차량 프롬프트 예시

A highly stylized 3D caricature of the person in the uploaded image, with expressive facial features, and playful exaggeration. Rendered in a smooth, polished style with clean materials and soft ambient lighting. Bold color background to emphasize the character’s charm and presence.

generate a detailed infographic that explains the 4 seasons as experienced in Toronto, Canada. The infographic is for a grade 3 classroom. Make it in the style of Eric Carle

一个极端鱼眼镜头拍摄的照片。金发双马尾的年轻女子穿着灰色开衫和格子裙校服，在涩谷十字路口兴奋地跳起，一只手夸张地伸向镜头前景，手指甲清晰可见。背景中，扭曲的涩谷109大楼和其他建筑林立，街道上挤满行人和车辆。巨大的粉色和蓝色渐变卡通怪兽漂浮在城市上空，巨大的触手和角环绕着扭曲的城市景观。阳光明媚，光影对比强烈。圆形画幅。

A highly stylized 3D caricature of [celebrity], with an oversized head, expressive facial features, and playful exaggeration. Rendered in a smooth, polished style with clean materials and soft ambient lighting. Minimal background to emphasize the character’s charm and presence.

A visual explosion in the middle of a fast-moving street. Frozen faces, sweeping movements, and a palpable "noir" atmosphere. Everything is planned, yet the results are always wild and raw.

<instruction> (指令) 分析输入图像的整个构图。识别所有存在的关键主体（无论是单人、群体/情侣、车辆还是特定物体）及其空间关系/互动。 生成一个连贯的 3x3 网格“电影印样（Contact Sheet）”，展示在同一环境中完全是这些主体的 9 个不同镜头。 你必须调整标准的电影镜头类型以适应内容（例如，如果是群体，保持群体在一起；如果是物体，构图包含整个物体）： 第 1 行（建立背景）： 大远景 (ELS)： 主体在广阔的环境中显得很小。 全景 (LS)： 完整的主体或群体从上到下可见（从头到脚 / 从车轮到车顶）。 中远景 (美式镜头/四分之三)： 构图从膝盖以上（针对人物）或 3/4 视角（针对物体）。 第 2 行（核心覆盖）： 4. 中景 (MS)： 构图从腰部以上（或物体的中心核心）。聚焦于互动/动作。 5. 中特写 (MCU)： 构图从胸部以上。主要主体的亲密构图。 6. 特写 (CU)： 紧凑构图于脸部或物体的“正面”。 第 3 行（细节与角度）： 7. 大特写 (ECU)： 强烈聚焦于关键特征（眼睛、手、标志、纹理）的微距细节。 8. 低角度镜头 (仰视/虫眼)： 从地面仰望主体（壮观/英雄感）。 9. 高角度镜头 (俯视/鸟瞰)： 从上方俯瞰主体。 确保严格的一致性：所有 9 个面板中是相同的人物/物体、相同的衣服和相同的光照。景深应逼真地变化（特写镜头中的背景虚化）。 </instruction> 一个包含 9 个面板的专业 3x3 电影故事板网格。 该网格以全面的焦距范围展示输入图像中的特定主体/场景。 顶行： 宽广环境镜头，全视图，3/4 剪辑（膝上景）。 中间行： 腰部以上视图，胸部以上视图，脸部/正面特写。 底行： 微距细节，低角度，高角度。 所有帧均具有照片般逼真的纹理，一致的电影级调色，以及针对所分析的主体或物体特定数量的正确构图。

Create a photo of me 240 leaning my back out the window car like a dark dreamy blurry vintage windy night wearing a off shoulder white knitted top. With brown long wavy hair. keep the facial details correctly. Please do not alter facial features and leave head positioning as is.

[Image_Specifications] Type = Realistic Portrait Style = Douyin Aesthetic Resolution = High Quality [Subject_Details] Demographics = Young Asian woman Facial_Structure = 100% original face (no editing) Hair_Texture = Straight, shiny Hair_Color = Black Hair_Length = Long [Makeup_&_Styling] Style = Douyin-style Eye_Makeup = Highlights large eyes, long eyelashes Cheeks = Rosy Nails = Long, painted beautiful dark black [Apparel_&_Accessories] Eyewear = Thin silver-framed eyeglasses Top = Black strapless top with a single strap Waist_Accessory = Brown and gold striped fabric belt (tied in a bow) Necklace = Small silver Vivienne Westwood Orb pendant [Pose_&_Expression] Action = Taking a selfie Angle = From above Right_Arm = Raised, holding the phone Left_Hand = Holding a round black lollipop Expression = Confident gaze, tongue slightly sticking out [Environment_&_Background] Location = Outdoor parking lot Time_of_Day = Night Ground_Surface = Gray concrete with white parking lines Featured_Vehicle = Black Bugatti (visible grille and bumper) Lighting_Conditions = Dimly lit by street lamps and distant city lights

Generate a photorealistic image of a cafe terrace in the Marais district of Paris on a Wednesday morning in March 2025. It is a crisp, cool spring morning with clear skies. Locals are drinking coffee. In sharp focus should be a young woman with a pixie cut wearing a scarf, stirring a cappuccino and looking thoughtfully to the side; the waiter and street traffic behind her are blurred. The photo should have the candid, natural morning light feel of an iPhone image.

Use the uploaded photo as the base. Keep the person’s **face, eyes, hairstyle, makeup, outfit, and overall identity** clearly recognizable and photorealistic. Do NOT turn the whole image into a drawing. Do NOT replace or redraw the background; only transform the perspective as needed. =================================================== TRANSFORM THE POSE — EXTREME “JOJO-STYLE” POSES =================================================== Repose the body into a **randomized, exaggerated JoJo-style pose**, pushing the limits of human flexibility: - extreme torso twist, strong contrapposto - head tilt with dramatic confidence - one hand framing the face, one arm extended or arched - bold leg positions (crossed, wide stance, pointed toes) The pose must be: - anatomically plausible but exaggerated like JoJo - stylish, flamboyant, theatrical Maintain realistic lighting and natural cloth deformation. =================================================== APPLY EXTREME CAMERA ANGLES (RANDOM EACH TIME) =================================================== Transform the camera viewpoint to create striking JoJo-style drama: Choose **one random angle** from the following list for each generation: - **Ultra low-angle (“仰ぎ見”) shot**: camera near the ground looking upward - **Ultra high-angle (“見下ろし”) shot**: camera directly above looking down - **Dynamic wide-angle (20–24mm)**: strong perspective distortion - **Super wide-angle (14mm)** for extreme depth & stretched limbs - **Fisheye lens effect** with curved perspective lines - **Dutch-angle (tilted horizon)** for manga-like tension - **Close-up with forced perspective**: large foreground hand reaching toward the camera - **Long-lens compression (85–135mm)** but still JoJo dramatic Rules: - The face must remain recognizable and photorealistic in the new angle. - The background may be warped to match the new perspective, but must remain the same scene. - No cartoon effects on the person themselves. =================================================== ADD MANGA-STYLE SFX (JOJO ONOMATOPEIA) =================================================== Add dramatic Japanese SFX in bold black-and-white ink lines: - 「ゴゴゴゴゴ…」 - 「ドドドドド…」 - 「ズキューーーン！」 - 「バァーーーン！！」 - 「メメタァ！」 - 「ガオンッ！」 Place them: - floating behind the person - along the sides of the pose - integrated with the new camera angle perspective Do NOT cover the person’s face. =================================================== OPTIONAL MANGA LINES =================================================== Add subtle JoJo-style: - speed lines - radiating impact lines - perspective shock lines But keep the original background visible through them. =================================================== FINAL GOAL =================================================== Create a realistic photo where: - the person remains fully recognizable, - their body is transformed into a bold, dramatic JoJo-style pose, - the camera angle is extreme and cinematic (low-angle, high-angle, fisheye, wide-angle, etc.), - powerful manga SFX surround them in true JoJo fashion. The image should feel like a **JoJo splash page happening inside a real photograph**.

Full body [SUBJECT] toy, [ATTRIBUTES/ACCESSORIES], [EXPRESSION], made of felt, in a [PLACE], [LIGHTING], friendly and cartoonish appearance, rich and soft textures.

[object Object]

A highly stylized 3D caricature of the person in the uploaded image, with expressive facial features, and playful exaggeration. Rendered in a smooth, polished style with clean materials and soft ambient lighting. Bold color background to emphasize the character’s charm and presence.

{ "style": { "type": "hand-drawn caricature", "technique": "cross-hatching, fine ink lines", "mood": "serious, slightly exaggerated expression", "medium": "black and white sketch" }, "subject": { "type": "male figure", "age": "middle-aged", "skin_texture": "detailed line work with emphasized shading", "hair": { "style": "short, tightly curled", "texture": "dense linework" }, "facial_features": { "eyes": "narrow, expressive, slightly squinting", "eyebrows": "furrowed, showing intensity", "nose": "long and defined with accentuated shading", "mouth": "exaggerated downward curve, caricatured pout", "ears": "large and prominently exaggerated", "jawline": "elongated and structured with sharp lines" } }, "composition": { "pose": "straightforward headshot with slight tilt", "framing": "upper torso visible, suit collar included", "background": "clean white, no elements" }, "clothing": { "attire": "formal suit", "details": "sharp collar lines with textured shading" }, "notes": { "emphasis": "hyper-exaggeration of facial structure", "aesthetic": "editorial political-cartoon style" } }

A [SUBJECT] is crouching on the beach, lifting a wave like a carpet to reveal a [OBJECT] lying underneath deep inside. The ocean is calm with a clear blue sky in the background. The scene creates a clever illusion, in a surreal manner, with the wave being lifted as if it is a tangible object

This is a whimsical【 orange-and-green】 fantasy castle crafted from 【Fanta 】bottle labels. The scene includes playful dragons and soda-themed airships — humorous yet surprisingly detailed, radiating an unexpected sense of magic.1080×1080

3×2 collage of six stylized 3D caricature portraits of [name], each with a different expressive pose (joyful, surprised, serious, cute, sassy, confident). Smooth polished look, soft ambient lighting, clean character design, and bold vibrant backgrounds for each panel.

Luxury portrait of the uploaded image, 100% same face identity. Bright, clean exposure with soft studio lighting, balanced brightness, natural highlights on face and eyes, smooth shadow falloff. Ultra-realistic skin texture, sharp detailed eyes, natural hair strands, high-detail fabric. Clean elegant background with soft depth of field. Premium cinematic color grading, rich natural colors. Full-frame DSLR look, 85mm f/1.8, 8K ultra-realistic, no cartoon, no over-smoothing, no face change.

A dynamic aerial view of a bustling city street, focusing on a miniature [BRAND] store. The camera performs a smooth, sweeping dolly in towards the storefront, capturing the vibrant activity of pedestrians, cyclists, and vehicles. Bright daylight illuminates the scene, highlighting the distinctive branding and merchandise displayed in the window. The atmosphere is lively and energetic, with a playful, miniature aesthetic that emphasizes the intricate details of the cityscape. 1080x1080 dimension.

a faithfully illustrated Christmas card design featuring the couple in Christmas hats, and the text "Happy Christmas 2025", it is friendly and traditional, with a classical design, in a winter wonderland