Awesome GPT-Image-2 Prompts

This is a living collection of real GPT-Image-2 prompts shared by creators on Twitter (X). Each entry links back to the original post. The list grows as more prompts surface — check back regularly.

Data Visualization: Dual-Axis Chart

Shared by @maxescu

Here is a GPT-Image-2 prompt for the "Data Visualization: Dual-Axis Chart" example.

DOMAIN: "Crime, Safety & Justice"

HEADLINE: "Violent crime in the US has fallen 50% since 1993. Most Americans think it's at an all-time high."

Use Google Search to find: US violent crime rate trend 1990–today (FBI UCR/BJS NCVS data), percentage decline from 1993 peak to today, and Gallup polling data showing % of Americans who believe crime is increasing (consistently 60–70%+ even as crime falls). Cream #F7F3EC. Square.

HEADLINE: "Crime is down 50% since 1993. Most Americans think it's going up. Both true simultaneously."

SUBHEAD: "US VIOLENT CRIME RATE vs PUBLIC PERCEPTION · 1990–PRESENT · BJS/FBI + GALLUP"

CHART: Dual-axis diverging chart.

LINE A (electric blue): US violent crime rate per 100,000 — sharp peak 1991–1993, dramatic decline, near historic lows today.

LINE B (coral dashed): % of Americans saying crime is "up from last year" (Gallup) — stays high, barely reflects actual trend. The two lines diverge dramatically. Reality vs perception.

ANNOTATION: "The crime rate and the public's feeling about crime have almost no relationship."

SOURCE: "Bureau of Justice Statistics NCVS · FBI Uniform Crime Reports · Gallup Crime Poll"

Hyper-Detailed Urban Scene

Shared by @mark_k, result tested by @WolfRiccardo

Here is a GPT-Image-2 prompt for the "Hyper-Detailed Urban Scene" example.

A hyper-detailed photograph captured on a Canon EOS R5 DSLR camera, 24-105mm f/4L lens at 35mm, f/5.6 aperture, 1/250s shutter, ISO 400, golden-hour dusk lighting with soft lens flare and subtle chromatic aberration. Epic bustling Times Square-style metropolitan intersection teeming with chaotic urban life: over 150 diverse pedestrians of every ethnicity, age, and attire (business suits on phones, tourists with backpacks and maps, families pushing strollers, street dancers performing, elderly with canes, cyclists, joggers, vendors in aprons). Yellow taxis, electric buses, motorcycles, delivery scooters, and hovering drones weave through heavy traffic. Towering glass skyscrapers reflect the vibrant chaos; wet pavement from light rain glistens with perfect specular highlights and steam rising from manholes. Foreground newspaper kiosk overflows with papers headlined "BREAKING: GPT-Image-2 Redefines AI Art 2026" and magazines showing crisp covers. Multiple illuminated billboards and neon signs feature perfectly legible text: "Coca-Cola Zero", "Nike Air Max 2026", "Tesla Full Self-Driving", "Starbucks Reserve", "iPhone 17 Pro Max – Preorder Now", "NYC Marathon – Nov 2026", "Macy's 70% Off Flash Sale". A massive central 3D digital billboard prominently glows with bold futuristic lettering "GPT-Image-2". Shop windows display "OPEN 24/7 – Fresh Bagels", phone screens show social feeds, license plates read "AI-2026" and "PRO-MODE", traffic signs say "No Honking" and "Pedestrian Crossing". Pigeons scatter, hot-dog carts emit smoke, distant helicopter hovers.

Realistic Portrait: Detailed Flash Photography

Shared by @BubbleBrain

Here is a GPT-Image-2 prompt for the "Realistic Portrait: Detailed Flash Photography" example.

CCD compact camera direct on-camera flash, full-body portrait, eye-level straight-on shot, gorgeous Korean idol woman, early 20s, 9-head body proportion, standing in confident S-curve pose with weight on back leg, front leg slightly forward and bent at knee, elongating leg line, one hand forming finger-gun gesture pressed against temple, head tilted, sharp cold gaze directly into lens, lips slightly parted, expression reads effortless danger — sexy and unbothered, long jet-black pin-straight hair reaching lower back, silky texture with fine strand separation under flash, no bangs, hair tucked behind one ear revealing jawline, cold-toned porcelain skin with authentic texture — visible fine pores on cheeks and nose, soft peach fuzz on jawline and cheekbones catching light, subtle subsurface scattering at ear edges and nose tip, natural skin micro-texture with faint expression lines, matte healthy glow with zero oiliness or plastic sheen, cool-white undertone, no yellow cast, no tan, refined Korean makeup — clean elongated cat eyeliner, individual lash strands visible, groomed natural brows, soft nude-pink matte lip, subtle highlighter on nose bridge and cheekbone peaks, small beauty mark under left eye, black thin-strap deep-V camisole top, fitted, fabric clinging to torso sculpting slim waist and lifted bust, black high-waisted bodycon mini skirt ending mid-thigh, fabric hugging hip curves with visible tension at seams, bare long toned legs with realistic skin texture — faint knee definition, subtle muscle tone, natural skin color variation, black pointed-toe stiletto heels 10cm, direct on-camera flash lighting, hard light quality, properly exposed — skin detail fully preserved with no blowout, characteristic CCD flash contrast: subject crisp and bright, background falling off to deep shadow behind her, short hard shadow outline cast on wall directly behind, slight natural vignette at frame corners, CCD color rendition — punchy midtone contrast, slightly cool white balance from flash mixing with warm ambient, ultra-realistic skin detail under harsh direct light, every pore and fine hair strand rendered, fabric weave texture visible on black garments, metallic sheen on stiletto heel catching flash, hair strands individually lit with scattered micro-highlights, sharp critical focus on eyes and face, 8K UHD, RAW photograph, masterpiece, best quality, photorealistic, zero stylization, real human being

Fashion & Lifestyle: Pinterest-Style Outfit

Shared by @WolfRiccardo

Here is a GPT-Image-2 prompt for the "Fashion & Lifestyle: Pinterest-Style Outfit" example.

Ref: outfit/combo - Woman. Pinterest vibe - cool pose.
The woman should be wearing only one sleeve of her jacket, and she should be holding the bag with that same arm.

Makeup & Beauty: Two-Panel Comparison

Shared by @WolfRiccardo

Here is a GPT-Image-2 prompt for the "Makeup & Beauty: Two-Panel Comparison" example.

These tones should be present. The woman should have applied eyeshadow and eye makeup in these tones.

It should be a 2:3 aspect ratio. It should be a two-panel image. One portrait, one close-up of the face/eyes (eyes closed, focus on makeup).

Should be realistic RAW quality, in a home environment.

It should have realistic skin textures and tones. Realistic facial structure and detail. She should have finished her makeup with gloss. It should be an pinterest-style image. It should give off a social media/Pinterest vibe.

Cinematography Annotation

Shared by @VictorInFocus

GPT-Image-2 was used to analyze and annotate a Blade Runner film still — overlaying lighting, composition, lens, and blocking labels accurately onto the image.

Here is a GPT-Image-2 prompt for the "Cinematography Annotation" example.

Analyze this film still and annotate the shot. Overlay:
- lighting direction and quality
- composition rules used
- lens characteristics (focal length, depth of field)
- blocking and actor positioning

Place labels accurately on the image. Clean typography, cinematic analysis style.

Vintage Travel Poster Illustration

Shared by @WolfRiccardo

Here is a GPT-Image-2 prompt for the "Vintage Travel Poster Illustration" example.

Modern pencil illustration of Vintage travel poster illustration of the Amalfi Coast, Italy, panoramic coastal cliff road scene, classic 1960s white car driving along a curved seaside road, deep blue Mediterranean sea with small sailboats, colorful pastel hillside village, bright blue sky with soft clouds, lemon tree branches with vibrant yellow lemons framing the foreground, warm summer sunlight, bold vibrant colors, retro 1950s travel poster style, cinematic composition, high detail, screen print texture, graphic illustration. Hand-drawn style, illustration with loose strokes and defined contours. High-contrast color palette, maintaining chromatic harmony between background and elements. Contemporary and decorative aesthetic.

Simple Prompt, Great Game Cover

Shared by @mirochill

Here is a GPT-Image-2 prompt for the "Simple Prompt, Great Game Cover" example.

Cover switch game : Discord Mod Simulator

World Knowledge: Zelda + Real Train

Shared by @marmaduke091

Here is a GPT-Image-2 prompt for the "World Knowledge: Zelda + Real Train" example.

In the game Zelda TOTK, Link is in an E531 series train made by him

Analog Editorial Portrait With Direct Flash

Shared by @BubbleBrain

Here is a GPT-Image-2 prompt for the "Analog Editorial Portrait With Direct Flash" example.

Analog 35mm film photography, high-fashion editorial portrait with intense on-camera direct flash (CCD hard flash style), intimate low-angle POV shot from slightly below (仰拍, around +15° upward angle), emphasizing long legs and elegant hourglass body proportions, 4:3 vertical format, 3/4 body shot, early 20s Korean idol-type young woman with delicate refined features, slightly upturned almond-shaped fox eyes, small sharp jawline, flawless porcelain skin with cool ivory undertone and visible specular highlights from direct flash, soft coral blush, natural dusty rose lips slightly parted, long naturally wavy dark brown hair with loose strands framing the face, wearing a slightly tilted black police peaked cap with silver badge.

She wears a fitted, stylish policewoman-inspired outfit: black short-sleeved collared crop top with shiny silver buttons and epaulets, a shiny silver police badge pinned on the chest, a thin black necktie loosely hanging at the front, a wide black duty belt with a silver buckle and handcuffs at the side, and a short black pleated mini skirt. Black thigh-high stockings and white low-top canvas sneakers with loose lacing add a casual contrast.

Pose: a subtle S-curve stance with weight shifted to one leg, hips angled slightly toward the camera to enhance silhouette and leg length. One hand lightly touches the cap brim or rests near the waist, while the other hand is placed at the hip or near the belt. Head tilted slightly down with a confident, self-assured upward gaze through lashes directed at the viewer, expression poised, cool, and subtly playful rather than overtly seductive.

Harsh on-camera direct flash from front/slightly above creates strong catchlights, sharp shadows behind the subject, crisp highlights on skin, hair, badge, belt buckle, and fabric textures. Cold flash quality mixed with warm ambient window light, visible flash fall-off, Kodak Portra 400 film simulation pushed for strong analog character, warm peachy skin tones with flash highlights, subtle cyan shadows, prominent heavy analog film grain (strength 0.65, larger grain size), noticeable film halation around bright areas, strong natural vignette, slight underexposure for a raw intimate mood.

Ultra-realistic photorealistic film photography, edgy magazine editorial aesthetic, visible fabric texture and reflective metal details, delicate hair strands glowing from flash, natural skin texture with heavy film grain throughout, no plastic skin, no digital sharpness, no airbrushing, no watermark, no text, authentic 35mm film look with strong grain and flash artifacts, analog color grading.

Historical Social Media: Oda Nobunaga

Shared by @itnavi2022

Here is a GPT-Image-2 prompt for the "Historical Social Media: Oda Nobunaga" example.

織田信長のX投稿ページ(本能寺の変直前)を作成してください。

English meaning:

Here is another GPT-Image-2 prompt for the "Historical Social Media: Oda Nobunaga" example.

Create an X post page for Oda Nobunaga just before the Honno-ji Incident.

Historical Social Media: Sakamoto Ryoma

Shared by @itnavi2022

Here is a GPT-Image-2 prompt for the "Historical Social Media: Sakamoto Ryoma" example.

日本の将来について熱く語る坂本龍馬のX投稿ページを作成して。

English meaning:

Here is another GPT-Image-2 prompt for the "Historical Social Media: Sakamoto Ryoma" example.

Create an X post page where Sakamoto Ryoma passionately talks about the future of Japan.

Concept Product Design: Seamless Jacket

Shared by @SRKDAN

Here is a GPT-Image-2 prompt for the "Concept Product Design: Seamless Jacket" example.

A jacket with no zip, no buttons, no fastening — closes perfectly.

Concept Product Design: Crownless Watch

Shared by @SRKDAN

Here is a GPT-Image-2 prompt for the "Concept Product Design: Crownless Watch" example.

A watch with no crown, no buttons — a sealed case that sets itself.

Concept Product Design: Seamless Wallet

Shared by @SRKDAN

Here is a GPT-Image-2 prompt for the "Concept Product Design: Seamless Wallet" example.

A leather wallet with no stitching, no clasp, no visible opening.

World Knowledge and Photorealism

Shared by @levelsio

Here is a GPT-Image-2 prompt for the "World Knowledge and Photorealism" example.

Create a four-image capability showcase:
1. A full-body human anatomy poster titled "Human Anatomy - Anterior View", split between muscles, bones, organs, arteries, veins, and nerves, with dense readable medical labels and a legend.
2. A detailed physical world map poster with oceans, countries, terrain relief, compass rose, scale, and small data tables along the bottom.
3. A realistic photo of a closed Bath & Body Works storefront seen through glass doors, with a printed sign saying the store is closed for the evening.
4. A dark-mode YouTube homepage screenshot with realistic video thumbnails, sidebar navigation, channel names, view counts, and readable UI text.
Make every label and interface element sharp, aligned, and believable.

Handwritten Medical Notes

Shared by @mark_k

Here is a GPT-Image-2 prompt for the "Handwritten Medical Notes" example.

Create a realistic photo of a doctor's handwritten clinical note on lined spiral notebook paper. Use blue ballpoint pen handwriting with abbreviated sections such as HPI, PE, A/P, vitals, dates, and medication notes. The page should look casually written during a real medical visit, with uneven spacing, natural ink pressure, and a signature at the bottom.

Visual Reasoning and Structured Thinking

Shared by @daniel_mac8

Here is a GPT-Image-2 prompt for the "Visual Reasoning and Structured Thinking" example.

Create a scanned school worksheet titled "Distance and Displacement" for a student named John Doe. Include printed physics questions, a baseball diamond diagram, a running silhouette, tables for distance and displacement, multiple-choice answers, and handwritten student responses in pencil. Make the worksheet look like a real completed classroom assignment with accurate layout and readable writing.

Comic Layout With Accurate Text

Shared by @itnavi2022

Here is a GPT-Image-2 prompt for the "Comic Layout With Accurate Text" example.

Draw a one-page manga with 8 panels. The main character is a chibi girl named Lisa with twin tails and a black gothic dress. She is explaining the new image generation model GPT-Image-2. Every speech bubble should contain accurate Japanese characters and readable dialogue. Keep the page clean, expressive, cute, and easy to follow.

Labeled Knowledge and Educational Graphics

Shared by @TrungTPhan

Here is a GPT-Image-2 prompt for the "Labeled Knowledge and Educational Graphics" example.

Create a four-image capability test for GPT-Image-2:
1. A Grand Theft Auto-style rainy nighttime scene in Hong Kong with neon Chinese signage, wet streets, a black sports car, minimap UI, subtitles, button prompts, and readable location text.
2. A Minecraft-style raid scene at night with TNT explosions, armored players, HUD hearts, inventory bar, chat messages, faction statistics, and a raid timer.
3. A typography accuracy test that places alphabet letters correctly in sequence.
Each panel should be visually distinct, highly legible, and compositionally polished.

Game Concept Art and Genre Fusion

Shared by @nicdunz

Here is a GPT-Image-2 prompt for the "Game Concept Art and Genre Fusion" example.

Create a videogame key art image titled "Doom in the Backrooms." Blend the oppressive fluorescent liminal-horror look of endless yellow office corridors with the heavy-action energy of a classic demon shooter. Cinematic perspective, eerie empty space, aggressive mood, realistic lighting, game-cover composition.

Model Upgrade Comparison

Shared by @AngryTomtweets

The original tweet compares GPT-Image-1.5 and GPT-Image-2 side by side to show how much image quality improved in one generation.

Photorealistic Social and Travel Photos

Shared by @Hesamation

Here is a GPT-Image-2 prompt for the "Photorealistic Social and Travel Photos" example.

Create two realistic travel photos:
1. A sunny beach selfie of three young friends in swimwear, smiling close to the camera, with ocean waves, sand, cliffs, palm trees, sunglasses, and harsh midday sunlight.
2. A moody travel portrait of a young woman walking beside a wire fence on green coastal cliffs, with cloudy skies, distant houses, ocean water, and a natural Irish countryside atmosphere.
Make both images feel like authentic phone or travel-camera photos with believable skin, lighting, and background depth.

Chinese Text Rendering

Shared by @xiaohu

The tweet highlights GPT-Image-2's Chinese text rendering quality.

Interface and Infographic Clarity

Shared by @super_bonochin

Here is a GPT-Image-2 prompt for the "Interface and Infographic Clarity" example.

Design a Japanese educational infographic titled "ChatGPTで画像を作るコツ" for an OpenAI Academy-style slide. Use four numbered columns with colorful headers, icons, checkmarks, Japanese bullet points, prompt examples along the bottom, and a simple workflow diagram. Keep the layout clean, readable, and presentation-ready.

Side-by-Side Model Comparison

Shared by @itnavi2022

The tweet compares a GPT-Image-2 candidate model against NanoBanana 2 side by side.

Image Quality at Zoom Level

Shared by @mark_k

The tweet is useful because it shows a real limitation: GPT-Image-2 can look great at normal viewing size but still break down in fine details when you zoom in.

Cinematic Driving Close-Up

Shared by @synthwavedd

Here is a GPT-Image-2 prompt for the "Cinematic Driving Close-Up" example.

Create a cinematic close-up shot of a bald man driving a car, seen through the windshield. He has a serious expression, one hand on the steering wheel, warm sunlight and shadow bands across his face, realistic car interior fabric, shallow depth of field, and a gritty film still look.

Anime and Character Scene Rendering

Shared by @studio_oneroom

Here is a GPT-Image-2 prompt for the "Anime and Character Scene Rendering" example.

Create an anime-style key visual with a detailed character in the foreground, a rich illustrated background, polished lighting, readable embedded text, and strong harmony between character art and environment design. High detail, clean linework, vibrant but balanced colors, polished poster-like finish.

Realistic Travel and Vacation Photos

Shared by @PurzBeats

Here is a GPT-Image-2 prompt for the "Realistic Travel and Vacation Photos" example.

Create a realistic close-up vacation selfie of a heavyset middle-aged man with short gray hair and a gray beard, making an excited wide-eyed expression from a hotel balcony in Hawaii. Show palm trees, high-rise buildings, blue sky, and bright daylight in the background. Make it feel like an authentic phone selfie.

Minecraft-Style Brand Environment

Shared by @BLCNYY

Here is a GPT-Image-2 prompt for the "Minecraft-Style Brand Environment" example.

Create a Minecraft-style first-person screenshot inside "Claude Headquarters." Show blocky office architecture, the Claude logo on the wall, a desk with a confidential document, and a held paper titled "Internal Document: Claude Opus 5" listing next-generation model features. Include Minecraft HUD elements, inventory bar, chat text, pixelated lighting, and readable document typography.

Character Makeover and Meme Images

Shared by @marmaduke091

Here is a GPT-Image-2 prompt for the "Character Makeover and Meme Images" example.

Create an anime fantasy character poster of MrBeast reimagined as a dark armored demon warrior. Show a confident male hero with a recognizable face, black-and-blue spiked armor, exposed torso, dramatic low-angle pose, glowing blue demonic creature behind him, vivid magenta and blue lighting, and readable "MR BEAST" text on a banner in the background.

Branded Satire and Corporate Mashups

Shared by @stark_nico99

Here is a GPT-Image-2 prompt for the "Branded Satire and Corporate Mashups" example.

YouMind 收购了 ChatGPT 的图

Same Prompt, Better Realism

Shared by @phasE89

Here is a GPT-Image-2 prompt for the "Same Prompt, Better Realism" example.

Amatérská fotka staršího páru sedícího v yorkshirské hospodě, amatérská kompozice, momentka.

Mixed Style Text and Character Tests

Shared by @itnavi2022

Here is a GPT-Image-2 prompt for the "Mixed Style Text and Character Tests" example.

Create a four-image test set for text, realism, and character rendering:
1. A realistic newspaper on a cafe table with the headline "OpenAI Unveils GPT-Image-2", columns of readable article text, coffee, glasses, water, pastry, and a pen.
2. A Japanese TV weather broadcast screenshot from Shibuya at 6:45, with live-news overlays, weather icons, temperature, humidity, wind speed, and readable Japanese captions.
3. A photorealistic cat-ear maid cosplayer eating soft-serve ice cream on the Spanish Steps in Rome, with tourists and architecture in the background.
4. A clean anime illustration of a cheerful twin-tail gothic girl waving, with a speech bubble saying "Hi!".

GPT-Image-1.5 Versus GPT-Image-2 in Illustration Quality

Shared by @itnavi2022

The original tweet compares two outputs and asks viewers to identify which one was generated by GPT-Image-2.

Prompting for Complex Religious Text on Objects

Shared by @TlanoAI

Original idea from the tweet:

Here is a GPT-Image-2 prompt for the "Prompting for Complex Religious Text on Objects" example.

般若心経が書かれたバナナ

Comparison Against Nano Banana Pro

Shared by @thefinnmckenty

The tweet compares GPT-Image-2 against Nano Banana Pro using the same all-American stunt-show idea, with a motorcycle jump, explosions, arena lighting, and American flag screens.

This list is updated regularly. If you have a prompt you want added, share it on Twitter and tag it with GPT-Image-2.

Sci-Fi Movie Poster With Japanese Typography

Shared by @studio_oneroom

Here is a GPT-Image-2 prompt for the "Sci-Fi Movie Poster With Japanese Typography" example.

画像生成には必ず最新のモデル GPT-image-2を使ってください

添付１の背景を添付２の画像に変えて その際にうまく馴染むように構図やライティングを整えて映画のポスター風にしてください

タイトル：アルゴディアス
キャプション： 2046年、ドル崩壊でアメリカが覇権を失い、世界は欧州防衛機構（EDA）と南半球資源同盟（SRA）に二分された。太平洋の制海権を巡る戦火はニュージーランドに達し、ウェリントン基地がEDA最前線となる。戦況が膠着する中、中立を掲げる技術大国・日本が戦局を覆す新型機動兵器「アルゴディアス」を極秘開発。その兵器が間もなくウェリントンに配備されるという...

Everyday Lifestyle Realism

Shared by @WolfRiccardo

Here is a GPT-Image-2 prompt for the "Everyday Lifestyle Realism" example.

1. A candid apartment doorway photo of a young woman in a simple black dress holding a small decorated birthday cake, shot with direct flash, realistic skin texture, casual home lighting, slightly messy interior, authentic smartphone photo look.

2. A warm indoor lifestyle portrait of a young woman sitting on a sofa in a black top and white skirt, looking at her phone, soft evening light, natural pose, cozy apartment background, photorealistic smartphone snapshot.

3. A live concert crowd photo of a female singer on stage under purple and pink lights, audience hands raised in the foreground, realistic arena lighting, motion and depth, captured like an iPhone concert photo.

4. A bright luxury poolside vacation photo of a woman in sunglasses relaxing beside a turquoise swimming pool, summer resort atmosphere, striped towel, palm shadows, glossy travel photography style.

POV and First-Person Angles

Shared by @WolfRiccardo

Here is a GPT-Image-2 prompt for the "POV and First-Person Angles" example.

1. First-person view from the driver's seat of a Tesla at a red light in a modern city, hands on the steering wheel, dashboard screen visible, realistic windshield reflections, natural daylight, smartphone photo realism.

2. Police bodycam-style night scene during a traffic stop, first-person perspective, one officer in frame, headlights and streetlights reflecting on wet pavement, gritty realism, documentary look.

3. First-person mountain biking shot on a narrow dirt trail through a green forest, handlebars visible, dynamic motion blur, sunlight through trees, action camera realism.

4. First-person view at a convenience store checkout counter, cashier and customers looking toward the camera, snack shelves and refrigerators in the background, fluorescent store lighting, believable candid photo style.

Human Anatomy Teaching Poster

Shared by @drkeithsiau

Here is a GPT-Image-2 prompt for the "Human Anatomy Teaching Poster" example.

Create a clean medical teaching poster showing the anterior view of human anatomy. Include readable labels for major muscles, bones, organs, arteries, and veins. Use a neutral background, textbook layout, accurate proportions, and crisp educational diagram styling.

Anime Mecha Concept Sheet

Shared by @old_pgmrs_will

Here is a GPT-Image-2 prompt for the "Anime Mecha Concept Sheet" example.

Create a concept sheet for a next-generation anime protagonist mecha. Show a towering black-and-silver robot with glowing accents, multiple technical callouts, front and side details, weapon notes, small pilot references, and polished industrial design presentation on a dark studio background.

Rough Colored-Pencil Plant Study

Shared by @Masimo_Blue

Here is a GPT-Image-2 prompt for the "Rough Colored-Pencil Plant Study" example.

Create rough colored-pencil concept sketches of a small potted seedling with simple gardening hardware nearby. Keep the lines uneven, the coloring loose, and the overall drawing slightly amateur and natural rather than polished or perfect.

Jewel-Toned Mermaid Fantasy

Shared by @NeneneAI

Here is a GPT-Image-2 prompt for the "Jewel-Toned Mermaid Fantasy" example.

Create a luminous fantasy illustration of a pink-haired mermaid princess swimming through an underwater palace filled with glowing crystals, pearls, gold ornaments, and floating bubbles. Use rich jewel tones, sparkling water caustics, elegant dress-like fins, and a magical storybook atmosphere.

Japanese Magazine Cover Layout

Shared by @old_pgmrs_will

Here is a GPT-Image-2 prompt for the "Japanese Magazine Cover Layout" example.

Design a bold Japanese magazine cover packed with readable headlines, subheads, badges, and editorial callouts. Center the layout around a festive New Year special theme with a confident host portrait, bright red-and-gold accents, and dense, realistic print-magazine typography.

Anime Suit Portrait

Shared by @mirochill

Here is a GPT-Image-2 prompt for the "Anime Suit Portrait" example.

Create a stylish anime portrait of a young man in a charcoal suit and tie, leaning back in a chair with one leg crossed. Use a low camera angle, soft office lighting, clean modern background, polished hair, and a calm confident expression.

Floating Fantasy City at Dusk

Shared by @old_pgmrs_will

Here is a GPT-Image-2 prompt for the "Floating Fantasy City at Dusk" example.

Create an epic fantasy city floating high above the clouds at dusk. Show glowing bridges, layered towers, hanging gardens, waterfalls dropping into the sky, and warm sunset light breaking through dramatic clouds. Make it feel like a grand matte painting for a fantasy film.

Japanese Infographic Before-and-After

Shared by @takuto_pitaliy

The tweet compares an older result with an updated GPT-Image-2-style result using the same prompt.

Here is a GPT-Image-2 prompt for the "Japanese Infographic Before-and-After" example.

Create a Japanese infographic poster that explains how to identify fever symptoms in children. Use a cute character illustration, a warm clinic-friendly color palette, clear section blocks, temperature callouts, and dense but readable Japanese text.

Realistic Engineer's Screen

Shared by @CuriousRefuge

Here is a GPT-Image-2 prompt for the "Realistic Engineer's Screen" example.

average engineer's screen

English and Japanese UI Rendering Test

Shared by @itnavi2022

Here is a GPT-Image-2 prompt for the "English and Japanese UI Rendering Test" example.

Create two side-by-side web page mockups for a text rendering test. One version should use English UI text and the other should use Japanese UI text. Keep the layouts similar, make the typography readable, and present both like polished website screenshots.

Battle Royale Lobby Screenshot

Shared by @SuguruKun_ai

Here is a GPT-Image-2 prompt for the "Battle Royale Lobby Screenshot" example.

Create a realistic battle royale lobby screenshot with four recognizable tech leaders standing side by side as playable characters. Include a polished game interface, party status panels, buttons, rank badges, and bright background lighting that feels like a live multiplayer game menu.

Weapon Skin Mockup in First Person

Shared by @WolfRiccardo

Here is a GPT-Image-2 prompt for the "Weapon Skin Mockup in First Person" example.

Create a first-person shooter weapon skin mockup shown from the player's hands. The rifle should have a playful pink-and-blue custom finish with sticker details, polished highlights, and a clean game-inventory presentation style.

Real-World Documents and Packaging

Shared by @mark_k

Here is a GPT-Image-2 prompt for the "Real-World Documents and Packaging" example.

1. Create a realistic printed medical intake form filled out by hand on a clipboard, with believable signatures, checkboxes, notes, and pen pressure variations. Keep the paper texture and lighting natural like a phone snapshot.

2. Create a realistic geological borehole log sheet with soil layers, handwritten field notes, measurements, chart markings, and engineering annotations on worn paper.

3. Design a cereal box package for "Corn Flakes" with a believable supermarket-brand layout, nutrition panel, cheerful mascot, and crisp readable packaging text.

4. Create a casual smartphone selfie of Barack Obama and Donald Trump together indoors, smiling toward the camera, with realistic skin, lighting, and social-media snapshot framing.

Manga-Style Japanese Explainer Panel

Shared by @itnavi2022

Here is a GPT-Image-2 prompt for the "Manga-Style Japanese Explainer Panel" example.

Create a manga-style Japanese explainer panel about testing a new AI image model. Use bold headline text, speech bubbles, side notes, and a smartphone screen insert. The layout should feel like a social media tutorial image with readable Japanese typography.

Product Launch Keynote Satire

Shared by @yousefrol

Here is a GPT-Image-2 prompt for the "Product Launch Keynote Satire" example.

Create a satirical Apple-style keynote slide introducing a strange new device. Show a presenter on stage, a giant product render behind them, dramatic presentation lighting, minimalist branding, and clean readable event text like a real launch announcement.

Composite Scene From Multiple References

Shared by @studio_oneroom

Here is a GPT-Image-2 prompt for the "Composite Scene From Multiple References" example.

添付１の背景を添付２の画像に変えて その際にうまく馴染むように構図やライティングを整えて自然な一枚絵にしてください

The tweet shows the generated image alongside the two source references.

GTA-Style Cinematic Game Screenshots

Shared by @marmaduke091

Here is a GPT-Image-2 prompt for the "GTA-Style Cinematic Game Screenshots" example.

Create cinematic screenshots from a fictional open-world crime game set in a bright coastal city. Show realistic characters, beachside streets, driving scenes, dialogue subtitles, warm sunset light, and a polished in-game HUD that feels like a modern AAA console game.

Lucia and Jason Game Screenshot

Shared by @GTAInfinity_YT

Here is a GPT-Image-2 prompt for the "Lucia and Jason Game Screenshot" example.

a screenshot from gta 6 with lucia and jason

The thread also includes a no-HUD version of the same idea.

Jason Walking in Leonida Keys

Shared by @GTAInfinity_YT

Here is a GPT-Image-2 prompt for the "Jason Walking in Leonida Keys" example.

a screenshot from gta 6 with Jason walking in leonida keys

Mechanical Keyboard Design Grid

Shared by @TanShilong

Here is a GPT-Image-2 prompt for the "Mechanical Keyboard Design Grid" example.

一个九宫格图片，展现九位当代知名设计师设计的同一组物体：机械键盘，包括设计师头像，设计师对于设计的中文文字解读和作品呈现。排版统一规则

Basketball Court Flash Portrait

Shared by @BubbleBrain

Here is a GPT-Image-2 prompt for the "Basketball Court Flash Portrait" example.

35mm color film photography with harsh direct on-camera flash, specular highlights on skin and clothing, strong catchlights in eyes, high contrast flash illumination, authentic film grain and color shift, high fashion fresh innocent basketball court editorial style, intimate first-person low-angle POV shot from below, early 20s sexy Chinese female idol with ultra-realistic delicate refined Chinese features, seductive almond-shaped fox eyes with natural double eyelids, high nose bridge, small sharp V-shaped jawline, flawless realistic porcelain skin with cool ivory undertone and visible flash specular highlights, fine delicate skin texture with subtle pores micro details and natural dewy glow under flash, fresh natural sporty makeup with soft dewy glow, subtle natural flush on cheeks, natural pink lips slightly parted, subtle natural freckles across nose and cheeks, long dark brown hair tied in a high playful ponytail with some loose strands framing the face and realistic loose strands, wearing a loose white tank top and white high-waisted basketball shorts, white knee-high sports socks, seductive natural leaning pose against the basketball hoop pole on the outdoor court at dusk, body angled sideways with naturally arched back and hips gently pushed back to accentuate perky round hips and sexy butt curve, one leg naturally extended forward toward the camera and the other leg slightly bent to emphasize long sexy legs, both hands lightly resting on the basketball pole at shoulder height, intensely seductive playful yet pitiable doe-eyed gaze straight at the viewer with soft vulnerable longing eyes and a gentle teasing smile full of quiet temptation and desire, harsh direct on-camera flash creating sharp specular highlights and strong catchlights, background with blurred basketball court and hoop under dusk sky, high contrast film color grading with natural flash look, extremely sharp yet soft skin rendering with authentic 35mm direct flash aesthetic, natural hair strands, realistic fabric texture on tank top and shorts with socks detail, no plastic skin, no digital over-sharpening, no airbrushing, no blemishes, no moles, no oily skin, no watermark, no text, authentic 35mm direct flash film basketball court look --ar 9:16

Old Game Character Sheet

Shared by @os_orabi

Here is a GPT-Image-2 prompt for the "Old Game Character Sheet" example.

Turn this single reference image of an old game character into a complete production-ready character sheet. Include front, side, and back views, facial expressions, close-up head details, accessories, material notes, weapon references, and a clean layout suitable for 3D modeling or concept art.

The tweet shows the generated character sheet with the original game reference.

Catalog Outfit Street Style

Shared by @VORTEX_Promos

Here is a GPT-Image-2 prompt for the "Catalog Outfit Street Style" example.

street style shot of a woman in this outfit.

Onsen Ryokan Film Portrait

Shared by @BubbleBrain

Here is a GPT-Image-2 prompt for the "Onsen Ryokan Film Portrait" example.

35mm film photography, warm vintage Japanese onsen ryokan aesthetic, soft ambient wooden lantern lighting mixed with gentle natural window light, subtle film grain, gentle color shift, high atmosphere editorial style, intimate medium shot, early 20s beautiful Chinese female idol with ultra-realistic delicate refined Chinese features, seductive almond-shaped fox eyes with natural double eyelids, high nose bridge, small sharp V-shaped jawline, flawless porcelain skin with warm ivory undertone, visible subtle skin texture and micro pores, soft natural makeup with dewy glow, subtle rosy flush on cheeks, natural soft pink lips slightly parted, long dark brown hair tied in a loose low bun with some messy strands falling around face and neck, wearing a loose white yukata (traditional Japanese bathrobe) deliberately slipped off one shoulder and loosely tied at the waist, the fabric slightly open revealing smooth skin and subtle cleavage, barefoot, seductive relaxed sitting pose on the edge of a traditional wooden engawa veranda at a vintage onsen ryokan, body slightly turned toward the camera, one leg bent with foot resting on the wooden floor, the other leg gently dangling, one hand lightly holding the yukata collar, the other hand resting on the wooden floor behind her for support, softly arched back to gently accentuate curves, intensely seductive yet gentle and inviting gaze straight at the viewer with soft doe eyes full of quiet temptation and warmth, warm wooden interior with paper sliding doors and distant steaming hot spring in soft focus, gentle rim lighting highlighting skin and fabric texture, authentic vintage film color grading with warm tones, extremely sharp yet soft skin rendering, natural hair strands, realistic fabric wrinkles and drape on the yukata, no plastic skin, no digital over-sharpening, no airbrushing, no blemishes, no moles, no oily skin, no watermark, no text, authentic 35mm film Japanese onsen ryokan atmosphere

SaaS Homepage and Pricing Flow

Shared by @qiufenghyf

Here is a GPT-Image-2 prompt for the "SaaS Homepage and Pricing Flow" example.

modern SaaS website homepage, figma style, clean navigation bar, hero section with floating prompt input UI, rounded card, soft shadow, minimal design

background filled with colorful creative design boards, portfolio layouts, typography posters, UI mockups, grid composition

centered composition, elegant spacing, premium UI design, soft lighting, subtle depth, product landing page, 8k, ultra clean

The tweet shows the model continuing from a homepage into pricing and feature pages.

Late-Night Convenience Store Portrait

Shared by @BubbleBrain

Here is a GPT-Image-2 prompt for the "Late-Night Convenience Store Portrait" example.

35mm film photography with harsh convenience store fluorescent lighting mixed with colorful neon signs from outside, authentic film grain, high contrast, slight color cast, cinematic street editorial style, intimate medium shot, early 20s sexy Chinese female idol with ultra-realistic delicate refined Chinese features, seductive almond-shaped fox eyes with natural double eyelids, high nose bridge, small sharp V-shaped jawline, flawless porcelain skin with cool ivory undertone and visible specular highlights from fluorescent light, subtle skin texture and micro pores, natural dewy makeup with soft flush on cheeks, glossy natural pink lips slightly parted, subtle natural freckles across nose and cheeks, long dark brown hair in a messy high ponytail with many loose strands falling around face and neck, wearing an oversized white button-up shirt as the only top, unbuttoned at the top with deep cleavage and loosely tied at the waist, paired with a tiny black pleated mini skirt, barefoot in simple white slides, seductive casual leaning pose against the glass door of a 24-hour convenience store at late night, body slightly arched, one leg bent with foot resting against the door frame, the other leg straight, one hand holding a bottle of iced drink, the other hand lightly pulling the hem of her mini skirt, intensely seductive playful yet slightly vulnerable gaze straight at the viewer with soft doe eyes full of quiet temptation and teasing smile, bright cold fluorescent store light from inside mixed with pink and blue neon glow from outside signs, realistic reflections on glass door, blurred convenience store interior with shelves and snacks in background, authentic 35mm film color grading with harsh lighting and neon accents, extremely sharp yet soft skin rendering, natural hair strands, realistic fabric wrinkles and drape on the oversized shirt and mini skirt, no plastic skin, no digital over-sharpening, no airbrushing, no blemishes, no moles, no oily skin, no watermark, no text, authentic late-night convenience store atmosphere

White Studio Tennis Portrait

Shared by @BubbleBrain

Here is a GPT-Image-2 prompt for the "White Studio Tennis Portrait" example.

Professional studio fashion photography, ultra-clean high-end digital editorial portrait in a pure white seamless cyclorama photography studio, massive soft octabox key light + large softbox fill light creating flawless even illumination with gentle sculpting shadows, Vogue-level minimalist high fashion aesthetic, eye-level shot, 3/4 body shot, early 20s Korean idol-type young woman with ultra-realistic delicate refined Korean features, slightly upturned almond-shaped fox eyes with natural double eyelids, small sharp jawline, flawless yet realistic porcelain skin with cool ivory undertone, completely natural post-workout no-makeup look, soft natural flush on cheeks, subtle dewy skin glow from light sweat, natural dusty rose lips slightly parted, subtle natural freckles across nose and cheeks, visible subtle skin texture, pores and micro skin details, long naturally wavy dark brown hair slightly messy with realistic loose strands, wearing a white fitted tennis polo or short-sleeve athletic top and a high-waisted white tennis skirt, standing naturally in the center of the pure white studio, holding a white tennis racket casually resting on one shoulder, the other hand relaxed at her side or lightly on her hip, one leg slightly forward, posture natural and confident, looking directly at the viewer at eye level with a calm, confident and fresh expression, pure soft professional studio lighting with large diffused sources, flawless even illumination, gentle sculpting shadows that naturally define the figure, clean high-key minimalist aesthetic, ultra-clean high-end digital photography, extremely sharp yet soft skin rendering with natural dewy glow, no film grain, no noise, no halation, no vignette, perfect neutral color grading, authentic Korean idol studio editorial aesthetic, visible realistic tennis racket texture, natural skin texture with freckles and subtle sweat sheen, no plastic skin, no digital over-sharpening, no airbrushing, no watermark, no text --ar 9:16

Spring 2026 Boston City Poster

Shared by @BubbleBrain

Here is a GPT-Image-2 prompt for the "Spring 2026 Boston City Poster" example.

A striking Spring 2026 city poster for Boston with an elegant celebratory mood and a bold contemporary design. On a clean off-white textured background with large areas of negative space, a miniature single sculler rows across the lower right corner of the image on a narrow ribbon of reflective water. The wake from the oar sweeps upward in a dynamic calligraphic curve, gradually transforming into the Charles River and then into a dreamlike hand-painted panorama of Boston. Inside this flowing river-shaped composition are iconic Boston elements: the Back Bay skyline, Beacon Hill brownstones, Acorn Street, Boston Public Garden, Swan Boats, Zakim Bridge, Fenway-inspired details, historic brick architecture, harbor ferries, and the city’s waterfront atmosphere. Soft morning fog, golden spring light, subtle festive accents in crimson and gold, rich detail, layered depth, sophisticated city-poster aesthetics, fresh and refined, visually powerful but not overcrowded. Elegant typography in the lower left reads “SPRING 2026” with a vertical slogan “BOSTON, A CITY OF RIVER, MEMORY, AND INVENTION”, text clear and beautifully composed, premium graphic design, 9:16

Shituoling Fantasy Scene Comparison

Shared by @MANISH1027512

This tweet compares MJ v8.1 and GPT Image 2 on the same fantasy scene prompt. The original post does not label which image is which, so the images are kept as a side-by-side comparison without assigning model names to the order.

中式怪异，黑暗神秘风格融合中式美学，完美细节，多重管线渲染，完美建模。西游记背景，狮驼岭，千妖万怪，坐在左边巨大王座上的大象王重甲妖精，坐在中间巨大王座上的狮王重甲妖精，坐在右边巨大王座上大鹏鸟王重甲妖精。渺小的背对镜头孙悟空肩抗金箍棒步行前进，孙悟空身穿铠甲，近地仰拍镜头，长焦镜头，强烈阴影。极致细节刻画，多次修改，正确透视和主体线条，精致细节

Reference Pose Test Against Nano Banana 2

Shared by @desds1678

This tweet compares the same prompt and reference image in GPT Image 2 and Nano Banana 2. The author labels the left image as GPT Image 2 and the right image as Nano Banana 2.

Here is a recreated prompt for the visible comparison.

Use the reference image to create a realistic full-body fashion portrait of a young woman sitting indoors on a white sofa near soft window light. Keep the same general pose, body proportions, casual white top, gray skirt, black tights, natural room lighting, and simple clean background. Make the result look like a realistic lifestyle photo.