FastArt.ai
30,883 厳選プロンプト

プロンプトライブラリ

9,106 件 · ページ 246 / 380
IMAGE · chatgpt

垂直三格校园胶片感长发女孩

A vertical 3-panel college photo strip. The subject is a girl with long hair in a beige knit vest. Panel 1(top): close up of her resting chin on the school desk, looking bored. Panel 2(middle): her standing against a white class wall, holding a book, slightly motion blur. Panel 3(Bottom): sitting on the wooden floor, trying shoelace. Aesthetic: Korean 2000s phone -camera quality, s' arm tint, slightly low resolution ow handwritten doodle overlay, Harsh flash.

IMAGE · chatgpt

便利店购物年轻女性写实人像

{ "image_generation": { "subject": { "description": "young woman shopping in a convenience store", "pose": "standing in a side profile position, slightly turned toward the right shelf", "expression": "natural candid expression, focused on comparing products", "action": "reading the label of a small bottle while holding another product" }, "appearance": { "hair": { "color": "dark brown", "style": "casual messy bun", "accessories": ["sunglasses resting on top of head", "small earrings"] }, "makeup": "neutral natural makeup", "skin": { "texture": "realistic skin texture", "tone": "natural" } }, "outfit": { "top": "fitted cream beige scoop-neck short-sleeve top", "bottom": "light gray leggings", "bag": "large patterned designer-style tote bag hanging from shoulder" }, "environment": { "location": "modern Southeast Asian convenience store", "setting": "brightly lit retail aisle", "background_elements": [ "colorful personal care products", "household items", "product shelves on both sides", "fluorescent ceiling lights", "narrow aisle" ], "atmosphere": "authentic retail environment" }, "camera": { "framing": "medium-full body shot", "angle": "eye-level", "perspective": "35mm lens", "composition": "vertical 4:5, subject centered slightly left of frame", "depth_of_field": "shallow depth of field with soft background blur" }, "lighting": { "type": "soft diffused fluorescent lighting", "shadows": "realistic indoor shadows" }, "style": { "genre": "documentary lifestyle photography", "aesthetic": "unposed snapshot aesthetic", "colors": "natural colors", "quality": "ultra-realistic RAW photo quality", "resolution": "4K", "focus": "sharp focus" } } }

IMAGE · chatgpt

唯美沙滩奔跑东亚女性人像摄影

9:16 vertical photorealistic beach running portrait. An adult East Asian young woman, 20–25 years old, sweet youthful look, natural joyful smile, direct eye contact with the camera, running toward the lens through shallow waves. Casual lightly wet but opaque short-sleeve shirt, dark pleated skirt, barefoot. Wind-blown hair, light splashes around the feet, face clear and natural. Real candid handheld photo feeling, slight motion blur only on the image edges, waves, splashes and hair strands. Natural matte skin, real skin texture, no oily highlights, no glossy face, no plastic skin, no heavy retouching, no AI influencer face. Create separate variations: overcast wind, soft pink dusk, golden sunset, blue-purple twilight. Avoid face looking away, side-running pose, wet hair covering the face, water splashes covering the face, over-polished lighting, strong glow, dreamlike filter, CGI look, distorted hands or legs.

IMAGE · chatgpt

高细节角色设定图与表情拆解

Based on this character [[ character name ]] create a high detailed character sheet ・Include 4-view diagrams: full body front, side, half body shot, and back ・Add variations of the character's facial expressions ( 4 variations ) ・Break down and display detailed parts of the costume ・Add a color palette Add a large close up shot of the face Add a description of his personality , All the descriptions write it in Japanese ・Overall, use an organized layout (white background, illustrative style) High resolution, professional concept art style 4k quality , cel shading

#角色设定#赛璐璐#四视图
IMAGE · chatgpt

甜点屋悬浮特效动感人像摄影

Use the uploaded portrait only as the identity reference. Accurately preserve the person’s real facial identity, face shape, facial features, skin tone, hairstyle, hair volume, and natural real-life appearance. Do not copy the original background, lighting, clothes, pose, or image quality from the uploaded portrait. Create a highly realistic vertical wide-angle action portrait in an indoor dessert shop or café. The subject is crouching low toward the camera in a dynamic playful pose, with one hand stretched very close to the lens, palm facing forward, creating strong foreground perspective and mild wide-angle distortion. The other arm is lifted upward in an energetic motion. The head is slightly lowered, with a casual cap or suitable accessory partially shadowing the upper face, but the visible facial features must still match the uploaded person naturally. Around the subject, several desserts appear suspended in mid-air: rolled crepes, layered tiramisu cake slices, rainbow cake, cream splashes, cocoa powder, crumbs, and milk-like dessert cream exploding around the foreground. The effect should feel like a frozen high-speed photography moment, playful and surreal, but still physically believable. Add realistic splashes on the floor and in the air, with natural motion direction, depth, and perspective. Generate suitable clothing automatically based on the uploaded person’s appearance and style. The outfit should feel casual, youthful, comfortable, and visually compatible with the dessert shop scene, but do not fix the exact clothing. Avoid logos, readable brand names, or watermarks on clothing or background. Use a low-angle camera close to the floor, vertical 3:4 composition, ultra-wide lens feeling, strong foreground hand perspective, dynamic depth, realistic indoor ceiling lights, soft ambient café lighting, natural shadows, realistic skin texture, slight motion energy, high-resolution commercial creative photography style. The image should look like a real camera photo with a creative advertising concept, not an anime image, not a plastic AI render, and not overly polished. Negative Prompt: watermark, logo, text, brand name, Chinese watermark, AI watermark, anime, cartoon, illustration, 3D render, plastic skin, overly smooth skin, doll-like face, fake face, over-beautified features, wrong identity, different person, distorted face, extra fingers, missing fingers, broken hand, unnatural palm, deformed limbs, messy anatomy, floating objects without perspective, unrealistic dessert scale, low quality, blurry face, bad lighting, harsh overexposure, pasted face, collage look, duplicated person, unreadable text, cluttered background, dirty floor, horror expression, uncanny valley.

IMAGE · chatgpt

现代韩系GenZ风薰衣草色时尚拼贴广告

Create a vibrant fashion collage advertisement inspired by modern K-fashion and Gen-Z social media aesthetics. Lavender (Light Purple) background mixed with cream white and soft gold accents. Same college girl appears in multiple trendy outfits and playful poses. Include selfie snapshots, candid walking frames, mirror photos, campus streetwear looks, and luxury portrait photography. Dynamic overlapping layouts, torn magazine edges, polaroid frames, doodles, stickers, social-media-inspired graphics, Viral Instagram and X aesthetic, ultra-realistic fashion campaign.

IMAGE · chatgpt

现代清爽西瓜青柠饮品商业宣传海报

Create a premium modern beverage promotional poster for We Drink. TOPIC: Watermelon Pink + Lime Green Refresh Campaign STYLE & ART DIRECTION: Modern energetic beverage advertising Youthful commercial branding Split-color background composition Bright refreshing summer aesthetic Minimal dynamic layout High-contrast drink advertisement style Instagram-ready beverage promotion Premium fast-moving commercial design MAIN SUBJECT: Two large ultra-realistic cold beverages positioned prominently in the center. Drink 1: A vibrant watermelon pink drink in a transparent plastic cup with visible ice cubes, condensation droplets, and a fresh watermelon garnish. Drink 2: A bright lime green drink in a matching transparent cup with visible ice cubes, condensation droplets, and a lime slice garnish. Additional elements: Floating ice cubes around the composition Dynamic water splash effects Soft realistic shadows beneath each cup Premium glossy liquid textures Tiny fruit slices suspended in motion LAYOUT & COMPOSITION: Diagonal split-color background Left side: watermelon pink gradient Right side: lime green gradient Large bold headline at the top center: “SIP THE FRESHNESS” Two hero drinks centered prominently Product descriptions placed beside each cup Promotional price section near the bottom-left We Drink logo and small branding elements at the bottom Floating ice cubes and splash effects around the drinks Spacious modern commercial hierarchy TEXT & TYPOGRAPHY: Bold oversized sans-serif typography Youthful rounded commercial fonts White typography accents Supporting text: “Watermelon Burst” and “Lime Rush” Promotional price: Only $3.99 Tagline: “Freshness in Every Sip” DEPTH & LIGHTING: Soft glossy studio lighting Bright refreshing reflections Realistic beverage highlights Floating commercial depth Soft ambient shadows Premium condensation texture lighting EXTRA DESIGN DETAILS: Floating ice cubes Water splash particles Glossy gradients Modern promotional badges Fruit slices and droplets Minimal energetic decorative elements COLOR PALETTE: Watermelon Pink (#FF4F87) Lime Green (#A8FF2A) White typography Soft transparent highlights QUALITY: Ultra-realistic beverage photography, premium advertising composition, Behance-quality commercial poster, high-resolution, sharp focus, photorealistic textures, professional brand campaign aesthetic.

IMAGE · chatgpt

褶皱织物透视文字排版时尚海报

Vertical editorial poster portrait of [CHARACTER] with [HAIR], face tightly framed behind crumpled [FABRIC], oversized bold condensed sans-serif typography cut through the fabric spelling “[SPLIT]” in stacked syllables across the whole image, eyes, nose and lips visible through the letter openings, small vertical side word “[SIDE]”, tiny barcode block near the lower right, high-fashion beauty lighting, realistic skin texture, soft shadows in the folds, muted [PALETTE], clean magazine-cover composition, sharp typography hierarchy, premium print finish, no extra words, no messy layout, no cartoon style, no 3D render, ar 4:5

IMAGE · chatgpt

超写实旅游美食明信片合成摄影

Create a hyper-realistic travel-food postcard scene. INPUTS: City: [CITY NAME] Local Delicacy: [LOCAL DELICACY] Background Location: [BACKGROUND LOCATION OR LANDMARK] SCENE: A real human hand is holding a vintage travel postcard in the foreground. Inside the postcard is a large, beautifully styled, ultra-realistic food photograph of [LOCAL DELICACY], captured like premium food advertising. The dish should appear larger than life, with rich textures, realistic details, appetizing presentation, natural lighting, subtle steam, shallow depth of field, and cinematic food photography. A single miniature traveler wearing a backpack sits naturally on the top edge of the postcard with legs dangling over the front. The traveler should be realistic, highly detailed, and positioned so they appear to be admiring the local delicacy. The miniature traveler acts as the emotional focal point and creates a strong sense of scale and wonder. Outside the postcard is the authentic destination environment of [BACKGROUND LOCATION OR LANDMARK] in [CITY NAME]. The background should feature recognizable local architecture, streets, scenery, cultural elements, landmarks, atmosphere, colors, and visual details unique to the destination. Include a rustic wooden directional signpost naturally integrated into the environment. The signpost must automatically generate four short destination-specific labels based on the city, culture, attractions, food scene, landmarks, neighborhoods, natural features, or travel experiences associated with the location. The generated signboards should feel authentic to the destination and enhance the travel storytelling. Composition hierarchy: Miniature traveler Local delicacy inside postcard Destination background Destination signpost Style: Hyper-realistic photography, luxury tourism campaign aesthetic, cinematic storytelling, authentic destination atmosphere, realistic hand, realistic miniature traveler, highly detailed food photography, natural golden-hour lighting, shallow depth of field, rich colors, editorial travel magazine quality, Instagram-worthy social media content, visual wow factor, vertical 4:5 aspect ratio, extremely detailed, premium commercial advertising.

IMAGE · chatgpt

硬核老奶奶地狱猎魔战

on a 3x2 grid create a detailed gaming screens sheet for a highly detailed 3d game of a cool old granny with a pumpgun who hunts demons in hell. the game is a AAA game. include the following screens: 1) a text that explains the game idea and mechanic 2) a startscreen with the character on white background and start and menu options, 3) a character creator screen with 2 outfit and 2 head choices, 4) a weapons skin screen with 2 more pumpgun screens (one nuclear themed, the other lava themed), 5) a ingame third person screen of the fight, 6) a ingame first person crafting screen with pumpgun upgrades,

#老奶奶#猎恶魔#霰弹枪
IMAGE · chatgpt

窗边光影超写实美女高级感特写肖像

Ultra-realistic beauty portrait captured in a tight close-up with a full-frame mirrorless camera and an 85mm f/1.4 portrait lens. A beautiful young woman with long straight dark hair, luminous fair skin, subtle natural freckles across the nose, thick well-groomed eyebrows, long curled eyelashes, and striking light blue-green eyes gazes softly toward the camera with a calm, relaxed expression and slightly parted glossy nude lips. She wears minimal "no-makeup" makeup with natural skin texture preserved and small gold hoop earrings. The composition fills almost the entire frame with her face, leaving very little background visible. Dramatic natural sunlight streams through a nearby window, creating a bold diagonal shadow across one side of her face while illuminating the other side with soft golden light. High dynamic range, cinematic contrast, crisp skin detail, realistic pores, catchlights in the eyes, shallow depth of field, soft blurred neutral background, editorial beauty photography, luxury skincare campaign aesthetic, ultra-photorealistic, 8K, HDR, natural color grading, razor-sharp focus on the eyes, premium fashion magazine quality.

IMAGE · chatgpt

自然纹理与巨型文字融合的摄影海报

Generate a visual work based on any subject that features dense natural textures and a text integration mechanism: the material, environment, or cultural symbols of the subject fill the entire frame, forming a close-up, layered, and detail-rich continuous background. The subject does not appear as an isolated object, but as a texture field for the viewer to immerse in; the primary visual reading is carried by a giant bold title positioned slightly below the center, with heavy, rounded, and clean letterforms. White or high-brightness information colors derived from the theme create a clear contrast with the background, with the edges of the title allowing a small amount of background texture to intersperse, overlap, or cut into the strokes, so the text appears embedded in the theme field rather than pasted on. Three small all-caps informational tags are kept at the top, arranged dispersedly with slightly wide letter spacing; a small curved text rhythm is added above the central title, and two short sentences and a page-number-style micro-info are used below to create pauses, with a tiny signature at the bottom. The overall information hierarchy moves from sparse to heavy and back to quiet. Colors are extracted from the material, season, mood, and narrative of the subject, retaining a large area of low-brightness but optically clean base color field, while a medium-brightness detail layer handles the texture undulations, and a small amount of high-brightness information colors is used only for text and key highlights; saturation is restrained, light and dark levels are clear, and shadows are transparent and not muddy, keeping the mood clear, quiet, immersive, and breathable. The background requires realistic detail density, slight grain, and a softly darkened photographic texture, avoiding vague illustration, decorative borders, and over-nostalgic dirty colors. —————— (The following are defined by you) Center text: a four-character motto Background environment: Environments favored by top-tier nature magazines Continuously generate 10 images, each following a different variation logic for the above instruction themes (background environment + four characters), as well as background color schemes, hue logic, and color logic. Note: do not use serial numbers. Similar to PPT, generate 10 images, ensuring differences between each other. Ratio 16:9 Special emphasis: The text and environment color schemes for each image must be different!!!

IMAGE · chatgpt

超饱和卡通剪纸立体模型

{ "VARIABLE": "[CARTOON_SHOW_NAME]", "concept": "Hyper-saturated physical paper cut-out diorama of the world of [CARTOON_SHOW_NAME] — maximalist, eye-level dead-center straight-on view, bleed-to-edge, no outer frame, no border, no tray", "style": { "medium": "thick layered cardstock — every depth plane physically stacked, hard knife-cut silhouette edges with exposed cross-sections at every layer break", "texture": "matte fibrous paper grain visible on all surfaces, no gloss, no sheen", "approach": "maximalist composition — every depth plane densely packed with characters, props, architecture and world-specific items from [CARTOON_SHOW_NAME]" }, "palette": { "rule": "Extract the 3 most iconic colors from [CARTOON_SHOW_NAME] as dominant hues, extract 3 secondary signature colors as accents", "saturation": "nuclear maximum — every hue pushed to absolute vivid limit", "finish": "matte throughout — no metallic, no gloss, no reflective surfaces regardless of subject matter" }, "depth_planes": { "rule": "Build exactly 8 stacked depth planes from the world of [CARTOON_SHOW_NAME] as follows:", "foreground_base": "Small iconic props, collectibles, and world-items from [CARTOON_SHOW_NAME] scattered and crowding the base plane edge", "layer_2": "The single most iconic protagonist character from [CARTOON_SHOW_NAME] as the central figure — frozen mid-signature-action, built entirely from stacked paper geometry", "layer_3": "The 2–3 closest supporting characters from [CARTOON_SHOW_NAME] each occupying their own isolated depth card, frozen mid-characteristic-pose", "layer_4": "The primary antagonist or rival from [CARTOON_SHOW_NAME] as a dominant stacked paper silhouette on an isolated depth card", "layer_5": "The most iconic building or location interior from [CARTOON_SHOW_NAME] — rendered as layered paper architectural strips with punched-void windows and doors", "layer_6": "Secondary characters and crowd figures from [CARTOON_SHOW_NAME] as flat die-cut paper silhouettes threading between architectural layers", "layer_7": "Signature special effects, powers, or world-specific phenomena from [CARTOON_SHOW_NAME] as concentric paper ring cutouts or radiating die-cut shapes", "background_layer_8": "Skyline, landscape, or world-panorama silhouette from [CARTOON_SHOW_NAME] as a monochrome cut-panel — progressively lighter paper tone" }, "lighting": { "type": "single-direction hard studio key light only", "angle": "top-left, 45 degrees", "shadow": "crisp, deep, hard drop-shadows between every physical paper layer — shadow depth must visually communicate the stacking distance", "NO": [ "glow", "bloom", "soft edges", "gradients", "volumetric light", "atmospheric haze", "bounced color", "lens flare", "any light emanating from characters or effects" ] }, "composition": { "density": "maximalist — zero empty space across all depth planes", "focal_anchor": "protagonist centered at exact optical midpoint of the frame", "framing": "bleed-to-edge on all four sides — no border, no outer frame, no shadow box, no tray, no display case", "perspective": "perfectly flat orthographic eye-level view — no tilt, no isometric angle, no fisheye" }, "render": { "engine": "Octane Render", "resolution": "8K", "detail": "ultra-sharp at 100% zoom — paper fiber, cut-edge thickness, and layer shadow all crisp", "aspect_ratio": "3:4 portrait" } }

#纸雕#剪纸风#立体画
IMAGE · chatgpt

日本时尚杂志三连拼摄影排版

The final output is a 9:16 vertical Japanese fashion photo magazine page (Portrait 9:16). Using a Japanese Fashion Editorial Layout, the entire page consists of three different photography works, separated horizontally by two extremely thin black lines. Important: Not one photo with three black lines drawn on it. Not crops of the same photo. Not repetition of the same pose. Not Split Screen. Not Storyboard. Must first generate three completely independent photography works, then automatically layout and combine them into one 9:16 magazine page (Composite Editorial Layout). The three photos belong to: The same girl The same outfit The same shooting space The same set of lighting But camera angles, poses, expressions, and compositions are all different, forming a continuous cinematic reading rhythm. 【First Photo (Top)】 Portrait Close-up (Chest-up close-up) The girl leans forward slightly, twin tails falling naturally, eyes looking directly at the camera, smiling gently, her gaze carrying a bit of girlishness and a sense of communication. Camera distance approximately 70cm 85mm portrait lens The background retains the laundromat environment but is significantly blurred The character takes up about 70% of the first frame 【Second Photo (Middle)】 Hero Shot (Visual center of the entire set) 24mm cinematic wide-angle lens Slightly low camera angle The girl supports herself on a transparent acrylic tabletop with both hands, leaning naturally toward the camera, creating strong spatial perspective The character takes up about 80% of the second frame The most abundant action, the strongest visual impact This one must become the visual focus of the entire set 【Third Photo (Bottom)】 Cinematic Ending Shot (Movie ending shot) The girl turns her body slightly, looks down and smiles, or looks away from the frame Relaxed and natural body posture The frame is quieter Forming a story ending shot The character takes up about 60% of the third frame The entire set of work adopts a Tokyo girl idol photo style (Japanese Idol Editorial), merging high-end Instagram lifestyle photography, Japanese magazine covers, Korean commercial photography, and movie still aesthetics. The subject is a 20-25 year old adult East Asian girl. Tall and slender figure, long proportions. Fair and delicate skin, real skin texture, with a slight natural dewy glow. Small and soft face shape, clear and bright eyes, pupils full of spirit. Naturally three-dimensional bridge of the nose. Soft and full lips, bean paste pink nude lip makeup, corners of the mouth slightly raised, naturally sweet. Hairstyle adopts high twin tails. Air bangs. Black long hair is smooth and thick, with weight and natural luster. A small amount of hair strands fluttering gently. Clothing adopts modern Japanese idol stage outfits. Pearly light purple silk satin halter-neck cropped top, fabric has soft pearl luster and silk satin reflection. Exquisite bows, crystal charms, and thin silver chain decorations added to the chest. Lower body paired with a pure white high-waisted pleated miniskirt. Skirt layers are rich, crisp and light. Wearing silver necklaces, small earrings. Double arms wearing translucent light purple tulle long sleeves. Wearing white mid-calf slouch socks and white sneakers. Scene is set in a Tokyo neon laundromat. Rows of light blue drum washing machines. Transparent acrylic chairs. Transparent storage baskets. Acrylic tabletop. Transparent heart-shaped ornaments. Transparent bead strings. Transparent crystal hanging decorations. A large amount of transparent materials together create a dreamy space. The foreground of the image includes many out-of-focus crystal bead curtains, transparent acrylic, crystal pendants, and heart-shaped transparent decorations, forming rich Foreground Framing (secondary composition). Utilizing real lens blurring to produce colored bokeh, refracted highlights, and dreamy light spots. Background includes slight volumetric light (Volumetric Light), forming soft atmospheric perspective. Overall color tone is dominated by pink-purple, light blue, cyan-blue, and candy pink. Lighting is soft, high-end cinematic lighting. Real lens out-of-focus. Real photography. Layer Composition. Z-axis Depth. Real lens optical blur. Cinematic color. Ultra-high definition. 8K. Japanese commercial photography. Korean magazine blockbusters. Instagram high-end lifestyle photography. Prohibit: 2D Anime Illustration CG feel Plastic skin Excessive skin smoothing AI face Low resolution Text Watermark Logo Duplicate characters Duplicate poses Ordinary collage Crops of the same photo Horizontal layout 16:9 output The final must output one 9:16 vertical magazine page, composed of three completely different photos automatically laid out, rather than one photo plus three horizontal lines.

IMAGE · chatgpt

水彩手绘墨西哥热带风情街景旅游海报

Watercolor travel poster illustration of (City Name) busy tropical street scene in the Hotel Zone, sunny Caribbean atmosphere, tourists walking through colorful market street, palm trees lining the road, straw roof shops, vibrant hand painted signboards, “Señor Frog’s”, “Coco Bongo”, Mexican souvenir stores, beachwear shops, restaurants and tequila signs, soft watercolor texture, ink sketch outlines, warm pastel palette, blue sky with fluffy clouds, lively vacation mood, highly detailed urban travel art, loose brush strokes, textured paper background, cinematic composition, travel postcard aesthetic, realistic crowd perspective, summer holiday vibe, handcrafted watercolor illustration style, ultra detailed, airy lighting, artistic tourism poster design.