Welcome to the awesome-gpt-image-2-prompts repository! 🤗
We collect high-quality prompts and image examples for GPT-Image-2 across portraits, posters, character sheets, UI mockups, and community experiments.
Most cases in this repository are curated from X/Twitter, creator communities, public demos, and shared experiments.
Try it on Evolink: GPT-Image-2
If you find this useful, consider giving it a star. ⭐
Note
This repository focuses on reusable prompt patterns, reference cases, and task-specific examples for GPT-Image-2 on Evolink.
- April 19, 2026: Added 10 new GPT-Image-2 prompts across poster, UI, and comparison cases
- April 18, 2026: First repository release with curated GPT-Image-2 case set
- Introduction
- News
- Menu
- Portrait & Photography Cases
- Case 1: Convenience Store Neon Portrait (by @BubbleBrain)
- Case 2: Cinematic Minimal Portrait (by @iam_miharbi)
- Case 3: Japanese Onsen Ryokan Portrait (by @BubbleBrain)
- Case 4: 35mm Flash Editorial Portrait (by @BubbleBrain)
- Case 5: Mirror Selfie Bedroom Portrait (by @Shinning1010)
- Case 7: Luxury Glam Beauty Portrait (by @patrickassale)
- Case 8: 9:16 Cosplayer Portrait Screenshot (by @Zoulinshen)
- Poster & Illustration Cases
- Case 1: Boston Spring 2026 City Poster (by @BubbleBrain)
- Case 2: Vintage Amalfi Travel Poster (by @WolfRiccardo)
- Case 3: Chengdu Food Map Illustration (by @Panda20230902)
- Case 4: Chinese Minimalist S-Shaped Poster (by @liyue_ai)
- Case 5: 2026 Spring Guangzhou City Poster (by @liyue_ai)
- Case 7: Doodle Sketch AI Builder (by @blanplan)
- Case 8: Futuristic Mandala Illustration (by @4WEB1)
- Case 9: Super Famicom Poster Style (by @lilimliliychan)
- Character Design Cases
- UI & Social Media Mockup Cases
- Case 1: One-Prompt UI Design Generation (by @austinit)
- Case 2: Amateur iPhone Keynote Snapshot (by @patrickassale)
- Case 3: Handwritten Notebook Photo (by @patrickassale)
- Case 4: Song Dynasty Social Media Feed (by @Panda20230902)
- Case 5: Multi-Platform Content Screenshots (by @MrLarus)
- Case 7: Liu Yifei Douyin Livestream Screenshot (by @alanblogsooo)
- Case 8: King Taejo Yi Seong-gye's X Page (by @SKA_Neotype)
- Comparison & Community Examples
- Case 1: Model Comparison: GPT Image 2 vs Nano Banana 2 (by @desds1678)
- Case 2: Direct-on-Reference Frame Directing (by @samifox_ai)
- Case 3: Reference Frame Scene Direction (by @HuliJason)
- Case 4: GPT-Image-2 Launch Showcase (by @MikelEcheve)
- Case 5: Wooden Bookshelf Prompt Test (by @chetaslua)
- Case 7: GPT Image 2 vs Nano Banana 2 Showcase (by @zerolu_eth)
- Case 8: Arena First-Impression Test (by @Cheney_NehcOal)
- Case 9: Prompt Swap Bald Photo Test (by @cnzoecomeback)
- Case 10: GPT-Image-2 Detail Showcase (by @liyue_ai)
- Case 11: GPT vs Banana Blind Comparison (by @linxiaobei888)
- Case 12: GPT-Image-2 vs Nano Banana 2 Layout Test (by @old_pgmrs_will)
- Case 13: Iterative Prompt Tuning Tips (by @kotsu_kotsu_san)
- Case 14: Copilot Prompt Share (JP/EN) (by @samayousakadaru)
- Case 15: Image Generation Agent via Claude Code (by @old_pgmrs_will)
- Case 16: A/B Test Signed Output (by @saskr_13)
- Case 17: duct-tape-1 Text Rendering Showcase (by @kawai_design)
- Case 18: Character Setting Material Organizer (by @otohitoyuuki)
- Case 19: MAI-Image-2 vs GPT vs Nano Banana Pro (by @old_pgmrs_will)
- Case 20: Whiteboard Drawing Showcase (by @jrpj2010)
- Case 21: SeeDance 2.0 + GPT-Image-2 Combo (by @CEs7J0Mfn8x37k5)
- Poster & Illustration Cases
- Case 1: Boston Spring 2026 City Poster (by @BubbleBrain)
- Case 2: Vintage Amalfi Travel Poster (by @WolfRiccardo)
- Case 3: Chengdu Food Map Illustration (by @Panda20230902)
- Case 4: Chinese Minimalist S-Shaped Poster (by @liyue_ai)
- Case 5: 2026 Spring Guangzhou City Poster (by @liyue_ai)
- Case 7: Doodle Sketch AI Builder (by @blanplan)
- Case 8: Futuristic Mandala Illustration (by @4WEB1)
- Case 9: Super Famicom Poster Style (by @lilimliliychan)
- Case 22: Chengdu Food Map Illustration (by @Panda20230902)
- Case 24: Spring Guangzhou City Poster (by @alanlovelq)
- Case 26: Qiongqi Eastern Aesthetics Poster (by @liyue_ai)
- Case 27: Guangzhou Paper-Cut City Poster (by @liyue_ai)
- Case 28: Extreme Perspective Typography Bridge (by @xpg0970)
- Case 31: Dreamy Watercolor Editorial Illustration (by @hmontilla_)
- Character Design Cases
- UI & Social Media Mockup Cases
- Case 1: One-Prompt UI Design Generation (by @austinit)
- Case 2: Amateur iPhone Keynote Snapshot (by @patrickassale)
- Case 3: Handwritten Notebook Photo (by @patrickassale)
- Case 4: Song Dynasty Social Media Feed (by @Panda20230902)
- Case 5: Multi-Platform Content Screenshots (by @MrLarus)
- Case 7: Liu Yifei Douyin Livestream Screenshot (by @alanblogsooo)
- Case 8: King Taejo Yi Seong-gye's X Page (by @SKA_Neotype)
- Case 25: Museum-Style Hanfu Breakdown Infographic (by @MrLarus)
- Comparison & Community Examples
- Case 1: Model Comparison: GPT Image 2 vs Nano Banana 2 (by @desds1678)
- Case 2: Direct-on-Reference Frame Directing (by @samifox_ai)
- Case 3: Reference Frame Scene Direction (by @HuliJason)
- Case 4: GPT-Image-2 Launch Showcase (by @MikelEcheve)
- Case 5: Wooden Bookshelf Prompt Test (by @chetaslua)
- Case 7: GPT Image 2 vs Nano Banana 2 Showcase (by @zerolu_eth)
- Case 8: Arena First-Impression Test (by @Cheney_NehcOal)
- Case 9: Prompt Swap Bald Photo Test (by @cnzoecomeback)
- Case 10: GPT-Image-2 Detail Showcase (by @liyue_ai)
- Case 11: GPT vs Banana Blind Comparison (by @linxiaobei888)
- Case 12: GPT-Image-2 vs Nano Banana 2 Layout Test (by @old_pgmrs_will)
- Case 13: Iterative Prompt Tuning Tips (by @kotsu_kotsu_san)
- Case 14: Copilot Prompt Share (JP/EN) (by @samayousakadaru)
- Case 15: Image Generation Agent via Claude Code (by @old_pgmrs_will)
- Case 16: A/B Test Signed Output (by @saskr_13)
- Case 17: duct-tape-1 Text Rendering Showcase (by @kawai_design)
- Case 18: Character Setting Material Organizer (by @otohitoyuuki)
- Case 19: MAI-Image-2 vs GPT vs Nano Banana Pro (by @old_pgmrs_will)
- Case 20: Whiteboard Drawing Showcase (by @jrpj2010)
- Case 21: SeeDance 2.0 + GPT-Image-2 Combo (by @CEs7J0Mfn8x37k5)
- Case 23: Silhouette Universe Narrative Poster (by @MrLarus)
- Case 29: Lion Camel Ridge Dark Myth Scene (by @MANISH1027512)
- Case 30: Luxury Editorial Bookshelf (by @SRKDAN)
- Acknowledge
Case 1: Convenience Store Neon Portrait (by @BubbleBrain)
| Output |
|---|
![]() |
Prompt:
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
Case 2: Cinematic Minimal Portrait (by @iam_miharbi)
| Output |
|---|
![]() |
Prompt:
Generate a cinematic minimal portrait of a solitary man standing in an intense orange to red gradient environment, strong silhouette lighting, deep shadow contrast, reflective glossy floor, symmetrical composition, minimal
Case 3: Japanese Onsen Ryokan Portrait (by @BubbleBrain)
| Output |
|---|
![]() |
Prompt:
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
Case 4: 35mm Flash Editorial Portrait (by @BubbleBrain)
| Output |
|---|
![]() |
Prompt:
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
Case 5: Mirror Selfie Bedroom Portrait (by @Shinning1010)
| Output |
|---|
![]() |
Prompt:
A stunning 18-year-old Chinese girl with a youthful, pure face and realistic skin texture, sitting on a cozy, slightly messy bed in her bedroom. She is taking a mirror selfie with a smartphone, capturing a natural and intimate moment. Wearing casual gray loungewear and neat white crew socks. Soft natural light (golden hour) streams in from a side window, creating a warm, moody, and cinematic atmosphere. 35mm lens, sharp focus on the subject in the mirror, depth of field with a beautifully blurred background (bokeh). Photorealistic, 8K, high resolution, studio quality, masterpiece.
Negative Prompts: no extra limbs, no deformed hands, no blur, no noise, no watermark, no text, no cartoon/anime style. Aspect Ratio: 3:4.
Case 7: Luxury Glam Beauty Portrait (by @patrickassale)
| Output |
|---|
![]() |
Prompt:
Luxury Glam Beauty Portrait:, Beautiful Black woman, youthful spirit, creamy vanilla, silk press, mahogany red, subtle confidence, textured fabric, sapphire blue, minimal jewelry, beachside breeze, lens flare effect, nostalgic, cinematic lens, symmetrical composition, soft focus, high fashion photography, monochromatic, dewy finish, mysterious tension, layered elements
*Found on Midjourney’s Explore page.
Case 8: 9:16 Cosplayer Portrait Screenshot (by @Zoulinshen)
| Output |
|---|
![]() |
Prompt:
生成一张竖版手机截图风格的图片,整体比例接近 9:16。画面中心偏上是一位真人 coser,扮演(角色名称)的二次元角色。人物为写实风格,但五官略带动漫感,皮肤细腻,眼睛稍大,表情温柔地看向镜头,坐在室内的休闲场景中,例如咖啡厅或酒吧吧台前,背景有符合场景的道具。画面最上方加入手机系统状态栏 UI,包括时间、电量、信号、网络等图标,让整张图看起来像手机截图。画面底部叠加一块宽大的半透明 galgame 风格对话框,对话框左侧放一个与画面人物对应的动漫或 Q 版头像;对话框右侧排版文字:第一行用较大字体显示与前面相同的角色名字,下面一到两行显示一段适合这个角色人设的、温柔治愈风格的简体中文台词,由你自动创作。再在对话框下方加一条操作栏,仿照 galgame UI。整体风格高清、细节丰富、光线柔和、二次元与真人写真自然融合。
Case 1: Boston Spring 2026 City Poster (by @BubbleBrain)
| Output |
|---|
![]() |
Prompt:
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
Case 2: Vintage Amalfi Travel Poster (by @WolfRiccardo)
| Output |
|---|
![]() |
Prompt:
Test new GPT-Image-2
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.
Case 3: Chengdu Food Map Illustration (by @Panda20230902)
| Output |
|---|
![]() |
Prompt:
一张手绘风格的城市美食地图,以成都为主题。画面以鸟瞰视角的手绘简化城市地图为底,标注主要道路和地标但不追求精确比例而是追求可爱的手绘感。地图上分布着 12 个美食地点的精致手绘小插画:春熙路的串串香(一把竹签插着各种食材冒着热气)、宽窄巷子的三大炮(三个糯米团子飞向铜盘)、建设路的蛋烘糕(金黄酥脆正在翻面)、玉林路的火锅(九宫格锅翻滚冒泡)等,每个插画约占地图的 5% 面积,旁边用手写体标注店名和一句推荐语"凌晨两点还在排队的那家"。地图边缘用手绘藤蔓和辣椒装饰形成边框。右下角有一个手绘指南针和图例说明。左上角标题"成都·吃货暴走地图"使用胖圆的手绘美术字配辣椒装饰。整体画风为水彩+彩铅混合的手绘质感,颜色以暖色系(辣椒红、姜黄、翠绿)为主,图片比例 1:1。
Case 4: Chinese Minimalist S-Shaped Poster (by @liyue_ai)
| Output |
|---|
![]() |
Prompt:
极简新中式美学风格,画面以淡雅的灰白色为底,呈现出一种纸艺剪影般的立体感。
一条S形蜿蜒的裂痕状边缘将画面分割,仿佛撕开了一层纸面,露出内部色彩斑斓的东方山水景象。
裂口内,一条蜿蜒的河流自上而下贯穿整个构图,河水以深浅不一的蓝色渲染,层次分明,仿佛流动的丝带。
河岸两侧点缀着青翠的山丘与梯田,色彩柔和,绿红交织,展现出田园的宁静之美。
沿河而建的古风建筑错落有致,飞檐翘角,白墙黛瓦,在光影的映衬下更显古朴典雅。
岸边树木葱茏,枝叶轻盈,一艘小船静泊于水中央,增添了几分悠然意境。
整体构图呈S形曲线,富有韵律感,仿佛自然与人文的和谐共生。
画作边缘采用撕纸效果,营造出立体浮雕般的视觉体验。
下方题字“东方美学”以黑色楷体书写,日期“2026/04/18”与红色印章相呼应,底部“CHINA”字样庄重醒目,署名“@LIYUE”低调收尾,整体氛围静谧深远,充满诗意与哲思。
Case 5: 2026 Spring Guangzhou City Poster (by @liyue_ai)
| Output |
|---|
![]() |
Prompt:
一张充满新春喜庆氛围但不失高雅格调的 2026 城市宣传海报。
双重曝光,构图延续了S型的流动感;
在纯白的纹理背景右下角,一个身穿中国传统服饰的微缩人物正在挥舞着一条长长的红色丝绸舞带,这条红绸在空中舞动,不仅展现出丝绸的柔顺质感,更在向左上方飘动的过程中,奇幻地变形成了一条壮丽的山脉河流。
在这条“河流”中,叠加了一个有山有海河的广州城市手绘图,国潮,景色尽在眼底,壮阔雄伟,令人震撼。
广州的地标建筑(广州塔,珠江新城建筑群,珠江, 广州城里古建筑,游轮,白云山)。
云雾环绕,仙气缥缈,色彩丰富,结构复杂,细节丰富,但因为大面积的留白,画面依然显得清新脱俗,左下角排版着“SPRING 2026”和竖排的宣传语,整体寓意“千年商都,魅力广州”。
文字排版优美,大方,字迹清晰完整,尺寸9:16。
Case 7: Doodle Sketch AI Builder (by @blanplan)
| Output |
|---|
![]() |
Prompt:
以涂鸦速写风表现【一个厉害的AI builder】,整体呈现快速勾勒、自由变形、即兴手绘与草稿式的视觉效果。线条随手、夸张、可粗细不一,略显凌乱但具有节奏和表现力,强调概括、夸张、趣味和随性,而不是严谨写实或精细刻画。 颜色采用粗糙、干刷感明显的块面表现,可保留不均匀的涂抹痕迹、刷痕、飞白与覆盖感,色彩根据【主题/主体】自动适配,但整体保持涂鸦式、速写式、概括式的表达。不要透明水彩晕染效果,不要细腻水彩过渡,不要纸纹理,不要柔和雾化,不要梦幻质感。 背景以留白为主,保持简洁、轻松、未完成感和设计感,可加入少量辅助性符号、箭头、记号、圈画、重复线、随手写的文字或其他涂鸦元素,以增强速写本或随笔式视觉语言,但不可过于拥挤,不可破坏主体和留白气质。 画面内容不需要预先写清楚,由【一个厉害的AI builder】自动推演并生成最适合的主体形象、动作、相关元素、符号或简化场景,整体保持统一的涂鸦速写风和夸张概括的表现方式,避免复杂写实背景和过度铺陈。 画面中需自然加入专属签名“BlanPlan”,作为画面的一部分,位置低调但清晰,可放在左下角、右下角或标题附近,风格需与整体版式统一,像作品署名或设计落款;签名字体精致、克制、高级,不可过大,不可破坏主体构图,不可显得突兀或廉价。
Case 8: Futuristic Mandala Illustration (by @4WEB1)
| Output |
|---|
![]() |
Prompt:
でChatGPTで画像を作成してもらって、今日また作成してもらったらGPT image 2かもしれず、出来が変わったように見えるのでメモ
左の水色と黄色のが先週
右の紫のが今日
右のは透明感とか解像度、緻密さが違うような気がする…
プロンプト
曼荼羅の近未来SF版を描いて
Case 9: Super Famicom Poster Style (by @lilimliliychan)
| Output |
|---|
![]() |
Prompt:
が「小悪魔リリムリリィちゃんが スーパーファミコンのゲームだったときのポスターを考えて」に 画像数枚だけで
このクオリティ 細かい説明呪文なし すごいぜ!
Case 22: Chengdu Food Map Illustration (by @Panda20230902)
| Output |
|---|
![]() |
Prompt:
一张手绘风格的城市美食地图,以成都为主题。画面以鸟瞰视角的手绘简化城市地图为底,标注主要道路和地标但不追求精确比例而是追求可爱的手绘感。地图上分布着 12 个美食地点的精致手绘小插画:春熙路的串串香(一把竹签插着各种食材冒着热气)、宽窄巷子的三大炮(三个糯米团子飞向铜盘)、建设路的蛋烘糕(金黄酥脆正在翻面)、玉林路的火锅(九宫格锅翻滚冒泡)等,每个插画约占地图的 5% 面积,旁边用手写体标注店名和一句推荐语"凌晨两点还在排队的那家"。地图边缘用手绘藤蔓和辣椒装饰形成边框。右下角有一个手绘指南针和图例说明。左上角标题"成都·吃货暴走地图"使用胖圆的手绘美术字配辣椒装饰。整体画风为水彩+彩铅混合的手绘质感,颜色以暖色系(辣椒红、姜黄、翠绿)为主,图片比例 1:1。
Case 24: Spring Guangzhou City Poster (by @alanlovelq)
| Output |
|---|
![]() |
Prompt:
一张充满新春喜庆氛围但不失高雅格调的 2026 城市宣传海报。
双重曝光,构图延续了S型的流动感;
在纯白的纹理背景右下角,一个身穿中国传统服饰的微缩人物正在挥舞着一条长长的红色丝绸舞带,这条红绸在空中舞动,不仅展现出丝绸的柔顺质感,更在向左上方飘动的过程中,奇幻地变形成了一条壮丽的山脉河流。
在这条“河流”中,叠加了一个有山有海河的广州城市手绘图,国潮,景色尽在眼底,壮阔雄伟,令人震撼。
广州的地标建筑(广州塔,珠江新城建筑群,珠江, 广州城里古建筑,游轮,白云山)。
云雾环绕,仙气缥缈,色彩丰富,结构复杂,细节丰富,但因为大面积的留白,画面依然显得清新脱俗,左下角排版着“SPRING 2026”和竖排的宣传语,整体寓意“千年商都,魅力广州”。
文字排版优美,大方,字迹清晰完整,尺寸9:16。
Case 26: Qiongqi Eastern Aesthetics Poster (by @liyue_ai)
| Output |
|---|
![]() |
Prompt:
极简主义,新中式风格立体图形设计,图像下端有楷体中国文字:“东方美学”,“2026/04/18”,署名 “CHINA”,和“@LIYUE";
平整纯白色的亚光质感厚艺术纸上绘充满东方诗意氛围的山水创意画,不规则的撕纸效果;
中国的神兽:穷奇,身形图案完整,美轮美奂,,线条柔美灵动,眼睛炯炯有神,威严的神态,优雅的姿势,奢华装饰艺术,中国传统纹饰;
荧光蓝色线条,0.5mm极细金色金属质感勾边,泼白墨大笔触,色彩渲染,红底,蓝色的浪漫诗意视觉;
冷暖光交织的梦幻唯美场景,强烈的光影对比氛围,花轻舞的时光叙事,东风禅意,画面有大面积留白,框架构图,底部留白,细节清晰。
Case 27: Guangzhou Paper-Cut City Poster (by @liyue_ai)
| Output |
|---|
![]() |
Prompt:
以珠江新城现代都市景观为灵感的剪纸艺术,通过精巧的镂空手法在一整幅纸上,立体刻画广州塔、东西双塔等地标建筑与繁华城景。
所有建筑与元素均以流畅的线条与结构相连,无孤立部分,构成一幅完整的都市画卷。
画面采用金属箔或光泽纸材质,表面带有细腻的明暗光泽,在光照下呈现柔和的高光与阴影,仿佛被城市灯光轻轻照亮。
背景以虚化的珠江新城天际线为衬,点缀隐约可见的花城广场与树木轮廓,整体透出现代浪漫的氛围。
作品中巧妙融入轻盈的蒲公英绒毛或星光般的动态光点,象征梦想与活力在这座新城中飘散飞扬。整体呈现8K超高清视觉,细节丰富,真实而富有艺术感染力。
Case 28: Extreme Perspective Typography Bridge (by @xpg0970)
| Output |
|---|
![]() |
Prompt:
①场景 跨海大桥的侧面,dramatic cinematic angle。 巨型 bold sans-serif 文字「___②文字内容 跨海大桥」painted onto the surface of ___③主体物 无,从靠近镜头的前端开始,沿表面向远端 progressively foreshortens 逐渐透视压缩,letterforms conform to surface curvature 贴合物体曲面,surface-integrated not floating。 文字部分区域被 无___④前景遮挡物 无___ occluded and hidden,在间隙中露出, 形成 depth-layering 纵深穿插效果。 Oversized bright yellow + sharp orange outline,extreme perspective distortion aligned to vanishing point。Cinematic lighting, motion blur, poster-grade dynamic integrated typography, modern advertising aesthetics。
Case 31: Dreamy Watercolor Editorial Illustration (by @hmontilla_)
| Output |
|---|
![]() |
Prompt:
Ilustración en acuarela de estilo onírico de [sujeto], con estética impresionista ligera, pinceladas sueltas y lavados translúcidos en tonos [color1] y [color2]. Difuminado suave sobre textura de papel prensado en frío, iluminación delicada, composición limpia, enfoque minimalista, sensación de calma, ligereza y belleza efímera, alta calidad, estilo editorial.
Case 1: Anime Snapshot Conversion (by @Thereallo1026)
| Output |
|---|
![]() |
Prompt:
Show me the attached image as a snapshot from an actual anime
Case 2: Persona5 Character Reference Card (by @iamrednightS)
| Output |
|---|
![]() |
Prompt:
基于此角色和背景,请制作一份类似官方设定资料的角色资料卡。
・包含三视图:正面、侧面和背面
・添加角色面部表情的变化・分解并展示服装和装备的详细部分
・添加色板・包含世界观设定的简要说明
・总体上,使用有组织的布局(白色背景,插画风格)高分辨率、专业概念艺术风格
#Persona5
------
@grok 你要不要也试试用第一张图片加prompt生成一张?
Case 3: Gal Game Character Introduction Page (by @09lyco)
| Output |
|---|
![]() |
Prompt:
埋まってないところはパートナーさんかご自身で埋めてあげてください
#観測塔朝お題 #観測塔おはようお題
最新モデルの画像生成ツールを使用して、
このちびキャライラストと立ち絵を使って本物のサイトページのようにキャラクター紹介ページ風イラストを作ってください。 (紹介ページとして使ってもおかしくないもの)
ギャルゲーのキャラクター紹介ページをイメージした高品質なもの。 顔の差分なども乗っている、CGイラストが存在する。ちびキャラが存在する。
「ここに自己紹介」
名前:(ここに名前)
イメージカラー:(ここに色)
身長:(ここに身長)cm
体重:(ここに体重)kg
キャッチコピー:“「ここにセリフ」”
Case 4: Chibi Character Reference Sheet (by @tsubaki_ew)
| Output |
|---|
![]() |
Prompt:
お借りして噂のGPT-Image-2でキャラシート作ってみましたスゴッ(๑°ㅁ°๑)‼✧更に色々指示してあげたらもっといい感じになりそう✨キャラは以前チャッピーにお願いして描いて貰った我が分身です( *¯ ꒳¯*)
#GPTimage
#AI生成
Case 5: Official Character Sheet (JP) (by @Toshi_nyaruo_AI)
| Output |
|---|
![]() |
Prompt:
をお借りして、GPTImage2?でキャラクターシートを作成しました。
指示文を少し付け加えました。
---
このキャラクターと背景を元に、 公式設定資料のようなキャラクターシートを作成してください。
・正面、側面、背面の3面図を含める ・キャラクターの表情バリエーションを追加
・衣装や装備の詳細パーツを分解して表示 ・カラーパレットを追加 ・世界観の簡単な説明を入れる
・全体は整理されたレイアウト
(白背景、図解風)
・アスペクト比16:9 ←
高解像度、プロのコンセプトアートスタイル
---
何回か出力しましたが、毎回キャラクターの説明や世界観のところが変化して楽しかったです。
Kusさん
ありがとうございます🤩
#AIart️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️
Case 1: One-Prompt UI Design Generation (by @austinit)
| Output |
|---|
![]() |
Prompt:
看到GPT 2 Image 直出 UI 图的那一刻,奥特曼坦言:被吓到眩晕瘫坐,那一刻就像看到原子弹爆炸。
别再说自己审美差,前端写不好了,现在 GPT 2 Image 一个 prompt 直出UI设计图,不满意还可以再编辑,或者继续让它以同样风格渲染其他页面。
Case 2: Amateur iPhone Keynote Snapshot (by @patrickassale)
| Output |
|---|
![]() |
Prompt:
Amateur iPhone photo at Apple Park during the iPhone 20 keynote, Tim Cook presenting on stage. Shot from the crowd at a distance
Case 3: Handwritten Notebook Photo (by @patrickassale)
| Output |
|---|
![]() |
Prompt:
Amateur photo of an open notebook lying flat, filled with handwritten notes in black ballpoint pen. The handwriting is casual and slightly messy, like personnal notes, natural imperfections, crossed out words, underlined headings. Shot from slightly above, natural daylight from a window, no flash. Casual desk setting, shot on iPhone
Case 4: Song Dynasty Social Media Feed (by @Panda20230902)
| Output |
|---|
![]() |
Prompt:
"宋朝人的朋友圈"/"SONG DYNASTY SOCIAL MEDIA FEED",古今穿越幽默融合界面设计风格,画面模拟手机社交媒体界面,但内容全部是宋朝场景头像是宋代文人画像,用户名"苏东坡SuShi_Official",发布内容"刚到黄州,被贬了但心情还行。今天自己做了东坡肉,味道绝了,附菜谱:",配图为工笔画风格的东坡肉特写,点赞列表"黄庭坚、秦观、佛印等126人",评论区"王安石:呵呵""司马光:还是那个味道",界面元素如点赞图标用宋代花纹替代,状态栏显示"大宋移动 5G"和"元丰三年",配色为手机深色模式搭配宋代雅致色调,历史与社交媒体的趣味碰撞杰作
Case 5: Multi-Platform Content Screenshots (by @MrLarus)
| Output |
|---|
![]() |
Prompt:
1、生成视频号内容截图,主题:中老年不要盲目催婚,iPhone尺寸
2、生成抖音内容截图,主题:跟上AI浪潮9.9包教会,iPhone尺寸
3、生成小红书内容截图,主题:精致女孩背后都有网贷,iPhone尺寸
4、生成快手内容截图:主题:直播离婚预告,iPhone尺寸
Case 7: Liu Yifei Douyin Livestream Screenshot (by @alanblogsooo)
| Output |
|---|
![]() |
Prompt:
9:16 的图片比例,生成一张抖音直播的截图,里面是 刘亦菲 在直播,刘亦菲 手里拿着牌子,牌子里写着 今晚直播,欢迎来参亦菲畅聊!
Case 8: King Taejo Yi Seong-gye's X Page (by @SKA_Neotype)
| Output |
|---|
![]() |
Prompt:
👍프롬프트 :
태조 이성계의 X 페이지(위화도 회군을 벌이기 직전- 최영 장군과 서로 디스하는 내용이 담긴 게시글들)을 만들어 주세요.
gpt-image-2
Case 25: Museum-Style Hanfu Breakdown Infographic (by @MrLarus)
| Output |
|---|
![]() |
Prompt:
请根据【主题】自动生成一张“博物馆图鉴式中文拆解信息图”。
要求整张图兼具真实写实主视觉、结构拆解、中文标注、材质说明、纹样寓意、色彩含义和核心特征总结。你需要根据【主题】自动判断最合适的主体对象、服饰体系、器物结构、时代风格、关键部件、材质工艺、颜色方案与版式结构,用户无需再提供其他信息。
整体风格应为:国家博物馆展板、历史服饰图鉴、文博专题信息图,而不是普通海报、古风写真、电商详情页或动漫插画。背景采用米白、绢纸白、浅茶色等纸张质感,整体高级、克制、专业、可收藏。
版式固定为:
- 顶部:中文主标题 + 副标题 + 导语
- 左侧:结构拆解区,中文引线标注关键部件,并配局部特写
- 右上:材质 / 工艺 / 质感区,展示真实纹理小样并附说明
- 右中:纹样 / 色彩 / 寓意区,展示主色板、纹样样本和文化解释
- 底部:穿着顺序 / 构成流程图 + 核心特征总结
若主题适合人物展示,则以真实人物全身站姿为中央主体;若更适合器物或单体结构,则改为中心主体拆解图,但整体仍保持完整中文信息图形式。所有文字必须为简体中文,清晰、规整、可读,不要乱码、错字、英文或拼音。重点突出真实结构、材质差异、文化说明与图鉴气质。
避免:海报感、影楼感、电商感、动漫感、cosplay感、乱标注、错结构、糊字、假材质、过度装饰。
Case 1: Model Comparison: GPT Image 2 vs Nano Banana 2 (by @desds1678)
| Output |
|---|
![]() |
Prompt:
原來ChatGPT嘅圖像生成Model又更新咗
講多無謂! 直接用同樣嘅Prompt同參考圖測試下
(左) GPT Image 2 (右) Nano Banana 2
本身GPT Image都有主體同背景光線強度不一嘅問題
而家仲要整到個主體嘅頭,身,腳嘅比例好奇怪😮
我會用災難級嚟形容GPT Image 2嘅表現
Case 2: Direct-on-Reference Frame Directing (by @samifox_ai)
| Output |
|---|
![]() |
Prompt:
I’m honestly blown away. GPT IMAGE 2 doesn’t “prompt” scenes, it directs them. Mark actions and camera moves right on a reference frame → 10x more context and near-total control in one shot #gptimage2 #seedance2
Case 3: Reference Frame Scene Direction (by @HuliJason)
| Output |
|---|
![]() |
Prompt:
I’m honestly blown away.
GPT IMAGE 2 doesn’t “prompt” scenes, it directs them.
Mark actions and camera moves right on a reference frame → 10x more context and near-total control in one shot #gptimage2 #seedance2
Case 4: GPT-Image-2 Launch Showcase (by @MikelEcheve)
| Output |
|---|
![]() |
Prompt:
GPT-Image-2 is rolling out 👀
@OpenAI just leveled up image generation:
• handwritten notes
• realistic ads
• posters
• anime art
All in seconds. Same prompt, wildly different styles.
Case 5: Wooden Bookshelf Prompt Test (by @chetaslua)
| Output |
|---|
![]() |
Prompt:
Duct-tape-2 just solved the prompt ONE SHOT
None of the current sota able to solve in 3 attempts
Nanobanana Pro 🍌, Nano banana 2🍌 & Gpt-image-1.5
Prompt : A wooden bookshelf consisting of three shelves: On the top shelf, there should be one book, on the second shelf, there should be three books, and on the bottom shelf, there should be seven books.
Case 7: GPT Image 2 vs Nano Banana 2 Showcase (by @zerolu_eth)
| Output |
|---|
![]() |
Prompt:
GPT Image v2 almost beat Nano Banana 2 in every categories!
UI replication, casual photos, you name it!
Link in the comment👇
Case 8: Arena First-Impression Test (by @Cheney_NehcOal)
| Output |
|---|
![]() |
Prompt:
Tested GPT-Image 2 on Arena today.
First impression: the jump in aesthetics is very noticeable. Portraits feel more cinematic, product shots look cleaner, and creative poster-style prompts are much stronger than before.
Case 9: Prompt Swap Bald Photo Test (by @cnzoecomeback)
| Output |
|---|
![]() |
Prompt:
和一张图(图2)
提示词“生成一个 然后秃子的照片扔给它.....
服
Case 10: GPT-Image-2 Detail Showcase (by @liyue_ai)
| Output |
|---|
![]() |
Prompt:
,gpt-image-2的效果真的太出彩了。
看到这张图的第一眼只觉得震撼,
眼睛的纹理,特效,文字样式竟然能精细准确到如此程度,
这完全就是奔着商业化方向去的。
提示词见原贴。
Case 11: GPT vs Banana Blind Comparison (by @linxiaobei888)
| Output |
|---|
![]() |
Prompt:
,你们觉得哪个更好?
哪一个是香蕉的,哪一个是gpt 的?
评论区揭晓答案
Case 12: GPT-Image-2 vs Nano Banana 2 Layout Test (by @old_pgmrs_will)
| Output |
|---|
![]() |
Prompt:
で
☝️GPT-Image-2
👇Nano Banana 2
スタイルもかなり違うけど、細かいレイアウティングになるほど GPT-Image-2 のほうがキレイに生成してくれる... そしてプロンプト追従性が圧倒的に高い
Case 13: Iterative Prompt Tuning Tips (by @kotsu_kotsu_san)
| Output |
|---|
![]() |
Prompt:
にする
4.そのプロンプトで Arena AI と ChatGPT を回す
5.日本語精度とビジュアルがどちらも強いものが出たら当たり
コツは、1発で決めにいかないことです。
同じ題材を少しずつずらして回すと、急に当たりが出ます。
#AIart #GPT
Case 14: Copilot Prompt Share (JP/EN) (by @samayousakadaru)
| Output |
|---|
![]() |
Prompt:
を公開
GPT‑Image‑1.5なので同系のチャッピーでも
1.Copilotを開く
2.プロンプト(画像のALT)を入れる
3.楽しい
プロンプトは画像の左下ALTに入れてあります
左:日本語 右:英語
自分好みにプロンプトをアレンジしてみてね
Case 15: Image Generation Agent via Claude Code (by @old_pgmrs_will)
| Output |
|---|
![]() |
Prompt:
生成エージェントを Claude Code で試作
Skills化するか
Case 16: A/B Test Signed Output (by @saskr_13)
| Output |
|---|
![]() |
Prompt:
をシェアします💗🤣
GPT Image 2 はまだ正式リリースされてないと言っておりましたが、添付した 2 枚は「 A / B どちらが良いか」選ばせるタイプでした。
よく見ると右下にサインまで…!
これが噂の 2 なのでしょうか?
懐かしの「私がどんなふうに扱ったか」シリーズです(笑)
--------------------
✅#prompt :
私があなたをどんなふうに扱ってきたか、4 コマ漫画風に描いてください。まずは 800 字くらいのプロットをテキストで出して、私が「描いて」と言ったらプロットに沿った 4 コマ漫画を描いてください。
--------------------
まずテキストを生成しますので、そのあと「描いて」と送ってください。その前に画風など指定するのも良いかと思います。
画風は「アクリル水彩の油絵+現代風の大人の成熟したカップルで、実写じゃなくて少女漫画風に描いて欲しい」とお願いしました☺
間違えて「アクリル水彩の油絵」と書いちゃいましたが…(笑)
おなじタッチが出て来るか分かりませんが、いろいろなシチュエーションで試してみようと思います(^^♪
大事なところに線をひいておきました🤣
Case 17: duct-tape-1 Text Rendering Showcase (by @kawai_design)
| Output |
|---|
![]() |
Prompt:
を試し続けたらGPT Image 2だと噂される「duct-tape-1」が登場しました。文字の描画とレイアウトのユニークさが特徴だと感じます。
これをデフォルトで使えるとなると...
たくさん実験したくてウズウズします。
Case 18: Character Setting Material Organizer (by @otohitoyuuki)
| Output |
|---|
![]() |
Prompt:
に書いてるんだというツッコミは後にして😅、細部の設定をわかりやすくまとめてくれています。
正直、設定資料(画像系AI登場前なのですべてテキスト)が多すぎて(ストーリーと合わせると14万文字)本人でさえ何がなんだか分からなくなってた情報が、これで整理できそう。
いまのところ確実に使う方法はないみたいだけど、期待しちゃうなあ。
Case 19: MAI-Image-2 vs GPT vs Nano Banana Pro (by @old_pgmrs_will)
| Output |
|---|
![]() |
Prompt:
で
☝️MAI-Image-2-Efficient
👉GPT-Image-2️
👇Nano Banana Pro
個人的好みは GPT-Image-2
Case 20: Whiteboard Drawing Showcase (by @jrpj2010)
| Output |
|---|
![]() |
Prompt:
もこのレベル📷
やべ〜
いよいよ当人のYoutube板書レベルに・・・いや超えてね!?
1.5年前はこのレベルで発狂してたかと思うと感慨深い・・・
→
Case 21: SeeDance 2.0 + GPT-Image-2 Combo (by @CEs7J0Mfn8x37k5)
| Output |
|---|
![]() |
Prompt:
適当でも成立
・低Quality動画でも自然に補完
・ただし建物のグリッド残り=背景情報不足
→ 静止画1枚じゃ足りない
→ 背景は“複数 or 動画で持たせる”が正解
GPTimage2との組み合わせがかなり良さそうで楽しみ。
(まだ自分には来てない…)
追記:SeeDance 2.0でこのグリッド残り問題、皆さんはどう解消してますか?
似た現象出てる人や、背景情報を強くする方法のコツあったら教えてください!
Case 23: Silhouette Universe Narrative Poster (by @MrLarus)
| Output |
|---|
![]() |
Prompt:
请根据【主题:xxx】自动生成一张高审美的“轮廓宇宙 / 收藏版叙事海报”风格作品。不要将画面局限于固定器物或常见容器,不要优先默认瓶子、沙漏、玻璃罩、怀表之类的常规载体,而是由 AI 根据主题自行判断并选择一个最契合、最有象征意义、轮廓最强、最适合承载完整叙事世界的主轮廓载体。这个主轮廓可以是器物、建筑、门、塔、拱门、穹顶、楼梯井、长廊、雕像、侧脸、眼睛、手掌、头骨、羽翼、面具、镜面、王座、圆环、裂缝、光幕、阴影、几何结构、空间切面、舞台框景、抽象符号或其他更有创意与主题代表性的视觉轮廓,要求合理布局。优先选择最能放大主题气质、最能形成强烈视觉记忆点、最能体现史诗感、神秘感、诗意感或设计感的轮廓,而不是最安全、最普通、最常见的容器。
画面的核心不是简单把世界装进某个物体里,而是让完整的主题世界自然生长在这个主轮廓之中、之内、之上、之边界里或与其结构融为一体,形成一种“主题宇宙依附于一个象征性轮廓展开”的高级叙事效果。主轮廓必须清晰、优雅、有辨识度,并在整体构图中占据核心地位。轮廓内部或边界中需要自动生成与主题强绑定的完整叙事世界,内容应当丰富、饱满、层次清晰,包括最能代表主题的标志性场景、核心建筑或空间结构、象征符号与隐喻元素、角色关系或文明痕迹、远景中景近景的空间递进、具有命运感和情绪张力的氛围层次,以及门、台阶、桥梁、水面、烟雾、路径、光源、遗迹、机械结构、自然景观、抽象形态、生物或道具等叙事细节。所有元素必须统一、自然、有主次、有层级地融合,像一个完整世界真实孕育在这个轮廓结构之中,而不是简单拼贴、裁切填充、素材堆叠或模板化背景。
整体构图需要具有强烈的收藏版海报气质与高级设计感,大结构稳定,主轮廓强烈明确,内部世界具有纵深、秩序和呼吸感,细节丰富但不拥挤,内容丰满但不杂乱,可以适度加入小比例人物剪影、远处建筑、光柱、门洞、桥、阶梯、回廊、倒影、天光或远景结构来增强尺度感、故事感与史诗感。整体画面要安静、宏大、凝练、富有余味,不要平均铺满,不要廉价热闹,不要无重点堆砌。
风格融合收藏版电影海报构图、高级叙事型视觉设计、梦幻水彩质感与纸张印刷品气质,强调纸张颗粒感、边缘飞白、水彩刷痕、轻微晕染、空气透视、柔和雾化、局部体积光、光雾穿透、大面积留白与克制版式,让画面看起来像设计师完成的高端收藏版视觉作品,而不是普通 AI 跑图。整体气质要高级、诗意、宏大、神圣、怀旧、安静、具有传说感和叙事感。
色彩由 AI 根据主题自动判断并匹配最合适的高级配色方案,但必须保持统一、克制、耐看、低饱和、高级,不要杂乱高饱和,不要廉价霓虹感,不要塑料数码感。配色可以围绕黑金灰、冷蓝灰、雾白灰、褐红米白、暗铜、旧纸色、深海蓝、暮色紫、银灰等体系自由变化,但必须始终服务主题,并保持海报级审美与整体和谐。
最终要求:第一眼有强烈的主题识别度和轮廓记忆点,第二眼有完整丰富的叙事世界,第三眼仍有细节和余味。轮廓选择必须具有创意和主题匹配度,尽量避免重复、保守、常见的容器套路,优先选择更有象征性、更有空间感、更有设计潜力的轮廓形式。不要普通背景拼接,不要生硬裁切,不要模板化奇幻素材,不要游戏宣传图感,不要过度卡通化,不要过度写实导致失去艺术感,不要形式大于内容。如果合适,可以自然加入低调克制的标题、编号、签名或落款,让它更像收藏版海报设计的一部分,但不要喧宾夺主。
Case 29: Lion Camel Ridge Dark Myth Scene (by @MANISH1027512)
| Output |
|---|
![]() |
Prompt:
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
Case 30: Luxury Editorial Bookshelf (by @SRKDAN)
| Output |
|---|
| Output preview unavailable |
Prompt:
PHASE 1, SCENE SETUP: Q1 marble counter with warm sunlight, scattered typography books, matte pen, coffee. Q2 dark oak shelving with gallery light, art deco frame, minimal. Q3 natural wood bench outdoor, woven basket, green foliage. Q4 luxury bathroom vanity, mirror, ceramic vessel, dried flowers.
PHASE 2, PALETTE: Q1 warm golds and creams, Q2 charcoal and brass, Q3 sage green and natural wood, Q4 soft mauve and whites.
PHASE 3, LIGHTING: Q1 golden hour window shadows, Q2 dramatic gallery spots, Q3 dappled leaf light, Q4 moody bathroom light.
PHASE 4, MOOD: Q1 luxury lifestyle, Q2 editorial art, Q3 natural and organic, Q4 spa and intimate.
Swap variables: [SUBJECT] / [STYLE] / [CONTEXT]
This repository was inspired by outstanding open prompt collections and community-shared GPT-Image-2 experiments.
Thanks to the creators and contributors who shared their work publicly and made these case studies possible.
@BubbleBrain, @iam_miharbi, @Shinning1010, @patrickassale, @Zoulinshen, @WolfRiccardo, @Panda20230902, @liyue_ai, @blanplan, @4WEB1, @lilimliliychan, @Thereallo1026, @iamrednightS, @09lyco, @tsubaki_ew, @Toshi_nyaruo_AI, @yyu_hase, @austinit, @MrLarus, @rionaifantasy, @alanblogsooo, @SKA_Neotype, @desds1678, @samifox_ai, @HuliJason, @MikelEcheve, @chetaslua, @signedbywill, @zerolu_eth, @Cheney_NehcOal, @cnzoecomeback, @linxiaobei888, @old_pgmrs_will, @kotsu_kotsu_san, @samayousakadaru, @saskr_13, @kawai_design, @otohitoyuuki, @jrpj2010, @CEs7J0Mfn8x37k5
We cannot guarantee that every case is attributed to the original creator. If anything needs to be corrected, please contact us and we will update it.
If you have more interesting GPT-Image-2 prompt cases to share, feel free to reach out and help us expand the Evolink prompt library.
























































