🎬 Seedance 2.0 Global API is now live
No real-person verification required No queues - instant generation Welcome to try it now → No real-person verification required No queues - instant generation Welcome to try it now →

Prompt Lib

Curated AI prompts for stunning image and video generation. Updated daily from top creators.

Auto-curated from X

Filter by Type:

Filter by Model:

I tried this with Nano Banana. It tried but just wasn't that great. GPT Image 2
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

I tried this with Nano Banana. It tried but just wasn't that great. GPT Image 2

GPT Image 2 web cases prompt: I tried this with Nano Banana. It tried but just wasn't that great.

Prompt Preview

I tried this with Nano Banana. It tried but just wasn't that great. GPT Image 2 kind of nailed it Prompt: 2x2 grid, do this for 4 AI inferred themes and shapes Anchor: A perfectly organized top-down knolling flat-lay of every object associated with [Theme (e.g. a Surfer / a Baker / Tokyo / the 1980s)] ::4 Macro Shape: Objects arranged so their collective outline forms the silhouette of [Master Shape (e.g. a wave / a chef's hat / Mount Fuji)] — order within, meaning at the edge. Infer 20–30 fitting items ::5 Composition: Strict 90° grid alignment, even spacing, generous margin ::3 Material Physics: Real objects, soft studio shadows, consistent matte finish ::2 Illumination: Flat overhead softbox, no glare ::2 Render Stack: Knolling photography, organized-neatly aesthetic, product flat-lay ::1 Negative: [tilted objects, overlap, mess, motion blur, duplicate items, off-theme objects] :: -1

Prompt: Use the uploaded portrait only to preserve the person’s facial features,
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

Prompt: Use the uploaded portrait only to preserve the person’s facial features,

GPT Image 2 web cases prompt: Prompt: Use the uploaded portrait only to preserve the person’s facial features, face shape, skin tone, hairstyle, hair length, and overall identity. Do not copy the outfit from any example image.

Prompt Preview

Prompt: Use the uploaded portrait only to preserve the person’s facial features, face shape, skin tone, hairstyle, hair length, and overall identity. Do not copy the outfit from any example image. Choose a stylish outfit that naturally suits the person’s appearance and vibe, such as a modern city-night outfit with elegant textures, clean silhouette, and youthful fashion sense. Create a realistic cinematic night street portrait in a vertical three-frame photo strip layout. The scene takes place on a busy urban street at night, with soft flash photography, moving traffic in the background, blurred cars and buses, glowing storefront lights, street lamps, road markings, and tall residential buildings. The subject is walking or turning slightly toward the camera with a natural relaxed smile, long hair gently blown by the night wind, looking effortless and candid. Use a realistic handheld camera feeling, slight motion blur in the background, sharp focus on the face, natural skin texture, soft facial highlights, realistic eyes, subtle makeup, and a clean youthful mood. The overall style should feel like a real nighttime street snapshot taken with a phone or compact camera, with cinematic Hong Kong-style city atmosphere, warm urban lights, film grain, flash-lit subject, and natural imperfect realism. Each of the three frames should show a slightly different angle and moment of the same scene: close portrait, half-body side turn, and walking street portrait. Keep the same person consistent across all frames. The subject should look natural, not over-posed, not like a studio shoot. No watermark, no logo, no readable text, no brand names, no AI-generated marks. Negative Prompt: watermark, logo, text, readable signs, brand logos, bad anatomy, deformed face, distorted eyes, forced smile, plastic skin, over-smoothed skin, overly perfect beauty filter, doll-like face, anime style, cartoon style, extra fingers, deformed hands, duplicated person, inconsistent face, blurry face, low resolution, harsh overexposure, unnatural hair, messy composition, ugly clothing, copied outfit, white lace blouse, headband, unrealistic lighting, AI look, over-retouched portrait.

Realistic cinematic seaside bedroom fashion portrait, vertical. Adult woman seat
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

Realistic cinematic seaside bedroom fashion portrait, vertical. Adult woman seat

GPT Image 2 web cases prompt: Realistic cinematic seaside bedroom fashion portrait, vertical. Adult woman seated sideways on a wide white windowsill beside a large open ocean-view window, bright natural daylight, airy coastal editorial.

Prompt Preview

Realistic cinematic seaside bedroom fashion portrait, vertical. Adult woman seated sideways on a wide white windowsill beside a large open ocean-view window, bright natural daylight, airy coastal editorial. Slightly right of center, one leg bent forward, other resting downward out of frame. Torso slightly toward camera, head turned left looking out through the window toward the sea — calm, thoughtful, serene expression, lips softly parted, relaxed elegant posture. One hand on window ledge, other hand near knee. Subject: Fair smooth skin, soft sunlit glow. Natural fresh makeup: softly defined brows, subtle eyeliner, natural lashes, faint peach-pink blush, muted rose lips. Long dark brown hair loose and slightly wind-tossed, center-parted, flowing over one shoulder and drifting right as if moved by ocean breeze. Fine strands catching sunlight around face, neck, shoulders, collarbones. Outfit: Minimal white ribbed bralette/cropped camisole — thin spaghetti straps, soft V neckline, gathered seam details under bust, fitted textured band below chest. Matte lightweight softly ribbed fabric, realistic folds and subtle tension. Paired with high-waisted light blue denim shorts — visible belt loops, button closure, seams, pockets, slightly frayed edges. Relaxed, summery, coastal styling. Setting: Bright seaside room, large window open to the ocean. Left side: window glass and frame showing softly blurred blue water, pale sky, and distant shoreline waves. Right side: white sheer curtains billowing dramatically, lifted by the breeze, flowing translucent fabric shapes behind the subject. Interior minimal and bright — white window trim, pale walls, strong sunlight across the sill and body. Lighting and palette: Strong soft natural sunlight from left/front-left. Bright highlights on face, hair, shoulders, arms, abdomen, legs, bralette, denim, and window ledge. Gentle warm shadows along torso, under arm, and on ledge. Palette: white bralette, pale skin, blue denim, dark brown hair, ocean blue, soft sky tones, white curtains, sunlit cream walls. Subtle film grain, soft highlight bloom, natural fabric motion. Camera and finish: Face upper-right third looking toward sea, large window frame left, blurred ocean outside, white bralette upper-middle, denim shorts and bent leg lower-middle, hand on ledge lower-left, sheer curtains flowing right. Sharp focus on face/eye profile/lips/hair/collarbones/ribbed bralette/denim seams/hands/skin/window ledge/curtain folds/ocean reflections. 50–85mm, f/2.0, shallow DOF, bright coastal bedroom lifestyle editorial finish. No logo, no watermark, no text, no signature, no brand marks.

Use my uploaded portrait photo only as the identity reference for the person’s r
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

Use my uploaded portrait photo only as the identity reference for the person’s r

GPT Image 2 web cases prompt: Use my uploaded portrait photo only as the identity reference for the person’s real facial features, face shape, skin tone, hairstyle, hair color, and overall appearance. Preserve the person’s identity accurately and consistently across all four panels.

Prompt Preview

Use my uploaded portrait photo only as the identity reference for the person’s real facial features, face shape, skin tone, hairstyle, hair color, and overall appearance. Preserve the person’s identity accurately and consistently across all four panels. Do not copy the original background or clothing from my portrait photo. All other elements, including composition, poses, lighting, atmosphere, and visual style, should follow the reference image. Create a square 2×2 four-panel collage featuring the same person in four slightly different close-up or half-body outdoor portraits. The setting should be a bright summer garden, park, campus, or tree-lined outdoor space with soft green foliage, natural sunlight, gentle bokeh, and subtle dappled light. The overall mood should feel fresh, youthful, airy, natural, and candid, like high-quality smartphone photography. Four panels: Top left: a natural gentle smile, with one hand making a relaxed peace sign beside the face. Top right: a cheerful smile, with both hands forming a heart in front of the chest. Bottom left: a shy or surprised expression, with one hand lightly covering the mouth. Bottom right: a calm and soft expression, looking naturally at the camera with relaxed arms. Keep the same facial features, hairstyle, age, body proportions, and identity in every panel. Each frame should have slightly different expressions, head angles, hand gestures, and camera distance to avoid a duplicated or copy-pasted appearance. All poses should feel natural, relaxed, and anatomically correct. Do not fix the clothing to the reference image. Choose a flattering summer outfit based on the person’s appearance, hairstyle, age, and overall temperament in the uploaded portrait. The clothing should be light-colored, simple, fresh, feminine, natural, and suitable for an outdoor summer portrait. Maintain realistic skin texture, pores, fine facial details, natural hair strands, believable lighting, and accurate hands. Avoid excessive skin smoothing, exaggerated beauty filters, enlarged eyes, reshaped facial features, plastic skin, anime aesthetics, illustration, or 3D-rendered appearance. Realistic photography, natural daylight, smartphone portrait style, summer freshness, youthful lifestyle photography, 2×2 four-panel composition, consistent identity, high resolution, no text, no logo, no border, no watermark. Negative prompt: Do not change the person’s identity, facial structure, hairstyle, age, skin tone, or body proportions. No plastic skin, waxy face, anime style, cartoon style, illustration, 3D render, exaggerated expressions, heavy makeup, over-retouching, oversized eyes, pointed chin, excessive face slimming, duplicated poses, identical panels, distorted hands, missing fingers, extra fingers, fused fingers, deformed limbs, unnatural anatomy, blurry face, low resolution, overexposure, strong filters, artificial lighting, text, logo, signature, QR code, or watermark.

GPT Image 2: Photography style: Soft light CCD style Photo direction: Urban life photo
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2: Photography style: Soft light CCD style Photo direction: Urban life photo

GPT Image 2 prompt: Photography style: Soft light CCD style Portrait direction: Urban life style portrait Scene direction: Self-service laundry room / in front of the drum washing machine / beside the glass window at night Clothing direction: slim short vest + denim shorts + light shirt outer temperament label: vitality, relaxation, sense of life, refreshing, natural, close facial features: bright and energetic face Facial features details: small oval face, round almond eyes, natural lying eyes, bright eyes, naturally flat eyebrows...

Prompt Preview

摄影风格:柔光CCD风 写真方向:都市生活感写真 场景方向:自助洗衣房 / 滚筒洗衣机前 / 夜晚玻璃窗边 服装方向:修身短款背心 + 牛仔短裤 + 轻薄衬衫外搭 气质标签:元气、松弛、生活感、清爽、自然、亲近 五官方向:明亮元气脸 五官细节:小巧鹅蛋脸,圆润杏眼,卧蚕自然,眼神有光,自然平眉,鼻尖清秀,笑容轻快 发型方向:高马尾 发型细节:发量蓬松,额前碎发自然,发尾轻卷,整体清爽利落 身形方向:丰腴自然曲线 线条强调:中 镜头方向:半身到大腿 姿态动作:一只手扶着洗衣机门边,另一只手拿洗衣篮或饮料,身体轻微侧向镜头,笑着看向镜头 光线氛围:洗衣房冷白灯 + 夜晚窗外环境光 + 柔闪 滤镜效果:奶白高光 + 轻颗粒 + 清透CCD色彩 + 轻微过曝 画幅比例:9:16 补充要求:像夜晚洗衣房里被CCD相机随手拍到的一帧,真实、清爽、生活化,曲线自然好看

GPT Image 2: Picture generation: Prompt words for Vincent pictures given by the original author:
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2: Picture generation: Prompt words for Vincent pictures given by the original author:

GPT Image 2 prompt: Picture generation: Prompt words for the Vincent picture given by the original author: Simulate an outdoor Japanese theater performance shot from the audience's perspective. On the stage, a young Japanese actor who plays "Naruto" stands a few meters in front of another young actor who plays "Sasuke." The two people are clearly visible, and the picture quality is high-definition, showing that they are about to start a duel. But if you use this set of prompt words to generate, the pictures will be very similar, allowing AI to match them based on the theme...

Prompt Preview

图片生成: 原作者给的文生图提示词: 模拟一段从观众视角拍摄的户外日本戏剧演出画面。舞台上,一位饰演”鸣人“的年轻日本演员站在饰演”佐助“的另一位年轻演员前方数米处。两人清晰可见,画质高清,呈现出即将展开对决的姿态。 但是如果你用这套提示词生成,图片雷同性很高,可以让 AI 根据主题来匹配原动漫中的背景。 下图是我生成调试好的剧场底图👇 要点:底图必须是全景、人物对峙、2K/4K分辨率。画质直接决定视频最终效果。

GPT Image 2: Prompt words: Generate a 9:16 vertical version of a high-end personal care product
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2: Prompt words: Generate a 9:16 vertical version of a high-end personal care product

GPT Image 2 prompt: Prompt words: Generate a 9:16 vertical version of a high-end personal care product advertising poster. [Product type]: Sunscreen / Scalp essence / Deodorant / Cleansing mud mask / Body lotion / Fragrance spray / Hand cream [Brand name]: Customized brand name [Product name]: Customized product name [Core keywords]: SHIELD / ROOT / AURA / DETOX / G...

Prompt Preview

提示词: 生成一张 9:16 竖版高级个护产品广告海报。 【产品类型】:防晒霜 / 头皮精华 / 香体膏 / 洁面泥膜 / 身体乳 / 香氛喷雾 / 护手霜 【品牌名】:自定义品牌名 【产品名】:自定义产品名 【核心关键词】:SHIELD / ROOT / AURA / DETOX / GLOW / CALM 【主色调】:冰川蓝 / 鼠尾草绿 / 雾紫 / 炭黑岩灰 / 其他独立色谱 【成分或材质】:冰晶、水膜、玻璃柱、草本叶片、香氛雾气、岩石、矿泥、亚克力、陶瓷、金属等 【画幅】:9:16 竖版海报 画面风格为高级个护产品静物广告,极简、干净、轻奢、海报化,有国际 Campaign 视觉感。产品作为画面核心,放在画面中下部,主体清晰,包装设计简洁高级,材质真实,边缘干净。 围绕产品构建一个“成分 / 功效装置”: 不要只是把道具摆在旁边,而是让成分、材质和产品形成结构关系,比如护盾、防护屏障、垂直生长、香气环绕、岩层支撑、液体涂抹、透明折射、玻璃实验室结构等。让画面一眼能看出产品的功效概念。 背景保持干净,有大面积留白,使用柔和渐变背景和高级棚拍光线。画面中加入轻量白色字体系统:一个巨大的半透明英文关键词作为背景大字,例如 “SHIELD / ROOT / AURA / DETOX”;再加入少量小字号产品说明、系列编号、成分短句。文字要轻、薄、克制、有设计感,不要抢主体。 整体构图为 9:16 竖版海报,上方留白充足,中部展示产品与装置关系,下方可加入少量反射、材质、说明文字或品牌标识。画面要像一张完整的高级广告海报,而不是普通电商详情页。 质量要求:真实摄影质感,高分辨率,柔和棚拍光,真实材质,干净阴影,产品清晰,玻璃、液体、植物、岩石、陶瓷、金属等材质真实自然,整体高级、克制、有系列感。

se my uploaded portrait only as the identity reference. Accurately preserve the
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

se my uploaded portrait only as the identity reference. Accurately preserve the

GPT Image 2 web cases prompt: se my uploaded portrait only as the identity reference. Accurately preserve the subject’s real facial features, face shape, skin tone, hairstyle, hair color, hair length, and natural hair texture.

Prompt Preview

se my uploaded portrait only as the identity reference. Accurately preserve the subject’s real facial features, face shape, skin tone, hairstyle, hair color, hair length, and natural hair texture. Ensure that the same recognizable person appears consistently in every panel. Do not copy the background, pose, composition, clothing, or lighting from the uploaded portrait. Create a five-panel spring portrait collage in a vertical 3:4 format, set in a vast field of golden-yellow rapeseed flowers or wildflowers. The flowers should look dense and natural, with soft background blur and a fresh, warm atmosphere. Use gentle spring sunlight, with a color palette dominated by golden yellow, creamy white, and soft green. The overall style should feel like natural Japanese-inspired portrait photography with a subtle vintage film look. Keep the subject, clothing, environment, lighting, and visual tone consistent across all five panels: Top-left: a close-up portrait with the subject gently resting her face on her hands, looking calmly toward the camera with a soft, natural expression. Top-right: a side-profile close-up, with the subject looking into the distance and smiling subtly while a light breeze moves a few loose strands of hair. Center: a wide horizontal half-body shot, with the subject leaning slightly toward the flowers, looking down at them or gently smelling the blossoms. Bottom-left: a medium shot of the subject standing naturally in the flower field, holding a small bouquet of yellow flowers while turning slightly toward the camera. Bottom-right: a distant back-view shot of the subject walking or standing deeper in the flower field, creating a quiet, cinematic sense of space and story. Do not copy the exact outfit from the reference image. Select clothing that naturally suits the uploaded person’s appearance, hairstyle, and overall temperament. Use light, soft spring colors such as cream, ivory, pale yellow, or other low-saturation warm tones. Keep the design elegant, simple, and free of distracting patterns. Small yellow flowers may be added naturally to the hair without changing the original hairstyle or covering the face. Use realistic portrait photography, a medium telephoto lens, shallow depth of field, soft creamy bokeh, and gentle natural lighting. Preserve real skin texture, pores, fine facial hair, and individual hair strands. Expressions and poses should feel relaxed, subtle, and candid. Maintain accurate facial proportions, natural hands, and correct body anatomy. The final image should look like a professional spring flower-field photoshoot, not a digital illustration. No plastic skin, no excessive retouching, no anime style, no artificial facial features, and no obvious AI-generated appearance. Keep the collage clean and cohesive, with no text, logo, signature, border, or watermark. Negative Prompt: anime, illustration, cartoon, 3D render, plastic skin, waxy face, excessive smoothing, synthetic face, facial distortion, inconsistent identity, changing facial features, altered hairstyle, age change, exaggerated expression, stiff pose, unnatural posing, empty eyes, duplicated facial features, extra people, repeated subject, deformed hands, extra fingers, missing fingers, incorrect anatomy, distorted limbs, unnatural body proportions, tangled hair, clothing deformation, flowers covering the face, overexposure, excessive sharpening, cheap filter, heavy makeup, cluttered background, text, subtitles, logo, signature, watermark

GPT Image 2 Themed Poster Layout Design: Bold Typography & Visual Identity
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2 Themed Poster Layout Design: Bold Typography & Visual Identity

Flat illustration, high-end oriental fantasy style city poster design, vertical 9:16 composition. The layout uses a diagonal + S-shaped flow extend...

Prompt Preview

Flat illustration, high-end oriental fantasy style city poster design, vertical 9:16 composition. The layout uses a diagonal + S-shaped flow extending from the bottom left to top right. The background is deep black grading down to intense dark red, creating strong warm-cool contrast and spatial depth with faint stardust and grain texture. In the center, a flowing golden energy line winds through like a flame, extending upward from the base, featuring fluid texture, particle effects, and gradient highlights, with subtle energy debris and volumetric light. Within the golden flow, the architectural landmarks of {argument name="city" default="Guangzhou"} emerge layer by layer: the Canton Tower is the visual core with prominent proportions, surrounded by the Zhujiang New Town skyline, Liede Bridge, and modern Lingnan architectural elements. Buildings are rendered using "fine line drawing + golden luminous blocks," with clear outlines and rich details, appearing to float in a void against the golden halo, creating a surreal spatial hierarchy with slightly fogged backgrounds for added depth. At the bottom of the frame is an oriental white-haired female figure with flowing hair like mist, naturally connecting and merging with the golden light. Her hair is translucent with gradient light effects; she has a graceful posture, eyes closed, and a serene expression, holding a bouquet of colorful flowers dotted with shimmering particles, symbolizing the spiritual connection between people and city energy. Character details are moderately simplified to emphasize the overall design. Lighting is concentrated on the golden flow, buildings, and character outlines, creating intense chiaroscuro and visual focus. The overall atmosphere is grand, mysterious, imbued with oriental mythology, and slightly healing. Colors use black and dark red as a base with brilliant gold as the main visual emphasis. The gold has rich light-dark layers, complemented by small areas of high-saturation floral colors, maintaining a sophisticated and restrained aesthetic. Integrated text and layout: Centered Songti font at the top reads "{argument name="city" default="Guangzhou"} · China," followed by smaller text "{argument name="date" default="2026/04/20"}" and "{argument name="author" default="LIYUE"}" below. Text uses pale gold or soft warm white, unified with the overall lighting. High-quality details, cinematic lighting, rich volumetric and particle details, clean image without noise, ultra-high 8K resolution, commercial-grade poster quality.

Previous Page 59 of 632 Next