GPT Image 2Prompts

Create a cinematic travel poster-style photograph of a narrow old European street in {argument name="city" default="Lisbon"}, viewed from slightly above and looking downhill between tall historic apartment buildings. A classic yellow tram is centered on the tracks, facing the viewer, with cobblestone pavement, overhead tram wires, aged cream and yellow facades, stone window frames, balconies, street lamps, and graffiti-covered walls on both sides. Warm golden-hour sunlight should create long soft shadows and a nostalgic urban atmosphere, with a glimpse of water or distant horizon at the end of the street. Add bold centered typography over the tram: the main headline reads {argument name="headline text" default="LISBON"} in large distressed white uppercase block letters with wide spacing. Beneath it, add a smaller handwritten cursive subtitle reading {argument name="subtitle text" default="Lost in the right direction"}. Add thin horizontal divider lines extending left and right under the subtitle, with a small white diamond/star ornament centered between the lines. Use realistic photography, high detail, warm color grading, strong depth, no people, no vehicles other than the single tram, and no extra text or watermark.

Aesthetic vintage paper collage portrait of a {argument name="subject" default="stylish woman taking a mirror selfie"}, made entirely from torn magazine and newspaper pieces, layered mixed-media artwork, neutral beige and brown tones, Vogue-inspired fashion editorial style, {argument name="accessory" default="black sunglasses"}, sleek ponytail hairstyle, {argument name="clothing" default="white corset top"}, silver jewelry, purple smartphone, textured ripped paper edges, handcrafted mosaic effect, realistic shadows and depth, chic typography cutouts, inspirational quotes scattered around, cozy luxury aesthetic, highly detailed analog collage art, soft warm lighting, Instagram moodboard vibe, premium editorial composition, ultra detailed, 4k

Goal: Create a cream-toned 3D editorial data visualization poster about {argument name="headline text" default="2020–2026 中国离婚人数"}, showing divorce counts in China with a refined miniature diorama style. Canvas: Wide horizontal 2:1 composition, warm off-white paper background with subtle grain, soft shadows, minimalist premium infographic aesthetic. Use a muted cream, black, terracotta, sage, ochre, and beige palette. Layout: Place the main title on the upper left in large elegant black serif Chinese typography. Under it, add the subtitle {argument name="subtitle text" default="全国依法办理离婚手续"} with a thin horizontal rule ending in a small orange dot. The central focus is a black oval/cylindrical stage platform spanning the lower middle of the image, viewed in slight perspective. On the platform, arrange exactly 7 year positions from left to right: 2020, 2021, 2022, 2023, 2024, 2025, 2026. Data bars: Show exactly 5 solid rectangular 3D vertical bars for years 2020–2024 and exactly 2 dashed-outline placeholder bars for 2025 and 2026. Use these visible values and labels: 2020 ochre-gold tall bar labeled 433.9; 2021 terracotta bar labeled 283.9 with a small callout tag reading “2021 低点”; 2022 muted sage-green bar labeled 287.9; 2023 salmon-pink bar labeled 360.53 with a small callout tag reading “2023 回升”; 2024 beige bar labeled 351.3; 2025 dashed empty bar with a hanging tag reading “待更新”; 2026 dashed empty bar with a hanging tag reading “待更新”. Put each year label in white or pale text along the front face of the black platform beneath its position. Supporting visual elements: Include exactly 2 miniature human figures: one standing near the left side of the stage railing looking toward the chart, and one standing on the right side near the 2026 area. Include a delicate small tree with thin branches near the 2020 bar. Add one large warm yellow sun circle in the upper right. Add a tall cream rectangular architectural block at the far right behind the platform. At the lower left foreground, add exactly 3 desk-like props: one semicircular wood block, one off-white paper sheet with faint chart lines and an orange dot, and one small pale green cube. On the front lower center of the platform, add one small beige inset chart card showing a simple black line chart with an orange dot. Legend and text: In the bottom-left corner, add an orange dot followed by “单位：万对”. Keep all Chinese text crisp and readable. Use the data source/style as a polished social-media infographic, not a scientific chart. Style constraints: Soft natural lighting, realistic paper and plaster textures, subtle 3D depth, clean negative space, no watermark, no extra years, no extra bars, no additional text beyond the specified labels. Use {argument name="background color" default="warm ivory"} as the overall background tone and {argument name="accent color" default="orange"} for dots and highlights.

{argument name="Subject" default="Female Android"} in {argument name="Location" default="Spaceship"}

Create a dark cinematic fantasy scene titled {argument name="series title" default="Journey with a Barbarian 6"}: two weary medieval travelers shelter in a narrow rocky canyon during heavy rain at night, resting beside a small bright campfire on muddy wet ground. The scene contains exactly 2 travelers: one central blond, curly-haired adventurer in soaked dark cloak and leather armor sitting on the ground and leaning against a pale gray horse, and one hooded barbarian-like companion in a black rain-drenched cloak sitting against the right rock wall with arms folded. Their faces should be obscured by deep shadow or simple dark square censor-like blocks, making them anonymous. Include exactly 2 horses: one pale gray horse lying or kneeling close to the fire beside the central traveler, and one large black horse standing on the left with wet mane, saddle, harness, and pack gear. Include exactly 5 notable foreground objects: a small campfire made of sticks, a metal cup near the flames, a leather travel bag on the left, a heap of black leather armor and straps on the lower right, and a soaked cloth or cloak spread across the mud. The canyon walls are steep, jagged, and glossy with rain, forming a narrow passage receding into misty blue-gray darkness. Use dramatic low firelight with warm orange highlights reflected in puddles and cold moonlit blue shadows in the background, ultra-detailed wet textures, realistic medieval fantasy costume design, grim survival atmosphere, high-contrast chiaroscuro, vertical composition, no text, no watermark.

Create a playful and relaxed "{argument name="Recipe Type" default="easy recipe introduction illustration page"}" using the character from the reference image. Use the provided image ONLY as a character reference. Do not copy the composition, pose, background, camera angle, or layout of the original image. The AI should freely invent the recipe content. The cooking genre should be easy dishes that can actually be made, such as {argument name="Cooking Genre" default="lazy meals, easy snacks, late-night food, budget meals, junk-style light meals, fridge leftovers, convenience store arrangements, quick side dishes"}. The overall screen should have the vibe of a Japanese internet recipe article, a magazine bonus page, a casual personal blog, an SNS meme image, or a laid-back manga. Structure: - Include multiple step panels. - Include SD/chibi versions of the character for each step. - Add reactions and small jokes during cooking. - Include panicked faces, smug faces, a sense of sloppy work, minor accidents, mysterious momentum, etc. - Add handwritten-style arrows, notes, supplementary comments, and rough warnings. - Make the page design slightly cluttered. - Keep the information dense but organized enough to read. Even if the cooking is shown in a gag style, make it look delicious enough that someone might actually think, "Maybe I'll try making this." Place a large main cut showing the finished dish at the bottom of the image. Include a scene of the character eating the food, speaking their thoughts in a speech bubble. The thoughts should be strangely convincing, silly, weirdly energetic, but make you want to eat it a little. Important: - Do not make the food look unappetizing. - Do not aim for high-end cuisine or authentic restaurant styles. - Do not use an overly clean minimalist design. - Do not make it a sterile infographic. - Emphasize manga-like reactions and a sense of daily life. - Balance a relaxed vibe with practicality. - Maintain the character's face and identity.

Create a moody dark gothic anime portrait of {argument name="character name" default="a demon girl"} seated in a shadowy Victorian room, shown in a close three-quarter view from the thighs up. She has very pale porcelain skin, a sleepy melancholic expression, half-lidded glowing amber eyes, and long vivid {argument name="hair color" default="pink"} hair with messy bangs, a high bun, a long side braid, and loose flowing strands down her back. Add exactly 2 large smooth white oni horns emerging from her head, one on each side. Her accessories include exactly 3 black bows: one tied around the hair bun, one at the white frilled collar, and one on the sleeve; exactly 2 visible earrings: a black key-shaped earring on one ear and a small skull earring with black beads on the other; plus a tiny skull ornament at the chest. Dress her in a black gothic lolita outfit: puffed long sleeves, white ruffled cuffs and collar, black lace details, a glossy black corset with metal eyelets and lacing, a short layered skirt with white ruffle trim, black stockings, and delicate dangling chains with cross charms along the sleeve and skirt. Pose her leaning forward with her head resting on one hand, the other hand relaxed near her knee, looking bored and slightly haunted. The background is a dim purple-black gothic interior with a tufted antique chair back on the right, vague dripping shadows and hanging chain silhouettes on the left. Use dramatic low-key lighting, deep violet shadows, glossy highlights on hair and corset, highly detailed painterly anime rendering, sharp linework, rich texture, high contrast, no text, no watermark.

Goal: Create a side-by-side anime color-variation test illustration of the same cute sailor-girl character concept in an ARIA-inspired canal city setting. Canvas: Wide horizontal 16:9 image split into exactly 2 equal vertical panels with a thin white divider in the center. Soft pastel lighting, dreamy waterfront atmosphere, high-detail anime illustration. Layout: Left panel shows one character seated or kneeling near the canal, facing slightly toward the viewer, holding a tall white gondola-style flagpole on the far left. Right panel shows a second variation of the character in a similar pose, holding a plush mascot. Both faces are intentionally obscured by opaque square censor blocks. Subject details: Use exactly 2 sailor-girl variants. Variant 1 on the left has {argument name="left hair color" default="mint green"} long wavy hair, a white sailor beret with blue trim, a small white flower hair accessory, a white short-sleeved sailor dress with blue and gold trim, white gloves, gold brooch details, and a blue ribbon at the waist. She holds a white flag with a blue curved emblem, and a small raccoon-like mascot sits beside her. Variant 2 on the right has {argument name="right hair color" default="pink"} twin-drill pigtails with large blue bows, a matching white sailor beret with blue trim and a tiny wing-like accessory, a white sailor dress with blue and gold trim, white gloves, and gold ornaments. She hugs a round white-and-brown cat-like plush mascot wearing a blue bow and gold medallion. Counted visible elements: exactly 2 vertical panels; exactly 2 main girls; exactly 2 opaque square face-cover blocks; exactly 2 mascots, one raccoon-like animal in the left panel and one cat-like plush in the right panel; exactly 1 tall white flag in the left panel; exactly 1 central white divider. Background: A romantic Venetian/Aqua-style canal city with pale cream and blue buildings, arched bridges, waterfront colonnades, shimmering turquoise water, reflections, distant towers, soft blue sky, and tiny birds. Keep the background continuous in mood but separated by the panel divider. Visual style: Polished Japanese anime key visual, pastel palette, soft bloom, delicate line art, glossy eyes mostly hidden by the censor blocks, ornate sailor uniform details, cute fantasy maritime aesthetic, high resolution, gentle bokeh and watercolor-like atmospheric depth. Constraints: Keep both face-obscuring squares clearly visible and opaque, left block in muted beige-gray and right block in pale dusty pink. Do not add readable text except the simple blue emblem on the flag. Avoid photorealism, avoid extra characters, avoid more panels, avoid logos or watermarks.

Search the web for detailed information about {argument name="topic" default="Grok AI"} including its development history, underlying architecture, technical capabilities, training methodology, real-world applications, cultural impact, major breakthroughs, controversies, notable model versions, and surprising lesser-known facts. Then create a dramatic editorial infographic poster in the style of a {argument name="style" default="National Geographic feature"} — but for groundbreaking artificial intelligence. The most powerful and recognizable visual representation of Grok is the full-bleed atmospheric hero filling the entire poster top to bottom, dramatically lit and color-graded in deep black, electric blue, chrome silver, and cosmic neon tones matching Grok’s rebellious futuristic identity. Oversized bold typography with the word ‘GROK’ dominates the upper portion in a sleek sci-fi font inspired by space technology and cyberpunk interfaces. Text and graphic panels float naturally over the image as editorial overlays — not boxed magazine layouts. Include: release year and creator/company (xAI / Elon Musk), model architecture and parameter scale, training data scale and computing infrastructure, key capabilities and benchmark performance, integration with X (Twitter), adoption statistics and market influence, launch milestones, famous public demos, major achievements, cultural significance, and 3 surprising lesser-known facts. A technical specification panel on one side showing architecture, multimodal abilities, reasoning features, context window, API ecosystem, and compute power. A timeline of Grok’s major breakthroughs and releases along the bottom. Include references to real-time internet integration, humor-driven personality, open-source initiatives, and competition with other frontier AI models. Color palette and mood drawn entirely from Grok’s own visual identity — cinematic, edgy, intelligent, futuristic, slightly rebellious. No white background, no magazine grid, no boxed sections. Everything layered organically over the full-bleed hero image. Aspect ratio 4:5. Dense, tactile, cinematic, unmistakably Grok.

Goal: Create a vertical Chinese educational poster that combines a miniature LEGO-like electrical components diorama with a study-note infographic about the poem {argument name="poem title" default="沁园春 长沙"}. Canvas: Portrait 3:4 poster, warm beige background, premium editorial layout. Left side is a clean information panel; right and lower area is a realistic macro miniature scene made from electrical hardware parts arranged like a tiny industrial city. Layout: Large dark navy brush-calligraphy title at the upper left reading “沁园春” on the first line and “长沙” on the second line, with a small vertical red seal beside it reading “毛泽东”. Under the title, add the subtitle “相关5个这篇文章的知识点”. Beneath the subtitle, create exactly 5 stacked knowledge cards, each with a navy numbered square, a small line icon, a bold heading, and two short lines of explanatory Chinese text. The 5 cards must be labeled exactly: 01 写作背景, 02 诗歌体裁, 03 主题思想, 04 艺术特色, 05 时代意义. Use fine divider lines and a subtle circuit-trace decoration near the subtitle. Miniature electrical diorama: On the right side, build a highly detailed tabletop scene using electrical spare parts as if they were LEGO architecture: white wall sockets, circuit breakers with red toggle switches, relays, terminal blocks, capacitors, metal rails, copper pipes, black cables, transparent fuse blocks, gray platforms, and tiny bolts. Include a prominent wooden sign at the upper right mounted above circuit components reading {argument name="main sign text" default="为人民服务"}. Add a large wall socket on the right edge and another socket block toward the upper middle-left. Add exactly 10 tiny worker figurines in blue uniforms and yellow hard hats positioned around the machinery, standing on platforms, beside relay towers, and near copper pipe routes. Add small model trees around the edges to make the electrical parts feel like a miniature city. Additional visible signs: Add exactly 2 smaller wooden placards in the lower half of the diorama. One near the bottom-left foreground reads “橘子洲头” with a small arrow. One near the lower-right foreground contains several short vertical Chinese lines suggesting poem-related notes; keep it legible but secondary. Visual style: Photorealistic macro photography mixed with infographic design, shallow depth of field, warm studio lighting, crisp focus on the central electrical components, softly blurred background, realistic plastic, ceramic, copper, and metal textures. Color palette: cream beige, dark navy ink, copper orange, electrical white, gray metal, red switch accents, and small blue-yellow worker figures. Constraints: Use Chinese text exactly where specified, keep the left infographic clean and readable, maintain exactly 5 knowledge cards and exactly 10 worker figurines, avoid random extra titles or watermarks, and make the electrical spare parts look playfully modular like LEGO while still recognizable as real electrical hardware.

Goal: Create a realistic screenshot of a ChatGPT-style web conversation showing an image-generation result for game assets, with Japanese UI text and four generated asset thumbnails. Canvas: Landscape browser/app screenshot, approximately 797×750 px, white background, clean minimal interface, cropped so only the assistant response area and the bottom row of images are visible. Layout: At the top center, place one rounded light-gray user message bubble containing {argument name="user request text" default="image genでゲームで使えそうなアセットの画像を4枚を個別で生成して それぞれを3D化してみて！"}. Below it, left aligned, show a small gray status line reading 「25m 50s作業しました 〉」 followed by a thin horizontal divider. Under that, create an assistant response in Japanese with file lists and blue clickable file links. Text content: Include the assistant paragraph 「できました。4枚のゲーム向けアセット画像を生成して、それぞれPixal3DでGLB化まで通しました。」 Then the label 「画像:」 followed by exactly 4 bullet links with small image/file icons: 1) mana_crystal_alpha.png, 2) treasure_chest_alpha.png, 3) energy_turret_alpha.png, 4) mushroom_house_alpha.png. Then the label 「3D化したGLB:」 followed by exactly 4 bullet links with document icons: 1) mana_crystal.glb, 2) treasure_chest.glb, 3) energy_turret.glb, 4) mushroom_house.glb. Then add the closing Japanese sentence 「生成したのは、魔法クリスタル、宝箱、SFエネルギータレット、きのこ家です。背景はクロマキーから透明化して、3D化に渡しています。」 Bottom image strip: Show exactly 4 rounded-square thumbnail cards in one horizontal row, each about 178×178 px with small gaps. Thumbnail 1 has a vivid green chroma-key background and a stylized fantasy {argument name="asset one" default="blue mana crystal obelisk on a dark stone base"}. Thumbnail 2 has a vivid green chroma-key background and a {argument name="asset two" default="wooden treasure chest with dark metal bands, gold lock, and red jewel"}. Thumbnail 3 has a vivid green chroma-key background and a {argument name="asset three" default="gray sci-fi energy turret with blue glowing core and cannon barrel"}. Thumbnail 4 has a bright magenta chroma-key background and a {argument name="asset four" default="cute mushroom house with red spotted cap roof, wooden door, and warm windows"}. All four assets are polished 3D game-art icons with transparent-cutout style lighting, centered and isolated. Visual style: Modern ChatGPT interface screenshot, Japanese typography, black body text, blue link text, small monochrome icons, generous margins, subtle divider lines. The asset thumbnails should look like high-quality mobile game props rendered in colorful semi-realistic 3D. Constraints: Include exactly 8 file links total, exactly 4 PNG links and exactly 4 GLB links, and exactly 4 asset thumbnail images. Do not add extra panels, watermarks, browser chrome, avatars, or unrelated UI controls.

A stylish illustrated character profile sheet of a handsome young man named “{argument name="character name" default="SAMRONE"}”, sketchbook aesthetic, mixed media ink and watercolor style, highly detailed fashion portrait, {argument name="hair style" default="messy dark curly hair"}, sharp blue eyes, short beard, confident expression, wearing a long black trench coat, dark casual clothes, brown leather backpack, rugged boots. The page layout includes multiple poses and close-up portraits, surrounded by handwritten notes, doodles, symbols, travel sketches, cameras, mountains, coding references, and adventure elements. Personality board design with handwritten text such as traveler, coder, photographer, teacher, sound engineer, Scorpio zodiac sign, river rafting, creative ideas, life goals, motivational notes. Includes small chibi version of the character, laptop working scene, rafting action scene, map sketches, stars, arrows, and artistic scribbles. Modern concept art meets fashion illustration, dynamic ink strokes, expressive line art, textured watercolor shading, warm paper background, cinematic composition, Pinterest aesthetic, highly detailed, visually rich, creative journal vibe, character design sheet, semi-realistic comic illustration.

{argument name="Race" default="Soap-bubble dream race of weasels"}. Freely create their abilities and lifestyle.

Create a cinematic anime inspired streetwear poster featuring a confident {argument name="subject" default="young man"} standing in the center in a relaxed pose with one hand in pocket. He wears {argument name="outfit" default="black sunglasses, a light blue oversized denim shirt layered over a white tank top, faded charcoal washed jeans, white sneakers, silver chain necklace"}, and a modern urban hairstyle with trimmed beard. Background features a massive {argument name="background icon" default="vintage textured Straw Hat Pirates skull logo from One Piece"}, blending into a gritty brown parchment wall with distressed textures, scratches, dust, and dark vignette edges. Add hand drawn anime doodles of Monkey D. Luffy around the composition with rough sketch aesthetics. Poster design should feel like a premium Gen Z fashion editorial mixed with anime street culture. Include cinematic shadows, moody warm brown tones, grunge overlays, faded ink textures, and dramatic contrast. Typography elements: Large distressed bold text saying “OUTFIT CHECK” Small handwritten phrases and pirate themed quotes Japanese vertical typography on the side Barcode element at bottom corner “Gear Fifth” graffiti text Minimal fashion magazine layout styling Style: ultra detailed, anime streetwear editorial, cinematic poster art, gritty urban fashion campaign, textured vintage paper aesthetic, modern hypebeast design, high contrast lighting, premium composition, realistic human proportions, sharp focus. Aspect ratio: 4:5 portrait.

A horizontal 4-panel fashion editorial grid, each panel featuring the same {argument name="subject" default="American white man with sharp jawline and defined facial features"}, each panel has a completely different outfit, pose, lighting, and vibe seamlessly arranged side by side: Panel 1 All-white oversized zip-up jacket, wide-leg cargo trousers, chunky white sneakers, silver chain, futuristic sunglasses, hands in pockets, relaxed confident pose, solid {argument name="background one" default="deep royal blue"} background, cold blue rim lighting, clean editorial vibe Panel 2 — Black leather biker jacket, slim dark jeans, combat boots, gold chain, casual hair, leaning against wall with arms crossed, solid {argument name="background two" default="burnt orange"} background, warm moody tungsten lighting, street fashion vibe Panel 3 — Olive green military cargo jacket, beige tactical trousers, chunky boots, backwards cap, one hand raised adjusting cap, solid dark charcoal background, dramatic single spotlight from above, rugged urban vibe Panel 4 — Cream luxury turtleneck sweater, tailored camel overcoat, brown loafers, minimalist watch, standing straight with subtle smirk, solid deep emerald green background, soft diffused warm lighting, high-end luxury fashion vibe All panels same male subject, consistent face, ultra sharp detail, seamless grid layout, horizontal landscape format 16:5. Ultra photorealistic, 8K, no text overlays, cinematic color grading.

Create a cinematic vintage Coca Cola advertisement inspired by 1940s Americana poster art. Use only the face from the reference image, keeping the same facial structure, wavy medium length hair, masculine features, and confident gaze. Style the subject as a charming retro

Create a creative graphic with the {argument name="subject" default="krabby patty secret formula"}

Create a low-resolution retro 3D video game cutscene-style close-up selfie of exactly two characters standing shoulder to shoulder in a snowy, gray mountain environment. Use a dark, moody PlayStation 1 / early PlayStation 2 aesthetic with visible polygonal geometry, blocky textures, jagged edges, muted lighting, and a 4:3 aspect ratio. The left character is {argument name="left character" default="a petite blue-haired elf girl named Yuki"} with long bright blue hair, pointed elf ears, a dark stitched cap or hood with black ribbon ties, and black tactical clothing; her face is deliberately covered by one opaque square censor block in a cool gray-blue tone. The right character is {argument name="right character" default="a rugged Solid Snake-like soldier"} with spiky dark brown hair, a navy headband tied at the back, tan skin, and bulky black tactical armor with a high collar; his face is deliberately covered by one larger opaque square censor block in a dark brown-black gradient. The composition is an intimate upward-angled close-up, with the left character lower and partly cropped on the left side, and the right character taller, dominating the right side and cropped at the top. Add a cold foggy background with a blurred snowy slope on the far left and exactly two visible face-covering censor squares, one over each character. Include soft falling snow made of small square pixel-like flakes scattered through the background. Keep the image dark, cinematic, and intentionally imperfect, like a captured frame from an old stealth-action game.