AI 提示词库

First, use the power of Nano Banana to enhance the three-view drawing. Nano Banana seems to have interpreted the mysterious decoration around the neck as a 'magic-infused stone.' Since that kind of decoration is acceptable, I decided to proceed with it (the decoration in this area varies depending on my mood, so I will fix it as a magic-infused stone from now on). Then, use Novel AI's features to generate images with various angles and expressions. Use these to prepare the minimum necessary learning materials.

[{argument name="number and clothing" default="100 girls with high school uniform"}] Chaotic and anime illustration poster design featuring the subject. Theme: Visual overload, maximalism, and disordered composition. Interpret the subject into a fragmented explosion of related concepts and abstract shapes. Randomly redraw input subject and chaotically arrange elements similar to the input subject, creating a sense of visual noise and repetition. Style: Mixed media collage, glitch art, acid graphics, random scattered objects. No negative space, fill every corner with details. High saturation, clashing colors, psychedelic atmosphere.Chaotic visual layout.

subject: "Armored Trooper ATM-09-ST Scopedog, classic first-generation AT from Armored Trooper VOTOMS" view: "tight frontal view, perfect orthographic projection, zero perspective distortion, strict symmetrical composition" style: "high-contrast military-industrial scientific render, cold war-era weapons lab visualization" background: "pure black void, absolute vacuum environment, no reflections, no floor, no shadows except self-emission" aesthetic: "false-color thermal X-ray hybrid imaging with heavy mechanical wear" transparency: level: "semi-transparent heavy armor plating and rolled homogeneous steel composite" reveal: "extremely sharp and brutally detailed internal skeleton and systems" internal_components: - "central torso-mounted turbo-custom plasma fusion reactor" - "exposed hydraulic muscle cylinders and heavy-duty linear actuators" - "high-pressure fluid lines pulsing with red-hot coolant" - "belt-fed 30mm gatling arm punch with visible ammo feed" - "rear skirt-mounted high-thrust rocket thrusters" - "dense array of infrared/optical sensors and lens turret" - "cockpit block with visible pilot seat and control sticks" - "knuckle joints with exposed wiring and coolant pipes" heatmap_gradient: base: "deep cold blues and gunmetal grays (inactive armor zones)" mid: "dull green to burnt orange (hydraulic pressure zones)" high: "glowing yellow to molten red (reactor core, thruster bells, gatling barrel)" peak: "blinding white-hot hotspots on reactor shielding and over-pressurized joints" lighting: primary: "harsh cyan-white plasma glow from reactor vents" sources: - "chest reactor glare bleeding through armor seams" - "red-hot hydraulic lines" - "amber warning strobes on lens turret" - "molten orange glow from thruster nozzles" secondary: "faint rim lighting on battle-scarred armor edges, subtle volumetric heat haze" surface_details: - "authentic battle damage, bullet dents, scorch marks, chipped paint" - "visible weld lines, rivets, maintenance hatches" - "grimy industrial texture, oil stains, hydraulic fluid leaks" quality_boosters: - "8K resolution, ultra-detailed mechanical realism" - "hyper-sharp engineering precision, Yamato 1/12 model kit level detail" - "military technical manual aesthetic, cold and unforgiving" - "photorealistic metal shading, micro-scratches visible" negative_prompt: "cartoon, anime exaggeration, clean toy look, glowing eyes, pilot face visible, green android, Gundam parts, bit staves, permet effects, logo, text, watermark, extra limbs, perspective distortion, bright background, cute, deformed" weight_guidance: "(masterpiece, ultra-detailed, absurdres, best quality):1.4" "(Armored Trooper Scopedog, perfect proportions, authentic VOTOMS design):1.6" "(military industrial X-ray thermal aesthetic, brutal mechanical realism):1.35" "(battle-worn h

{ "prompt": "Hyper-realistic 8K portrait of a futuristic fashion model in neon-lit cyberpunk Tokyo street at night. She wears a sleek metallic silver bodysuit with glowing pink neon accents, high-slit skirt, and holographic accessories. Dynamic pose: leaning against a rainy pink coupe car, hair in wet wavy balayage (pink-cyan highlights), confident gaze over shoulder. Lighting: dramatic golden hour neon reflections on wet asphalt, bokeh crowd blur. Style: high-fashion editorial, cinematic, shallow DoF, warm-cool contrast.", "style": ["Cyberpunk Fashion", "Neon Glow", "2026 Trend"], "resolution": "2160x3840 (9:16 vertical)", "negative": "blurry, low-res, cartoonish" }

"Conditions to include in the diagram: ・Top 3 reasons why designers fail ① Always studying ② Lacking confidence to apply for projects ③ Spending too much money hopping between schools Create an image for an X post based on these conditions"

Please change the aspect ratio of this image to {argument name="aspect ratio" default="1:2"}

Upscale the character in the first image to the high resolution of the second image, and zoom in close enough to clearly show the skin texture. First image: Original image Second image: Skin image Third image: Nano Banana Pro Fourth image: Seedream 4.5

{ "preset_name": "Ultimate_Weapon_Mastery", "mission": "MAXIMIZE_LETHALITY_AND_AESTHETICS", "source_integrity": { "_hint": "[PREMISE] Maintain the character's identity, but actively allow for dramatic changes like 'sharp gaze' or 'wind-blown hair' typical of combat situations.", "identity_lock": "strict_facial_features", "combat_mode_adaptations": { "expression": "intense_focus_or_fearless_smile", "hair_physics": "dynamic_flow_matching_action_speed", "clothing_damage": "optional_minor_wear_and_tear_for_realism" } }, "weapon_analysis_engine": { "_hint": "[WEAPON ANALYSIS] Analyze the 'type', 'center of gravity', and 'method of killing' of the weapon provided to determine the optimal stance.", "analyze_weapon_class": true, "tactical_mapping_logic": { "class_blade_light": { "keywords": ["katana", "dagger", "saber"], "action_style": "high-speed_slash_or_iaijutsu_stance", "camera_effect": "motion_blur_on_blade" }, "class_blade_heavy": { "keywords": ["greatsword", "axe", "hammer"], "action_style": "weighty_impact_pose_using_ground_drag_or_shoulder_rest", "camera_effect": "camera_shake_simulation" }, "class_firearm_handgun": { "keywords": ["pistol", "revolver", "dual_wield"], "action_style": "close_quarters_combat_stance_(C.A.R._system)_or_dynamic_aim", "grip_discipline": "trigger_discipline_active" }, "class_firearm_long": { "keywords": ["rifle", "sniper", "shotgun"], "action_style": "stable_aiming_with_cheek_weld_or_patrol_carry", "perspective": "looking_down_the_sights" }, "class_polearm": { "keywords": ["spear", "halberd", "staff"], "action_style": "dynamic_thrust_with_extended_reach", "composition_note": "utilize_diagonal_lines_across_frame" } } }, "heroic_pose_database": { "_hint": "[CHOREOGRAPHY GENERATION] Refer to 'key visual' level pose data from movies, games, and anime to eliminate amateurish results.", "retrieval_logic": { "source": "cinematic_combat_pose_db", "query_parameters": [ "weapon_type", "character_physique", "desired_coolness_factor" ], "pose_correction": { "line_of_action": "strong_s_curve_or_c_curve_body_line", "silhouette_check": "ensure_weapon_is_clearly_visible_against_background" } }, "dynamic_foreshortening": { "_hint": "[FALSE PERSPECTIVE] Exaggerate the size of weapons or limbs closer to the camera to enhance impact (perspective emphasis).", "apply_perspective_distortion": "moderate_to_high", "focus_point": "weapon_tip_or_muzzle" } }, "cinematic_combat_composition": { "_hint": "[DIRECTION] Create the 'atmosphere of a battlefield', not just a standing figure.", "camera_work": { "angle": "dutch_angle_to_create_tension", "height": "low_angle_hero_shot", "lens_choice": "wide_angle_24mm_for_depth_exaggeration" }, "visual_effects": { "lighting": "contrast_heavy_rim_lighting", "atmosphere": "sparks_dust_or_energy_aura_matching_weapon", "depth_cue": "blurred_foreground_elements_(debris/sparks)" } }, "safety_a

Please execute the respective prompts using four person images after dividing the screen into four equal parts. The scene colors should match the characteristics of the clothing.

{ "target": "NanoBanana", "role_task": "Create a professional OOTD magazine-style fashion collage", "layout": { "left": { "width_ratio": 0.60, "preserve": { "face": true, "hairstyle": true, "outfit": true }, "photo_style": "clean, bright, magazine-quality", "pose": "cute, amusing, slightly quirky, realistic atmosphere" }, "right": { "width_ratio": 0.40, "background": "white", "product_grid": { "quantity": "[quantity]", "arrangement": "vertical", "final_module": "underwear_estimated_from_image", "module_fields": [ "product_image_cutout_white_bg", "product_name", "price_yen" ] } } }, "example_products": [ {"id":1, "name":"{argument name="Product 1 Name" default="[Product 1]"}", "price":"¥{argument name="Product 1 Price" default="[price]"}", "image":"[path_or_url_or_placeholder]"}, {"id":2, "name":"{argument name="Product 2 Name" default="[Product 2]"}", "price":"¥{argument name="Product 2 Price" default="[price]"}", "image":"[path_or_url_or_placeholder]"}, {"id":3, "name":"{argument name="Product 3 Name" default="[Product 3]"}", "price":"¥{argument name="Product 3 Price" default="[price]"}", "image":"[path_or_url_or_placeholder]"}, {"id":4, "name":"{argument name="Product 4 Name" default="[Product 4]"}", "price":"¥{argument name="Product 4 Price" default="[price]"}", "image":"[path_or_url_or_placeholder]"}, {"id":5, "name":"{argument name="Product 5 Name" default="[Product 5]"}", "price":"¥{argument name="Product 5 Price" default="[price]"}", "image":"[path_or_url_or_placeholder]"}, {"id":6, "name":"{argument name="Product 6 Name" default="[Product 6] (final underwear)"}", "price":"¥{argument name="Product 6 Price" default="[price]"}", "image":"[path_or_url_or_placeholder]"} ], "typography": { "font_family": "modern_sans_serif", "product_name_weight": "medium", "price_weight": "bold" }, "style": { "aesthetic": "bright, fresh, professional, Instagram fashion-blogger", "layout": "clean with generous white space", "color_palette": ["natural_tones", "white", "soft_gray"], "photo_quality": "professional_ecommerce_photography" }, "output_requirements": { "file_format": "PNG or JPG at editorial resolution", "left_image_handling": "preserve original pixels for face/hair/outfit (no warp)", "right_images_handling": "clip to white background, consistent lighting and scale", "notes": "final module must reflect underwear inferred from uploaded image" } }

①: No input image Create 42 scenes, dividing the screen horizontally 7x vertically 6, based on "A single everyday photo taken with a low-quality disposable camera. A clumsy photo taken by Japanese high school students." Display serial numbers from 1 in the bottom left of each scene. Each scene is separated by thin white borders. Image of a thumbnail sheet that comes when film is developed. Do not draw real company names or product names. ---------- ②: Using ① as input image The input image is a thumbnail sheet that comes when film is developed. Create the undeveloped negative film from this thumbnail sheet. Place the completed negative film on a school desk and photograph it from a diagonal overhead angle. Foreground blur and background blur due to depth of field. Live-action. ---------- ③: Using ② as input image A single everyday photo taken with a low-quality disposable camera of "Japanese high school students goofing around while holding this negative film." A clumsy photo taken by Japanese high school students. Do not draw real company names or product names. ---------- ④: Using ③ as input image Include the input image at the beginning of "A single everyday photo taken with a low-quality disposable camera... (same as ① below)"

Ultra-realistic live-action photo of a hand holding a snack package. The background also shows shelves lined with different flavors and types of packages featuring the character from the reference image. Character Name: "{argument name="Character Name" default="〇〇"}" (If not specified, strongly parody the characteristics of the reference image character with intense humor) Snack Setting: "{argument name="Snack Setting" default="〇〇"}" If not specified, randomly select one type from all snack genres sold in convenience stores, supermarkets, or candy stores, and boost the design for either eccentricity or stylishness. Realistic photo-style depiction of an original snack package fully decorated with the reference image character, held in a hand. The design should be natural enough to look plausible on a store shelf. The surrounding area of the snack should realistically show the store interior. Snack Package Design: Place the reference image character inside the package. Emphasize the name of the snack with intense humor based on the characteristics of the reference image. The package should be ultra-realistic, high-quality, and a highly stylish design that stimulates appetite. Realistically reproduce gloss reflections and material texture. Include an appetizing photo of the snack contents. Parts other than decoration should be transparent vinyl, or have a transparent film window allowing the contents to be partially visible. Place multiple humorous and exaggerated catchphrases and product names based on the reference image, using a font that reflects the atmosphere of the reference image, prominently. Draw a background (sales floor) appropriate for the snack's worldview. Also, ensure emotional and chromatic consistency between the background and the package concept. 📦 Package Shape Randomizer (Snack Package Shape Randomizer) Regardless of the snack type, randomly select from the following package shapes with equal probability. Furthermore, ensure the shape, background, texture, and light source are consistent. ◆ Shape Category List (Total 12 types) Vertical bag package (Snack type) Horizontal bag package (Chocolate bar/Candy bar type) Box type (Small box) (Candy/Ramune type) Box type (Large box) (Family pack type) Blister pack (Gum/Gummy/with bonus item) Cup container (Potato chips/Ice cream style) Cylindrical container (Tube candy/Tower potato chips) Stick type packaging (Long, thin candy type) Jelly suction pouch (Drinkable gummy/Juice type) Booklet type (Opens to reveal stickers or cards) Toy integrated package (Built-in toy) Eccentric shaped package Example: Character face 3D shape, car shape, treasure chest shape, glowing bottle shape, etc. 🧭 Scene Optimization (Scene Optimization Rules) Automatically adjust the following to create an environment where contrast stands out and the package is highlighted, according to the snack package design and concept: Lighting (Brightness, warm/cool colors, direction) Seasonality (Summer/Winter, Spring/Autumn) Indoor/Outdoor Time of day (Day/Night)

Show me 1 day later, 1 year later, 10 years later, and 30 years later in a 4-grid layout

Based on the image, add stunning microscopic city artwork.

Gently hold your city in the palm of your hand. SSS skin material allows light to pass through the gaps between the fingers, making the city glow like a jewel in the palm lines. Try replacing the topic with your hometown?

Using this prompt will dramatically increase the sense of luxury in the thumbnail.

Turn {argument name="number of people" default="4"} women into a colored illustration. The hair color should be {argument name="hair color" default="blonde"}, and the clothes should be based on {argument name="clothing colors" default="red and white"}.

Embrace that Q-version self. Generate a Q-version doll that wears the same clothes and looks the same! Perfectly supports locking the face and clothes, suitable for both men and women.

1. Overall Visual Style Style Keywords: Flat UI, Vector, Modern Minimalist, Card-style design. Lines and Shapes: Rounded Corners Priority: All borders, background blocks, buttons, and process nodes must be rounded rectangles (Rounded Rectangles, with a large corner radius, approximately 10-15px). Elbow Lines: Process connections use right-angle polylines (no curves), lines are simple and strong. Color Logic (Key): “Candy Color” Scheme: Use light backgrounds with high brightness and low saturation (such as light blue, light green, light purple), paired with darker borders of the same color family. Border Emphasis: All graphics must have clear 2px~3px solid borders. 2. Vertical Layout Structure Regardless of the topic, please follow the following top-down layout order, which must be contained within a large border container: Layer 1: Main Title (Header) Position: Centered at the top of the container. Style: Bold black font, largest font size, darkest color. Layer 2: Core Flowchart Area Position: Occupies 50% of the core area of the layout. Content: Rectangular nodes + arrow connections. If it is a loop step, please use a dashed line pointing back. Layer 3: Feature List Position: Below the flowchart, centered or left-aligned. Style: Short and concise bullet points, slightly smaller font, with some white space. Layer 4: Full-width Summary Box (Footer Box) Position: At the very bottom of the container, filling the width horizontally. Color Scheme: Use a contrasting color (such as purple in the example), distinct from the main color scheme above. Function: Used to place 'Summary', 'Analogy', or 'Core Conclusion'. Landscape size (horizontal/scenic mode) is chosen because: Content Adaptation: Horizontal content like timelines is better displayed in a horizontal canvas to show the evolution process. Presentation Friendly: The 3:2 horizontal ratio is very suitable for insertion into PPTs and documents, and displays well on projectors or screens. Information Capacity: Horizontal layout can accommodate more text and icons, avoiding clutter.

Select two characters and generate a scene where they are 'working part-time selling Christmas cakes on a street corner while wearing Santa Claus costumes'.

Scene: type: "battle scene" camera_angle: "dramatic dutch angle, tilted composition" lens: type: "super wide-angle lens" effects: - "extreme perspective" - "strong spatial compression between foreground, midground, background" Character: identity: ethnicity: "Japanese" gender: "{argument name="gender" default="girl"}" hair: "{argument name="hairstyle" default="Brown medium length hair with cat ears"}" outfit: style: "windy, dressy, Idol costumes that resemble high school girl uniforms" pose: description: "bold, dynamic action pose" body_orientation: "leaning with momentum implied by the tilt" Hands_and_Gesture: right_hand: gesture: "holding a Japanese sword" position: "held in front of her face, higher than her left hand, blade down and pointing towards you" gaze_alignment: "her eyes follow the pointing direction" left_hand: gesture: "open hand" fingers: "all five fingers widely spread" position: "The palms are facing forward as if aiming." palm_direction: "facing upward as if supporting it" perspective_role: "dominates the extreme foreground" perspective: dominance: "left hand is massively enlarged by wide-angle distortion" clarity: "both hands and face in sharp detail" depth_of_field: "full DOF, no background blur" Lighting: type: "soft indoor lighting" mood: "gentle highlights, controlled shadows" background: "neutral, blurred environment" Cinematic_Effects: atmosphere: "action tension + stylized anime dynamism" motion_sense: "perspective and Dutch angle add momentum" Output: aspect_ratio: "16:9" style: "high-quality anime illustration" rendering: "clean lines, sharp details, accurate anatomy"

Generate a photo of you with Judy and Nick from 'Zootopia'. The style must be consistent with the movie, character expressions natural, lighting transparent, and the background is {argument name="background" default="Zootopia street scene"}. If a photo of two people is uploaded, please generate a double portrait.

【Scene】{argument name="scene" default="City characteristic wall"}｜{argument name="background" default="Large text background"} 【Lens】{argument name="lens" default="Ultra wide-angle"}｜{argument name="angle" default="Low angle shot"}｜{argument name="high angle shot"} 【Action】{argument name="action" default="Waving hand"}｜{argument name="walking"}｜{argument name="making a heart sign"}｜{argument name="shading eyes"}｜{argument name="looking back and smiling"} 【Atmosphere】{argument name="atmosphere" default="Natural"}｜{argument name="relaxed"}｜{argument name="candid feel"}｜{argument name="lighting" default="Transparent light"} 【Character】Consistent facial features｜Consistent outfit｜Consistent body proportions

Based on the following topic [{argument name="topic" default="Map of Specialty Coffee Origins and Flavors"}], create a professional knowledge infographic. Requirements: 1) Extract 3-5 core knowledge points; 2) Use elements such as icons, flowcharts, and data visualization; 3) Information hierarchy must be clear, and visual guidance must be smooth; 4) Must include accurate Chinese title and explanatory text; 5) Color scheme must be professional and coordinated, suitable for business presentations. Layout should adopt a modern flat design style, 4K resolution, suitable for printing and sharing.