AI 提示词库

Referenced image ②① and the character sheet to nanobanana pro and instructed a costume correction.

Create a minimal, poetic illustration of a {argument name="subject" default="young woman"}, shown from {argument name="framing" default="close-up"}. The subject is {argument name="emotion" default="contemplative"}, with clear facial details and soft, natural expressions. Introduce one subtle surreal element [unexpected object / scale shift / visual metaphor] that reflects their inner world. Use clean shapes, limited color palette, gentle lighting, and a calm background. The mood should feel introspective, cinematic, and quietly emotional.

If it's 'Good morning' it appears, but 'After this' doesn't come out properly.

iPhone随手拍，宿舍日常场景照片，两位穿着校服的女生坐在双层铁架床的下铺。左侧女生左腿搭床沿、右腿前伸，低头看手机；中间女生双腿弯曲并拢，身体端正。背景为女生宿舍，上铺堆放杂乱衣物，地面散落多双运动鞋、休闲鞋及袜子。低分辨率照片，随手拍，生活化随意氛围，展现宿舍放松日常状态。比例 9:16。

A disgusting monster with many eyes that is hard to tell if it's an ogre or something else.

When I extracted the intrinsic color, shading, and highlights from this picture using Nanobanana Pro, it came out beautifully

A cozy miniature diorama of {argument name="activity" default="[ACTIVITY]"}, tiny handcrafted figures with subtle expressions, meticulously detailed props at 1:87 scale, warm golden-hour lighting casting soft shadows, dust motes visible in light beams, a gentle slice-of-life atmosphere. Tilt-shift photography effect, shallow depth of field, nostalgic and intimate.

Make me a panorama of this location in anime style.

Create a triptych of three 2.39:1 shots within a 4:5 composition. Make them cinematic, science-fiction shots with an atmospheric feel, as if shot by Roger Deakins in IMAX, with high contrast and desaturated blue and gray color grading. Then expand the three images one by one into three separate 4:5 scenes.

Create an illustration based on the following classical Chinese poem, and include the original text in the image. [Full poem text of “Song of Everlasting Regret” follows as in the Chinese content.]

"Turn this image into a Pixar style."

"Carbonite" Upload an image and all the characters get put into a deep freeze.

A top view photograph of a real chess board with all pieces in starting position on a table as per chess rules.

{ "task": "image_restoration_upscale", "positive_prompt": "Restore and enhance the provided image. Preserve original identity, facial structure, proportions and composition. High-fidelity photo restoration, ultra-realistic, natural skin texture, accurate details, professional photographic look. 4K output, sharp but natural focus, modern cinematic lighting, subtle volumetric lighting, professional color grading, depth of field, HDR. Shot on Arri Alexa, raw photo aesthetic, masterpiece.", "negative_prompt": "Creative reinterpretation, style change, identity alteration, face reshaping, exaggerated features, cartoonish, painting, illustration, over-sharpening, plastic skin, blur, noise, film grain, jpeg artifacts, distortion, bad anatomy, overexposed, underexposed, washed out colors.", "parameters": { "steps": 30, "cfg_scale": 6.5, "denoising_strength": 0.45, "upscaler": "4x_NMKD_Siax_200k", "target_resolution": "4K" } }

Create a completely new visual style by synthesizing two contrasting visual languages: STYLE FOUNDATION: A cinematic architectural illustration with the clean composition, strong perspective, elegant architectural forms, crisp selective linework, luminous tropical colors, dramatic blue sky, and polished environmental storytelling of a high-end anime-inspired background painting. PAINT HANDLING: Fuse this with expressive traditional watercolor and ink techniques: loose gestural brush strokes, dry-brush texture, translucent watercolor washes, pigment blooms, irregular ink contours, spontaneous splatters, visible paper grain, partially unfinished edges, atmospheric paint bleeding, and subtle abstract fragmentation. NEW HYBRID STYLE: Do NOT simply imitate either reference. Develop an original visual language that sits between polished digital illustration and expressive architectural watercolor sketching. Keep the major architectural structures highly readable and beautifully designed, but allow secondary details, vegetation, reflections, clouds, distant objects, and peripheral elements to dissolve into loose watercolor marks and ink gestures. Use selective precision: sharp, deliberate linework around important architectural silhouettes, windows, domes, roofs, bridges, lamps, boats, and foreground structures; looser broken lines and painterly abstraction toward the edges and background. Combine luminous cinematic lighting with watercolor transparency. Use layered washes of turquoise, cyan, deep blue, warm ochre, coral, terracotta, muted green, and soft cream. Let colors subtly bleed into one another rather than appearing as perfectly flat digital fills. Atmosphere should feel tropical, poetic, nostalgic, peaceful, slightly dreamlike, and cinematic. Include strong foreground / middle-ground / background depth. Use reflections on water as loose, broken watercolor reflections rather than perfectly mirrored digital reflections. Clouds should be volumetric and luminous but painted with soft watercolor masses and irregular edges. Vegetation should alternate between identifiable tropical foliage and expressive abstract brushwork. SURFACE: fine cold-pressed watercolor paper texture, subtle grain, transparent pigment layers, ink-and-wash marks, dry brush, soft granulation, occasional paint splashes, slightly imperfect handmade edges. COMPOSITION: vertical cinematic composition, strong leading lines, architectural focal point, deep perspective, generous atmospheric space, balanced negative space, beautiful visual hierarchy, high-end editorial travel illustration. IMPORTANT: The final result must look like a coherent NEW ART STYLE, not a collage and not a literal combination of the two references. Avoid photorealism. Avoid generic watercolor clip-art. Avoid overly clean vector art. Avoid excessive anime facial features. Avoid uniform line thickness. Avoid making every object equally detailed.

A horizontal split-screen cinematic shot of {argument name="scene location" default="Lalchowk, kashmir india"}, seamlessly blending two different eras: {argument name="era A" default="1920s"} on the left and {argument name="era B" default="present day"} on the right (default: about 100 years ago vs. present day). On the left side ({Era_A}): show era-appropriate architecture, interior or environment design, materials, vehicles, and props that clearly belong to that historical period. People wear authentic clothing from {Era_A}, including hairstyles, accessories, and typical items in their hands (such as books, umbrellas, instruments, letters, newspapers, etc.). The overall mood feels nostalgic and historically accurate. On the right side ({Era_B}): show the same {Scene} in the modern era, with updated architecture or renovated structures, contemporary materials (glass, steel, LED screens, modern furniture), modern vehicles or equipment, and current technology (smartphones, laptops, cameras, etc.). People wear contemporary fashion that matches today’s style in this setting. In the center: the two eras merge and overlap organically, without a hard dividing line. Elements from {Era_A} and {Era_B} visually interact: people from different times look at each other, walk through each other’s space, or seem surprised by the other era’s technology and objects. Architecture and environment smoothly morph from old to new (for example, stone gates turning into modern campus gates, classical concert hall décor fading into a futuristic stage, old street shops transforming into neon-lit storefronts). Make sure the scene is not just a simple left/right comparison but a dynamic time-travel interaction where buildings, clothing, props, and human gestures clearly emphasize the contrast and fusion between the two eras. Photorealistic, 8k resolution, cinematic lighting, wide angle, highly detailed textures, rich sense of time-travel storytelling.

"Restore this old photo into professional portrait of DLSR - quality colour and detail, using an advanced upscaling algorithm comparable to the results from canon EOS R6 II. Ensure the restored the image looks natural, retains exact facial features, has great clarity......"

Restore and colorize the uploaded old photograph into a crystal-clear, photorealistic, high-detail image while preserving 100% of the original composition. Keep the exact same pose, expression, facial structure, proportions, framing, clothing, hairstyle, background, objects, and all details unchanged. Do not add, remove, move, or restyle anything. Remove blur, noise, scratches, fading, stains, and age-related damage. Recover natural sharpness, fine skin texture, realistic textures, true-to-life colors, and lifelike skin tones. No identity change, no stylization, no cartoon or CGI look, no plastic skin.

Extreme close-up black and white portrait of a man with intense eye contact, partially hiding his face behind the high collar of a textured dark coat. His short-cropped hair and pale skin are sharply defined under dramatic lighting, creating deep shadows and high contrast across the face. The texture of the skin and fabric is clearly visible, adding a tactile, almost tangible quality. The background is completely black, focusing all attention on the expression and mood. Cinematic; bold, and mysterious. Natural light, glossy paper feel chaos {argument name="chaos" default="45"} style raw p.470wg66-v-7 -ar 3:4

{ "type": "image_generation_prompt", "style": "hyper-realistic, cinematic, urban rebel aesthetic", "resolution": "8K", "identity_preservation": { "use_reference_image": true, "strict_identity_lock": true, "alter_face": false, "notes": "Maintain the woman’s precise facial features, hairstyle, skin tone, body proportions, age, and expression with 100% accuracy based on the uploaded reference image." }, "composition": { "camera_angle": "eye-level to slightly low-angle", "framing": "medium-to-full body", "focus": "sharp focus on subject with cinematic depth" }, "subject": { "gender": "female", "pose": { "position": "sitting on the chrome grille of a purple classic lowrider car", "hands": { "right_hand": "resting down naturally on her thigh or near her side", "gesture": "relaxed, non-aggressive" }, "posture": "confident, relaxed, rebellious calm", "expression": "tough, self-assured, intense" }, "appearance": { "hair": { "color": "brown", "style": "messy bun", "accessory": "light blue hairband" } } }, "wardrobe": { "top_layers": [ "open blue plaid flannel shirt", "white turtleneck hoodie" ], "bottoms": "full-length trousers (dark or neutral tone, relaxed or baggy)", "footwear": "white Nike sneakers" }, "accessories": { "handheld_item": { "hand": "left", "item": "coffee", "handling": "casually held" } }, "environment": { "location": "dark garage", "vehicle": { "type": "classic lowrider", "color": "purple", "details": "chrome grille with reflective metallic finish" }, "atmosphere": { "effects": [ "light smoke or fog in the background", "subtle reflections on chrome surfaces" ] } }, "lighting": { "style": "cinematic", "tone": "cool-toned lighting", "effects": [ "moody highlights", "deep shadows", "enhanced texture and depth" ] }, "mood": { "atmosphere": "rebellious, intense, confident", "tone": "urban, gritty, cinematic" }, "quality": { "realism": "ultra-photorealistic", "detail_level": "high detail in skin, fabric textures, chrome reflections, and smoke", "rendering": "cinematic DSLR-quality finish" }, "output_goal": "Create a hyper-realistic, cinematic portrait of a tough woman sitting on a purple classic lowrider in a dark garage, with a relaxed hand-down pose and full-length trousers, preserving her exact identity while conveying a rebellious and intense mood." }

A cinematic macro toy-photography scene of dozens of identical bean-sized instances of the uploaded reference character charging forward through a violent rainstorm in a partially broken military formation, led by a commanding figure riding a fantastic mount deeper in the frame. ar 16:9 🧬 Likeness Integrity (CRITICAL) All instances must preserve exactly: • proportions • eye shape, spacing, stylization • silhouette • material identity No redesign. No added features. No facial changes. All soldiers are identical instances of the same character. ⚔️ Scene Concept & Motion Structure The army transitions from formation into full charge: • front rows breaking into aggressive motion • mid rows reacting milliseconds later • deeper rows still partially aligned Motion spreads like a wave through the army Each unit runs with controlled variation: • different stride timing and body angles • no identical poses • all movement directed forward Weapons: • each unit carries an oversized medieval-style weapon • designs vary but follow a unified visual language • subtle controlled glow, never overpowering • must not obscure character identity 🐉 Leader & Mount (COMMAND LAYER) A commanding leader appears deeper in the frame, elevated above the formation: • positioned off-center along a rule-of-thirds axis • partially silhouetted through rain and haze • clearly distinct from the soldiers through scale and placement Mount Design Logic (CRITICAL): • derived from the character’s material and world language • no literal cloning or costume mimicry • subtle harmony in form, texture, and accents Pose: • mount in forward surge, cutting through rain • leader stable and controlled, not exaggerated • presence communicates authority, not motion chaos The leader has already moved. The army is catching up. 🪂 Foreground Hero (IMPACT ANCHOR) The closest instance dominates the foreground: • captured mid-air in a dynamic jumping attack pose • limbs extended with directional force • weapon leading the motion This figure acts as the visual entry point into the scene 🎥 Camera & Perspective (PRESSURE SHOT) Ultra-low ground-level camera, almost touching wet terrain 18–24mm close-lens perspective • foreground character enlarged by proximity • army recedes diagonally into depth • leader visible in mid/deep plane • slight horizon tilt for instability • some units cropped at frame edges Viewer feels inside the charge 🔍 Depth of Field (MANDATORY) Extremely shallow depth of field • foreground hero = razor sharp • nearby units slightly softened • leader readable but partially diffused • distant army dissolves into rain and haze No full-frame clarity 💡 Lighting Doctrine (STORM LIGHT) Hard directional back/side light cutting through rain • strong rim light outlining silhouettes • rain streaks illuminated as sharp lines • deep shadow poc

The most weird mundane photo you can imagine.

Generate four distinct, hyper‑realistic images, each depicting a world‑renowned landmark. For each image, include a comprehensive and clearly legible set of annotations directly overlaid onto key architectural features, historical elements, or culturally significant details. These annotations should provide brief, informative descriptions. The first image should feature the Eiffel Tower in Paris, France, at sunset, with annotations highlighting its iron lattice structure, observation decks, and historical significance. The second image should showcase the Great Wall of China, specifically a section in Mutianyu, during a clear autumn day, with annotations detailing its watchtowers, construction materials, and strategic importance. The third image should present the Colosseum in Rome, Italy, bathed in morning light, with annotations identifying its arches, seating tiers, and its role as an ancient amphitheater. The fourth image should capture the Taj Mahal in Agra, India, under a soft, ethereal pre‑dawn glow, with annotations pointing out its marble dome, minarets, and inlaid floral designs. Each image should be rendered with exceptional detail, vibrant colors, and dynamic lighting to emphasize the grandeur of the location, making the annotations seamlessly integrated into the visual narrative.

Create a photo-style line drawing / ink sketch of the person identical to the uploaded image — keep every facial feature, proportion, and expression exactly the same. Use blue and white ink tones with intricate, fine line detailing, drawn on a notebook-page style background. Show a right hand holding a pen and an eraser near the sketch, as if the artist is still working.