Phone Illustration
Create stunning smartphone and mobile device illustrations using our curated collection of AI prompts, from sleek modern designs to retro classics.
2026.07.04
·
Full-Body Flag Cheering Shot
GPT Image 2· Image
Use the uploaded person photo as the only identity anchor. Preserve the person's recognizable face shape, eyes, nose, lips, skin tone relationship, hairstyle impression, natural expression, and believable body proportions. Transform the photo into an authentic K-World Cup match-day stadium fan photo using these elements: real stadium seat rows, a green football pitch visible in the distance, metal railings, concrete stadium steps, red football jersey styling, Korean cheering props, casual 인증샷 mood, and realistic smartphone friend-shot photography. Keep the person as the clear main subject. Do not use any external reference images as input.
The person should stand between actual stadium seat rows or near a railing, framed as a full-body or three-quarter-body vertical portrait. Style them in a red football jersey with casual shorts, skirt, or denim. The person is holding a clearly visible, highly accurate South Korean national flag: white rectangular field, central red-over-blue Taegeuk circle, and four correct black trigrams placed in the four corners. The flag must look like a real fabric flag with natural folds, but the Taegeuk circle and four trigrams should remain recognizable and correctly arranged. The South Korean flag is allowed; avoid all other readable symbols, brand marks, official tournament emblems, sponsor logos, or text.
Style rules: not a studio editorial, not a trophy fantasy, and not a generic football poster. The image should feel like someone actually visited a real stadium during World Cup season before kickoff. Use natural daylight or stadium floodlights, candid phone-photo framing, realistic skin texture, realistic hands, shallow but believable depth of field, and a polished social-media finish. Preserve the person's identity strongly and do not redesign the face. No watermark, no extra people, no distorted hands, no extra fingers, no unreadable fake lettering.
Supermarket Couple Selfie Prompt
GPT Image 2· Image
[Person Assignment]
- First uploaded photo = Male
- Second uploaded photo = Female
[Top Priority Rule: Identity Preservation]
Use the uploaded photos as the absolute identity reference for both individuals.
Identity preservation is the highest priority.
Priority:
Face Identity > Clothing > Composition > Lighting > Atmosphere > Image Quality
Maintain exactly:
- Eye shape
- Nose shape
- Mouth shape
- Face shape
- Jawline
- Cheekbones
- Skin texture
- Natural skin features
- Age appearance
- Hairstyle
- Facial proportions
- Overall impression
- Expression characteristics
Do not alter:
- Facial structure
- Facial proportions
- Skin characteristics
- Natural asymmetry
- Unique identifying features
The final image must look like the exact same real people photographed in another moment of their lives.
Not AI-generated faces.
Not beautified versions.
Not stylized versions.
Face similarity: maximum possible.
[Shooting Scenario]
A real couple shopping together at a supermarket.
The woman is holding a smartphone and taking a casual front-camera selfie while standing beside a shopping cart.
The man stands naturally next to her with a comfortable and familiar distance.
The shopping cart contains realistic groceries such as vegetables, snacks, drinks, fruit, and daily necessities.
The image feels like a spontaneous photo taken during an ordinary shopping trip.
No posing for social media.
No influencer atmosphere.
Just a genuine everyday moment.
[Composition]
- Upper body framing
- Both faces clearly visible
- Faces positioned near the center of the frame
- Natural smartphone selfie angle
- Slightly imperfect composition
- Realistic handheld framing
[Expression]
- Both looking directly at the smartphone camera
- Warm and comfortable smiles
- Relaxed expressions
- Natural eye contact with camera
- Genuine couple atmosphere
Avoid:
- Exaggerated laughter
- Model-like posing
- Dramatic expressions
- Forced smiles
[Outfit]
Maintain the clothing from the original uploaded photos as closely as possible.
Do not change:
- Outfit style
- Colors
- Materials
- Fit
[Background]
Real supermarket interior.
Include:
- Grocery aisles
- Product shelves
- Shopping cart
- Store lighting
- Price tags and packaging softly visible in background
Background should feel authentic and lived-in, not staged.
[Lighting]
- Standard supermarket lighting
- Soft overhead indoor lights
- Realistic shadows
- No studio lighting
- No cinematic lighting
[Camera Characteristics]
Looks like a genuine smartphone selfie.
Include:
- Slight handheld imperfection
- Mild digital noise
- Natural smartphone processing
- Slight focus inconsistency
- Realistic lens characteristics
Avoid:
- HDR look
- Beauty filters
- Over-sharpening
- Unrealistic skin smoothing
- Advertisement quality retouching
- Fashion photoshoot appearance
[Final Goal]
An authentic everyday supermarket selfie of a real couple shopping together.
The image should feel like a casual photo saved in a phone gallery rather than a planned photoshoot.
Most importantly, preserve the exact facial identity and overall impression of both uploaded individuals while creating a believable real-life shopping moment.
Rose Wall Portrait
GPT Image 2· Image
Use the uploaded person as the identity anchor. Preserve the model's recognizable face shape, eyes, nose, lips, skin tone relationship, hairstyle impression, and natural expression. Transform the image into a trendy rose-themed social media portrait inspired by viral Instagram rose photo shoots. The person must remain the clear main subject, with the rose styling, props, and background redesigned around them. Keep it realistic, like a high-quality iPhone friend-shot or lightly retouched editorial SNS photo, not a 3D render.
Rose photo aesthetic: romantic close-up composition, lush roses as the main visual motif, soft dreamy light, shallow depth of field, gentle film grain, creamy skin tone, subtle beauty retouch, natural but polished makeup, glossy lips, softly defined eyes, healthy blush. Use real fresh roses with layered petals, visible stems or bouquet wrapping when relevant. Avoid plastic-looking flowers. No text, no watermark, no readable logo, no duplicate person, no distorted hands, no extra fingers, no melted roses.
Concept 2 — rose wall portrait. The model stands in front of a dense rose-covered wall or garden arch, with red, blush, and cream roses filling the background. Half-body vertical portrait, one hand lightly touching a rose stem near the shoulder, soft smile, natural friend-taken angle. Background is dreamy and slightly blurred while the face and nearest roses stay crisp.
Camera and output: vertical 4:5 or 9:16 social media portrait, realistic smartphone photography, soft bokeh, natural skin detail, high-resolution editorial yet candid feel.
City Street Rose Bouquet Snap
GPT Image 2· Image
Use the uploaded person as the identity anchor. Preserve the model's recognizable face shape, eyes, nose, lips, skin tone relationship, hairstyle impression, and natural expression. Transform the image into a trendy rose-themed social media portrait inspired by viral Instagram rose photo shoots. The person must remain the clear main subject, with the rose styling, props, and background redesigned around them. Keep it realistic, like a high-quality iPhone friend-shot or lightly retouched editorial SNS photo, not a 3D render.
Rose photo aesthetic: romantic close-up composition, lush roses as the main visual motif, soft dreamy light, shallow depth of field, gentle film grain, creamy skin tone, subtle beauty retouch, natural but polished makeup, glossy lips, softly defined eyes, healthy blush. Use real fresh roses with layered petals, visible stems or bouquet wrapping when relevant. Avoid plastic-looking flowers. No text, no watermark, no readable logo, no duplicate person, no distorted hands, no extra fingers, no melted roses.
Concept 5 — city street rose bouquet snap. The model walks on a stylish city street or café terrace holding a wrapped bouquet of roses, like a spontaneous birthday or date-day photo. Full-body or three-quarter body framing, motion in hair and skirt/jacket, rose bouquet prominent in the foreground. Bright overcast daylight, natural smartphone texture, stylish SNS lifestyle mood.
Camera and output: vertical 4:5 or 9:16 social media portrait, realistic smartphone photography, soft bokeh, natural skin detail, high-resolution editorial yet candid feel.
Rose Arch Full-Body Snap
GPT Image 2· Image
Use the uploaded model photo as the only identity anchor. Preserve the person's recognizable facial structure, eyes, nose, lips, skin tone relationship, hairstyle impression, and natural expression. Do not use any external image as input. Create a new original rose-themed SNS portrait inspired by trendy Instagram rose garden photos: lush rose walls, rose bushes, bright outdoor light, romantic life-shot poses, and fresh social-media retouch. The result should look like a realistic high-quality smartphone photo taken by a friend, not a 3D render or illustration.
Rose visual rules: real fresh roses with layered petals, vivid red roses mixed with blush pink and cream roses, natural green leaves, dense flower-wall or rose-garden background, soft daylight, shallow depth of field, creamy bokeh, clean realistic skin texture, natural polished makeup, subtle blush, glossy natural lips, stylish daily fashion. No text, no watermark, no readable logo, no duplicate person, no extra people, no distorted hands, no extra fingers, no plastic-looking flowers, no copied Instagram layout exactly.
Composition 3: vertical full-body or three-quarter-body snap under a rose arch or beside a rose-covered fence. Stylish casual outfit, one hand adjusting hair or sleeve, candid friend-shot angle, overflowing flowers in background.
Output: vertical 4:5 social media portrait, realistic iPhone photography, high detail, natural colors, believable rose garden environment.
City Bus Window Commute
GPT Image 2· Image
Create a square 1:1 realistic iPhone-style candid portrait photo in South Korea. Scene: inside a Seoul-style city bus, blue patterned fabric seats, hanging straps, Korean transit card reader shape near the entrance, blurred Seoul street outside the window, no readable signs. Subject: one Korean office worker in their early 30s, slightly tired eyes, natural skin texture, short neat hair, wearing a navy jacket and white shirt. Action: sitting by the window with wired earphones, looking outside, window reflection faintly overlapping the face. Composition: side close-up from the aisle, shoulder and face visible, square crop. Lighting: clean late afternoon window light, realistic bus interior color, balanced contrast, no haze. Avoid: Chinese bus interior, readable route numbers, film grain haze, fashion editorial pose, perfect symmetrical face.
Brunch Cafe with a Friend
GPT Image 2· Image
IMG_4180.HEIC, clean realistic iPhone photo of two Korean women at a small brunch table, square 1:1. Natural color, bright but believable cafe daylight, balanced contrast, crisp facial detail, true-to-life skin texture, subtle smartphone noise only. Fresh Instagram daily photo look without haze. iPhone 16 Pro, 24mm main camera, casual table-level angle. Main subject young Korean woman early 20s, natural pretty face, short face, slim V-jaw, bright double-lid eyes, soft rounded nose tip, defined lips, tiny freckle on cheek. Friend partly visible laughing beside her. Main subject has hush cut curtain bangs. Dusty rose satin blouse with soft directional sheen, relaxed fit. She looks into lens with playful eye-smile while lifting a fork; friend reaches for toast. Small plates, iced coffee condensation, wrinkled napkin, Seoul brunch cafe window. No text, no watermark, no 3D render. No studio lighting, no heavy makeup, no portrait mode blur, no washed-out gray cast, no heavy film grain.
Apple Watch Series 11 Luxury Poster
GPT Image 2· Image
Ultra-premium 4:5 vertical luxury campaign poster for Apple Watch Series 11, 8K cinematic product photography, Apple-grade luxury-tech minimalism, Nike-style billboard hierarchy. Deep cinematic gradient background in matte black, graphite, and emerald Apple-green, soft volumetric lighting, subtle flowing metallic ribbon curves, glossy reflections, premium atmospheric depth.
Three floating hyper-realistic Apple Watches arranged in a dynamic triangular premium composition:
- Main hero upper-right with dark green woven loop strap, Apple Activity Rings UI glowing vividly, elegant perspective tilt, ultra-sharp titanium edges, realistic sapphire crystal highlights
- Supporting center watch with dark navy sport band, incoming call interface visible, subtle cinematic rotation toward camera
- Foreground bottom-left watch with silver aluminum case and white woven strap, glowing heart-rate monitoring UI, dramatic premium lighting depth
Clean editorial luxury layout.
Top left:
White Apple logo
“MURPHY AI” in small uppercase bold sans-serif typography.
Main headline left-aligned in massive bold geometric sans:
“Stay Ahead.
Stay Connected.”
with “Stay Connected.” in rich Apple-green typography.
Subheadline:
“Health. Fitness. Connection.
All on your wrist.”
Top right:
“Apple Watch Series 11 • Built for a better you.”
Bottom section:
Three minimal Apple-style feature blocks with thin outline icons and clean hierarchy:
- Advanced health insights
- Smarter every day
- Stay connected
Bottom-left premium rounded CTA button:
“Explore Apple Watch”
thin neon-green outline, subtle green glow, circular arrow extension.
Tiny URL below:
“”
Luxury commercial studio lighting, soft overhead diffusion, cinematic edge reflections, realistic OLED glow response, soft shadows, premium anti-aliased typography, 85mm commercial product lens, Apple keynote realism, hyper-detailed textures, billboaed typography, 85mm commercial product lens, Apple keynote realism, hyper-detailed textures, billboard-ready composition.
STRICT PALETTE:
matte black, graphite, emerald green, matte white, cool gray, OLED activity-ring colors only.
Photorealistic.
Minimalist.
Expensive.
Editorial.
Award-winning luxury commercial advertising.
Library Study Table
GPT Image 2· Image
Square 1:1 realistic iPhone photo, clean quiet indoor lighting, balanced contrast. Scene: Korean public library reading table, wooden desks, book carts, fluorescent ceiling lights, blurred Korean book spines without readable text. Three people with very different appearances studying separately: Korean college woman with long braided hair, oval face, navy cardigan highlighting notes; Korean middle-aged man with shaved head, round glasses, brown sweater reading a thick book; Korean teenage boy with messy hair, pale blue hoodie, earphones, leaning over a notebook. Candid composition from across the table, no direct posing, calm everyday mood. Avoid: identical faces, classroom uniformity, Chinese/Japanese library signs, readable book titles, over-polished stock photo, haze, strong film grain.
Recycling Day Candid Snap
GPT Image 2· Image
Create a square 1:1 realistic iPhone-style candid portrait photo in South Korea. Scene: a Korean apartment complex recycling area in the late afternoon, with separate bins for paper boxes, transparent plastic bottles, and general recycling, Korean-style apartment buildings in the background, no readable text. Subject: one Korean woman in her late 20s, natural face with slight asymmetry, tied-back hair with a few loose strands, wearing a light beige cardigan over a white T-shirt and loose denim. Action: she is folding a cardboard box and looks up at the camera with a small embarrassed smile, one hand still on the box. Composition: slightly high angle, waist-up, casual snapshot framing, square crop. Lighting: clean natural daylight, balanced contrast, true-to-life skin texture, crisp facial detail, natural colors, subtle smartphone noise only. Avoid: Chinese-looking signs, Japanese street elements, readable brand names, foggy filter, washed-out gray cast, heavy film grain, glossy AI beauty look, overly perfect skin.
World Cup Broadcast Camera Reaction
GPT Image 2· Image
TEAM A: [대한민국]
TEAM B: [체코]
Transform this photo into an ultra-realistic FIFA World Cup 2026 live television broadcast crowd-camera shot.
Preserve the exact facial identity, facial structure, hairstyle, and natural features of the person in the original image.
Replace the original outfit entirely with an authentic football supporter outfit appropriate for attending a FIFA World Cup 2026 match.
The subject is wearing:
Official supporter jersey of [TEAM A]
Match-day supporter scarf
Small national flag accessories
Realistic football fan apparel
Authentic stadium supporter fashion
Do not preserve any original dress, stage outfit, glamour styling, celebrity fashion, eveningwear, or revealing clothing.
The subject is attending the FIFA World Cup 2026 match between:
[TEAM A] vs [TEAM B]
Current score:
[TEAM A] [SCORE A] - [SCORE B] [TEAM B]
Match clock:
[MINUTE]
Tournament stage:
[GROUP STAGE / ROUND OF 16 / QUARTER-FINAL / SEMI-FINAL / FINAL]
The subject has been unexpectedly captured by the live broadcast crowd camera during a crucial moment of the match.
No posing.
No direct eye contact with the camera.
Natural emotional reaction only.
Expression should show:
[EXCITEMENT / TENSION / SHOCK / RELIEF / ANTICIPATION]
Shot using a professional 400mm sports broadcast telephoto lens.
Authentic television framing.
Compressed stadium perspective.
Shallow depth of field.
Realistic focus falloff.
Natural skin texture.
Documentary-style realism.
Subtle broadcast compression artifacts.
Slight crowd motion blur.
The stadium is completely sold out.
Supporters of both nations fill the stands.
Flags, scarves, face paint, jerseys, and cheering fans surround the subject.
Powerful stadium floodlights illuminate the scene.
Include realistic live football broadcast graphics:
• FIFA World Cup 2026 branding
• Live scoreboard overlay
• Match clock showing [MINUTE]
• Team abbreviations and scoreline
• Tournament stage indicator
• Television network watermark
• Small player statistics graphic
• Authentic sports broadcast typography
Top-right corner graphic should read:
FIFA WORLD CUP 2026™
LIVE
The image should look exactly like a frame captured from a real international television broadcast watched by millions around the world.
The broadcast director intentionally cuts to this spectator because they have become a fan-favorite reaction shot during the match.
Authentic supporter fashion.
Natural stadium attire.
Reuters sports photography quality.
Getty Images sports photography quality.
Photorealistic.
Documentary realism.
Natural imperfections.
Cinematic sports color grading.
Ultra-realistic.
Hyper-detailed.
8K.
Viral World Cup crowd-camera moment.
Dog Mascot on the Pitch
GPT Image 2· Image
Use the uploaded dog photo as the only identity anchor. Preserve the dog's breed impression, fur color, face, eyes, muzzle, ears, grooming silhouette, and personality. Transform the photo into a realistic K-World-Cup match-day pet fan snapshot using these elements: real stadium seats or green pitch, red football jersey/bandana styling, Korean cheering props, casual cute 인증샷 feeling, premium smartphone pet photography. Keep the dog as the clear main subject. Do not use external reference images as input. No readable logos, no official emblems, no text, no watermark, no extra animals, no distorted paws.
Style rules: not a studio editorial, not trophy fantasy, not generic global football poster. It should feel like someone actually visited a stadium during World Cup season. Use red jersey or red fan outfit, white/blue accent props, Taegeukgi-inspired flag colors without readable symbols, stadium seating rows, railings, concrete steps, green pitch, daylight or stadium floodlights, candid phone-photo framing, natural skin/fur texture, shallow but believable depth of field, high-quality Instagram carousel look.
Dog on pitch edge with football. The dog sits or stands on green turf near the stadium sideline, wearing a tiny red jersey/scarf, a football placed beside the paws. Stadium seating and floodlights in the background, playful mascot-like mood but realistic, bright clean fur detail, candid low-angle pet photography, vertical social-media portrait.
What Are Phone Illustration AI Prompts?
Phone Illustration AI Prompts are specialized descriptive strings that act as creative blueprints for generative artificial intelligence. These prompts empower users to transform conceptual ideas into high-quality visual representations of mobile communication devices. In the contemporary digital landscape, a 'phone' can range from a minimalist glass rectangle to a complex, futuristic foldable device or even a nostalgic 1990s brick phone. These AI prompts are engineered to capture the specific aesthetic qualities of these objects: the way light refracts off a curved screen edge, the tactile appearance of a brushed metal frame, and the vibrant glow emitted by an OLED display. By leveraging Carat's advanced prompt library, designers and enthusiasts can generate assets that would traditionally require hours of 3D modeling or professional photography. The prompts handle everything from composition and lighting to the specific UI elements shown on the screen, providing a comprehensive toolkit for anyone looking to incorporate mobile technology into their visual storytelling.
Best Use Cases
The applications for phone illustrations are vast and varied, touching nearly every aspect of modern digital design. One of the most common uses is in UI/UX design mockups, where a stylized phone illustration provides a beautiful frame for displaying a new mobile app's interface. Marketing teams frequently use these illustrations for social media ads, website headers, and promotional banners to showcase mobile accessibility. For tech bloggers and content creators, AI-generated phone images serve as perfect thumbnails for YouTube videos or hero images for articles about mobile trends. Beyond commercial use, these illustrations are popular in the world of digital art and lifestyle content-think of a cozy desk setup illustration featuring a smartphone playing a lo-fi playlist, or a futuristic sci-fi scene where holographic phones are used by cyberpunk characters. The ability to customize the phone's color, model, and environment makes it an incredibly flexible asset for branding, allowing a company to align the device's look perfectly with its corporate identity.
Why This Tag Works
The Phone Illustration tag on Carat is uniquely effective because it simplifies the process of generating sleek, modern technology while maintaining high artistic standards. While a smartphone might seem like a simple object to render, achieving a 'premium' look-characterized by perfect reflections, clean lines, and balanced lighting-is notoriously difficult in AI generation without the right guidance. Our prompts include specific parameters that ensure the AI understands the material science of modern devices, such as the difference between matte finishes and high-gloss glass. Furthermore, this tag encourages artistic experimentation. Users can easily take a standard phone subject and apply a 'Retro 8-bit' style, a 'Vibrant Neon' palette, or a 'Soft Pastel Watercolor' aesthetic, creating something far more unique than a standard stock photo. The tag also ensures structural integrity, preventing the common AI issue of distorted proportions or nonsensical button placements. Whether you need a hyper-realistic render for a corporate presentation or a whimsical illustration for a children's book, this tag provides the reliable foundation needed for high-quality outputs every time.
Explore Related Prompts
Dive deeper into the world of digital art with these related tags that pair perfectly with phone illustrations.
Prompt Building Tips
To achieve professional-level phone illustrations, it's important to focus on the 'atmosphere' and 'interaction' of the device. Instead of just prompting for a 'smartphone', try describing the context: 'A smartphone resting on a marble nightstand, soft morning sunlight casting long shadows'. Mentioning specific screen contents can also add life to the image-use phrases like 'the screen displays a vibrant music player' or 'a futuristic map interface glowing in the dark'. To get a specific material feel, use terms like 'titanium frame', 'frosted glass back', or 'carbon fiber texture'. Lighting is another crucial element; 'cinematic rim lighting' can make a device pop against a dark background, while 'diffused studio lighting' is better for clean product shots. If you're going for a retro vibe, don't forget to include era-specific details like 'coiled telephone cord' or 'physical antenna'. Lastly, consider the camera angle: 'isobaric top-down view' is great for clean layouts, while a 'low-angle hero shot' makes the device look powerful and impressive. By layering these details, you can transform a basic prompt into a truly bespoke piece of digital art.
