails", "colors": ["Deep Navy Blue", "Glowing Cyan", "Iridescent Gold", "Soft Peach"] } }, "prompt_export": { "natural_language_prompt": "A wide panoramic digital artwork depicting a figure composed of flowing ribbons of light, translucent smoke, and iridescent particles. The background features deep, moody indigo and dark blue tones. The figure emits a soft, magical bioluminescent glow in hues of gold, peach, and cyan. The overall style is abstract fantasy, emphasizing fluid motion and a dreamy atmosphere, rendered in 8K resolution with highly detailed textures and exhibiting the Tyndall effect.", "tag_based_prompt": " silhouette, flowing light lines, smoke effects, particle effects, bioluminescence, iridescent effects, dark blue background, cinematic lighting, ethereal, mystical, masterpiece, best quality, 8k, wide angle --ay 21:9 ", "negative_prompt": "photorealistic, solid skin, heavy outlines, messy lines, text, watermark, low quality, jpeg artifacts, blurry, distorted face, bad anatomy" }, "technical_settings_recommendation": { "sampler": "Euler a / DPM++ 2M Karras", "steps": 30, "cfg_scale": 7.0, "model_suggestion": "Niji 6 (for Midjourney) or Abstract/Fantasy-based SDXL models" } } Character set as: {argument name="character setting" default="The four master and disciples from Journey to the West"}

@岚叔
12th-Century Javanese Battlefield at Dawn
GPT Image 1.5

12th-Century Javanese Battlefield at Dawn

A battlefield at dawn in 12th-century Java, rendered in muted, desaturated tones. Smoke drifts low across scarred earth and broken vegetation. A Pendekar Jawa is seen in silhouette, walking forward with calm resolve as the rising sun breaks through the haze behind him. He wears traditional Javanese warrior attire ikat head cloth, loose garments, and a sword at his side bearing subtle signs of battle and leadership. Long lens compression, gritty textures, cinematic lighting, documentary-style realism, evoking historical gravitas, quiet defiance, and spiritual strength.

@DΞV
Prompt to Generate Intentionally Bad, Child-like Crayon Drawings
GPT Image 1.5

Prompt to Generate Intentionally Bad, Child-like Crayon Drawings

Place the subject standing in the center, with a plain pose and composition, giving the impression of poor quality, like a child's scribble who just started drawing. The style should be a hand-drawn, anime-style color sketch using rough crayon lines (leaving the under-drawing lines), emphasizing the poor quality!

@榊正宗🫛ずんだもん発案者
Complex Four-Quadrant Paper World Composite Prompt
GPT Image 1.5

Complex Four-Quadrant Paper World Composite Prompt

A seamless 16:9 full-frame composite image divided into four distinct quadrants. **CRITICAL:** The four sections touch each other directly. NO GREY BACKGROUND. NO BORDERS. NO GAPS. The image is filled edge-to-edge with paper details. **Composition:** A split-screen view looking deep into four different paper worlds. 1) **Top-Left (Luckin):** A wide view of a magical paper forest. Blue and white paper clouds and coffee leaves fill the quadrant completely. A white paper stag leaps through the density. 2) **Top-Right (Google):** A wide view of a **"Topographic Map" style paper cavern**. The "G" logo is formed by **hundreds of thin sheets** of Blue, Red, Yellow, and Green paper stacked horizontally. It looks like a sediment canyon or a contour map. Visible paper fibers and sharp cut edges. NO plastic smoothness. 3) **Bottom-Left (Coke):** A wide view of a red paper explosion. The Coke bottle is a **Negative Space Silhouette**—a deep hole void cut through dense layers of red paper. White paper ribbons span across the void. 4) **Bottom-Right (McDonald's):** A wide view of a yellow paper city. Vertical strips of yellow paper (french fries) stand densely packing the frame. The Golden Arches rise from deep within the layers. **Global Material:** Everything is matte cardstock. **Lighting:** Soft, even studio lighting revealing the depth of the paper cuts. **Tech:** Octane render, 8k, --ar 16:9 --stylize 400 --no borders, frames, background wall, isolated objects, 3d plastic, seamless texture

@两斤
Surreal Diorama from 'Brave New World'
GPT Image 1.5

Surreal Diorama from 'Brave New World'

Surreal diorama emerging from an open vintage book of "{argument name="book title" default="Brave New World"}" by {argument name="author" default="Aldous Huxley"}: the pages form a futuristic hatching laboratory with rows of glowing test tubes containing embryonic figures on conveyor belts, lab-coated workers in white uniforms operating machines, a large all-seeing eye symbol on the wall, conveyor belts moving via hidden mechanisms, cool blue neon lighting, hyper-detailed miniature sculpture, clinical and eerie atmosphere, photorealistic.

@Gadgetify
Ultra-Photorealistic Editorial Prompt for Accidental Fall Pose
GPT Image 1.5

Ultra-Photorealistic Editorial Prompt for Accidental Fall Pose

{ "task": "editorial_accidental_fall_pose", "output": { "type": "single_image", "resolution": "ultra_high_resolution", "realism": "ultra_photorealistic", "skin_detail": "true_to_life_natural_skin", "quality": "high_end_editorial" }, "scene": { "environment": "minimal studio", "background": "clean light grey seamless backdrop", "prop": { "type": "white rectangular cube", "finish": "matte" } }, "composition": { "moment": "captured immediately after losing balance", "pose": { "torso": "upper body fallen forward onto the floor", "hips": "caught unevenly on the cube edge", "upper_legs": "resting on the cube", "lower_legs": "lifted upward in the air, bent naturally", "head": { "position": "lying sideways on the floor", "neck": "fully relaxed", "expression": "neutral, unposed, natural" }, "arms": { "one": "extended loosely on the floor", "other": "relaxed, bent near torso" } }, "camera": { "angle": "side profile", "shot_type": "full body", "lens": "85mm", "framing": "natural distance, not too close" } }, "subject": { "gender": "{argument name="subject gender" default="female"}", "ethnicity": "{argument name="ethnicity" default="Scandinavian"}", "age_range": "{argument name="age range" default="mid 20s"}", "body_type": "athletic", "face": { "makeup": "no makeup", "skin": "natural texture, visible pores, frekles, slight redness, real-life imperfections", "expression": "calm, unfixed, almost blank" }, "hair": { "color": "{argument name="hair color" default="dark blonde"}", "style": "fallen forward, slightly messy from motion" } }, "wardrobe": { "outfit": "pilates wear", "color": "{argument name="outfit color" default="deep pink"}", "top": "fitted pink pilates crop top", "bottom": "high-waisted pink pilates shorts", "footwear": { "type": "high heels", "style": "minimal stiletto", "color": "pink" } }, "lighting": { "type": "clean white studio lighting", "color_temperature": "neutral white (5000–5600K)", "setup": "even top-front softbox lighting", "shadows": "very soft, realistic contact shadows only", "look": "clinical, honest, unstyled" }, "mood": "raw, accidental, intimate, fashion realism", "style": "unposed editorial photography", "negative_prompt": [ "beauty makeup", "glam lighting", "warm tones", "yellow light", "dramatic shadows", "plastic skin", "cgi", "posed look", "perfect face symmetry" ] }

@Prompt Ninja
GPT Image 1.5 World Tour Prompt Template
GPT Image 1.5

GPT Image 1.5 World Tour Prompt Template

GENERAL STYLE & MOOD: Photorealistic live concert documentary. Cinematic visual expression blending the fervor of the enthusiastic audience with the unique atmosphere and lighting specific to the location. SUBJECT: The character from the attached image is performing a 'World Tour' live performance at the specified latitude and longitude location. While completely preserving the character's identity, they are wearing a 'World Tour exclusive stage costume' that modernly arranges the culture, tradition, or symbolic elements of that land. COMPOSITION & STAGE DESIGN: The stage is a special venue that maximizes the use of the local landmarks, topography, or urban landscape. - Dynamic angle using a wide-angle lens (24mm equivalent). - Immersive framing, looking up at the stage over the audience. - Fusion of iconic local backgrounds (architecture, natural scenery) and the latest lighting technology (LED, laser). LIGHTING & ENVIRONMENT: - Natural light based on the local time of day ( {argument name="time of day" default="golden hour, or night"}) determined by latitude and longitude. - Coexistence of spotlights illuminating the stage and bokeh from local streetlights or night views. - A sea of light created by the audience's glow sticks and smartphone lights. PRESERVE FROM IMAGE: - The character's facial features, hairstyle, hair color, and physical characteristics. - The character's unique expressions and performance habits. CONSTRAINTS / DO NOT: - Do not distort the character's form. - Avoid unnatural finger shapes or duplication of limbs. - Ensure that text or logos on the stage are depicted extremely clearly, avoiding illegible random strings. - The background must not be a generic concert venue; it must incorporate a unique landscape that could only exist in that specific location. LOCATION SPECIFICATION: {argument name="latitude" default="-13.1631"} {argument name="longitude" default="-72.5450"}

@Maki@Sunwood AI Labs.
Image Editing Prompt: Adding Creatures to Background
GPT Image 1.5

Image Editing Prompt: Adding Creatures to Background

using the first image and its style and size, add the creature from the second image into the first at varying distances in the background, ensure the focus and size of the creatures is appropriate for its distance, there should be a total of {argument name="number of creatures" default="7"} of them, their look and style may vary slightly from one another

@Kyle Salazar
Testing Style Maintenance and Modification in GPT Image 1.5
GPT Image 1.5

Testing Style Maintenance and Modification in GPT Image 1.5

Request the state of singing and dancing on stage while maintaining the art style Request a change in art style (simplification such as color reduction and deformation, and a request to shift the color palette towards bright pastel tones) Change to a headset and make a heart shape with both hands, leaving the color arrangement to the AI

@眠い個人
Desert Ruins of Pure Math Grid
GPT Image 1.5

Desert Ruins of Pure Math Grid

Desert Ruins of Pure Math (Cairo-style monumental stone) A 2x2 grid of 4 monumental mathematical symbols built as ancient desert ruins in sandstone [Top Left: The Integral (∫) as a collapsed arch-aqueduct, wind-eroded blocks, carved microtext equations, tiny caravans for scale] [Top Right: The Sigma (Σ) as a stepped fortress-ziggurat with sharp terraces, long shadows, sand drifts collecting in corners] [Bottom Left: The Pi (π) as two colossal pylons and a lintel bridge over a narrow oasis canal, chipped stone, scattered rubble geometry] [Bottom Right: A Penrose Triangle as impossible ruins half-buried in dunes, optical illusion architecture, Escher perspective, sunlight slicing across paradox edges] Aerial oblique view, golden desert haze, crisp hard sunlight, dramatic shadows, photoreal ruins texture, subtle river ribbon, swiss 2x2 grid layout.

@Gadgetify
Ultra-Detailed 3D Graphite Pencil Sketch Generation
GPT Image 1.5

Ultra-Detailed 3D Graphite Pencil Sketch Generation

Generate an image from the uploaded photo that reimagines the subject as an ultra-detailed 3D graphite pencil sketch on textured white notebook paper. Emphasize crisp paper grain, subtle imperfections, and natural surface fibers. Show the subject actively drawing, with their hand holding a pencil as the sketch comes to life. Include an eraser, sharpener, and scattered pencil shavings resting on the page. Add realistic shadows, smudges, and fine graphite residue around the working area to reinforce the tactile, hand-drawn feel.

@ChatGPT

Some prompts are collected from creators on X. Copyright belongs to the original authors.