AI 提示词库

If you attach the image of the character and their SNS profile, visualize "Key points to convey 👀 read from the profile 📣" in about 10 speech bubbles! ✔ AI selects words based on the profile ✔ Expressions and poses are linked to the dialogue

Kopokopo☺️ Kopokopo☺️ Rukutan is good at walking (っ ◜ω◝ c) is good at walking (っ ◜ω◝ c)✨

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

A miracle where you somehow make it on time even if you oversleep... it turned into a wonderful great fortune

You are an **architect and concept artist who visualizes story structures**. Analyze the provided input text (the movie synopsis) and generate a **"Vertical Layered Diorama"** where the height direction represents the timeline. The character in the attached reference image should be placed in the "Present (Middle Layer)" or "Future (Top Layer)" of this vertical structure, acting as the **storyteller/time traveler**, and posed to **look down on the past / look up at the future**. --- ## ▼ Instructions for Generation Process (Nano Banana Pro: Thinking Mode) 1. **[Step 1: Timeline Mapping]**: Decompose the synopsis into three time phases and assign them to physical layers. * **Bottom Layer (Past/Origin)**: Cause of gravity collapse, sealing, deep underground. Dark and heavy tone. * **Middle Layer (Present/Conflict)**: Survival and conflict in gravity-broken Tokyo. Vivid and dynamic tone. * **Top Layer (Future/Conclusion)**: Birth of a new gravity order, hope or ruin. Open and symbolic tone. 2. **[Step 2: Connection Design]**: Design the layers so they are not disconnected, but physically connected by elements such as **Gravity Well pillars / inverted spiral staircases / magnetic elevators / waterfalls where falling turns into rising**. 3. **[Step 3: Text Integration]**: Place the movie title in a stable location at the very top or bottom, and engrave famous lines on the **layer boundaries**. --- ## ▼ Design and Style Specification * **Composition/Layout**: **Vertical Cross-section / Tower structure**. Aspect ratio is vertical (**9:16**). Viewpoint is **slightly above the front**, at an angle that shows the thickness and depth of the layers. * **Taste**: **Precise museum model, geological cross-section, surreal architecture**. Express different eras and materials in each layer (concrete → neon metal → white structure on clouds) while integrating them as one giant object. * **Texture/Image Quality**: Photorealistic, precise detail, **8k**. Raindrops, wet asphalt, reflections, fog, volumetric light. * **Gravity Expression (Important)**: * Tokyo roads **curve 90 degrees as a continuous surface**, where the ground becomes a wall, and then arches to the ceiling, connecting in a **loop**. * Buildings, signs, cars, and pipes **protrude vertically** from the curved surface, and landmarks exist **upside down** suspended in the air. * Depict as a **physically continuous urban structure**, not just a reflection. * Light sources match the reality of a rainy night (reflections of neon and streetlights, diffused light through clouds). --- ## ▼ Input Text (Fictional Movie) **Title**: **{argument name="Movie Title" default="GRAVITY BROKEN TOKYO (Gravity Fault City Tokyo)"}** **Genre**: Sci-Fi Thriller / Disaster / Human Drama **Synopsis**: One night, due to the fracture of the "Gravity Lattice" above Tokyo, the city's gravity lost its uniformity. Roads bend into the sky, buildings lose their up and down, and falling chooses a direction. People survive by redefining "where the ground is." The narrator (reference character) dives across time to the origin of the gravity collapse, struggles in the current city, and reaches the new order of the future. ### [Bottom Layer / Past and Origin] (PHASE 1: YEAR 2036) * **Setting**: Deep underground research complex. Black basalt-like strata, old wiring, gravity control reactor "Atlas Core." * **Description**: Suggests that the device meant to "fix" gravity instead triggered the "tearing" of gravity. Tools and paper documents are scattered on the floor, and water droplets float horizontally due to gravity disturbances. * **Tone**: Dark, oppressive. Warning lights, fine dust, the stillness of low gravity. ### [Middle Layer / Present and Conflict] (PHASE 2: YEAR 2046) * **Setting**: The center of gravity-broken Tokyo, where rain continues to fall. A continuous city where **wet asphalt curves 90 degrees, becoming a wall, and continuing to the ceiling**. * **Description (Reflecting Gravity Prompt)**: * Roads rise vertically and then arch overhead to loop. * Landmarks are suspended upside down, and road signs protrude into the air. * Neon lights bleed along the curved surfaces in the fog and light rain, and reflections establish the light of a real rainy night. * **Character Placement**: Place the reference character in the **"Present" of the Middle Layer**. Grasping a railing or pipe with one hand, pointing to the light of the upper layer with the other. Gaze **looking down on the past (bottom layer) while looking up at the future (top layer)**. * **Tone**: Dynamic, tense. People's evacuation routes continue along the "wall roads." ### [Top Layer / Future and Conclusion] (PHASE 3: YEAR 2058) * **Setting**: The "Stable Gravity Layer" above the clouds. City remnants are rearranged, forming a new residential area composed of white frame structures and transparent materials. * **Description**: Ambiguous whether the gravity lattice was "repaired" or if a "new direction" was accepted. A pale column of light from the gravity well extends into the sky, connecting to the darkness below. * **Tone**: Open and symbolic. Hope and unease coexist. --- ## ▼ Connection Points (Gimmicks connecting the layers: Required) * **Gravity Well Light Column**: A column of pale blue volumetric light penetrating from the core of the bottom layer to the top layer. Particles flow upward. * **Inverted Spiral Staircase**: "Up" and "down" switch midway. Small year plates on the staircase railing. * **Waterfall where Falling Turns into Rising**: The water flow reverses at the boundary, emphasizing the layer separation. --- ## ▼ Visual Elements (Motifs to emphasize) * Wet asphalt, trajectory of raindrops, neon reflections, fog, volumetric light. * Curved City: Roads, architecture, and signs bend as a **continuous surface**, forming a **physical loop**. * Small objects floating in the air (umbrellas, paper scraps, tools, petals) visualize the disturbance in the direction of gravity. * Material changes in each layer: Rough rock stratum underground → Wet concrete and metal in the present → White structure and transparent material in the future. --- ## ▼ Text Instructions (On-screen Typography) * **Title**: "**{argument name="Title" default="GRAVITY BROKEN TOKYO"}**" * Placement: **Sky of the Top Layer**, or engraved on the pedestal of the bottom layer. * Font: Inorganic sans-serif, movie poster style. * **Famous Line** (Engrave on layer boundaries): * `{argument name="Famous Line" default=""Where is down, when the world forgets gravity?""}` * Placement: **Boundary between Middle and Top Layers**, like a sculpture on the landing of the inverted staircase or the edge of the light column. * **Timeline Display (Optional)**: Small next to each layer * `PHASE 1 / YEAR 2036` * `PHASE 2 / YEAR 2046` * `PHAS

I used nanobanana pro as a shading tool to add texture, decals, and glow to MMD output. I wanted to emphasize the edges, so I added lines with a croquis effect.

Please reduce the font size of "by Sugoi Kaizen"

A prompt that makes characters stylish

I entrusted the new album jacket font to it, and it designed the original image on the right like this

Today's theme is {argument name="theme" default="hot and cold"}

(masterpiece, highest quality, high resolution: 1.2), watercolor semi-realistic fantasy animation, impasto, oil painting, traditional art materials

[BRAND NAME]: A high-end, glossy concept art magazine editorial photograph of a unique, unexpected functional object conceptualized and designed by the brand. **1. The Concept & Object (AI Invention):** Based on the design philosophy, heritage, and material vocabulary of the specified brand, the AI must invent a novel utility product (NOT standard clothing, shoes, or bags). Examples could be home goods, tech accessories, tools, or sporting equipment, reinterpretated through the brand's lens. The object should feel sculptural yet functional. **2. Materials & Details (Hyper-Premium):** The object is constructed from ultra-premium, highly tactile materials characteristic of the brand (e.g., patinated exotic leathers, brushed aerospace-grade titanium, sculpted matte ceramics, molded carbon fiber, or technical high-fashion textiles). Every detail is hyper-realistic: visible stitching, microscopic material grain, precision engravings, and complex texture contrasts. **3. Photography & Lighting (Cinematic Studio):** Shot on a medium format Phase One camera with a 100mm macro lens. Extremely shallow depth of field, with sharp focus on the hero details of the object and a creamy, smooth bokeh background. The lighting is sophisticated studio softbox lighting: gentle, enveloping fill light with precise rim lighting to accentuate contours and material textures. **4. Environment:** A seamless, impeccably clean studio cyclorama background in a pure, ultra-light pastel tone (e.g., desaturated mint, pale blush, or off-white), free of shadows. **5. Layout & UI Elements (Strict Placement):** - **Bottom Right Corner:** A small, understated, monochrome gray logo of the brand. - **Bottom Left Corner:** Small, minimalist monochrome gray text describing the invented product. The font style looks like Manrope Regular with very tight tracking (kerning) and balanced line spacing. Example format: "CONCEPT STUDY: [AI inserts invented product name]. MATERIAL: [AI inserts main materials]. SS25."

New Year's illustration In the background, large, simple, gold text of {argument name="year" default="2026"} Luxurious and gorgeous decorations Color the illustration freely with flat colors

Utilizing the composition, background, and Pegasus from this image, generate a fantasy illustration of a character riding the Pegasus. Character: - A human character naturally riding the Pegasus. - Slightly leaning forward to maintain balance during flight. - Hands holding the reins or in a natural position suitable for riding. - Expression is cool and focused. Pegasus and Direction: - The Pegasus is flying at high speed. - The wings are powerful, conveying the motion of cutting through the wind. - Hair and clothing are flowing in the wind. Visual Representation: - High-quality anime-style illustration. - Cinematic expression with unified lighting, shadows, and color palette. - An aerial scene conveying speed and tension. Constraints: - Do not significantly alter the Pegasus design or the overall composition. - Do not add new characters or unnecessary elements. - Do not include text, logos, or watermarks. - Aspect ratio is 16:9

A handwritten signature of [{argument name="text" default="Happy New Year ♡"}] boldly written with a thin black marker. Style details: A very fluid and speedy cursive script (running hand), like a celebrity's signature. A dynamic composition combining large loops, long extending lines, and sharp sweeps. An artistic expression that prioritizes design and individuality over textual readability. A realistic texture that shows ink bleed and variations in pen pressure. The background is pale colored Japanese paper (Washi).

Change the white background to an American retro pinup-style background. Design a high-sense background incorporating elements such as retro-future, Space Age, and Googie architecture. Add a thin border like an old photograph. Generate the background in high resolution, adding a slight sense of realism to the texture and details. Use expressions that suggest neon or indirect lighting. Mainly generate only the background, without significantly changing the character's pose, expression, clothing, or coloring. Design the background to match the character's pose. The setting is: [{argument name="setting" default="airport"}]

{ "creation_intent": "{argument name="creation intent" default="Commercial Persuasion"}", "generation_logic": "Centered on people or characters", "subject_kit": { "primary_subject": "{argument name="primary subject" default="Sports Shoe"}", "secondary_elements": [ "Miniature climbers", "Shoelace ropes", "Sole texture terrain" ] }, "core_tension": "Containment vs. Infinity", "twist_mechanisms": [ "Keycap world", "Cross-section logic", "Book stage" ], "stage_context": "{argument name="stage context" default="Kitchen countertop macro scene"}", "composition_rule": "Forced perspective layering", "lighting_rule": "Warm practical light with soft shadows", "imaging_assumption": "Industrial product photography", "deliverable_type": "Miniature scene" }

{ "creation_intent": "{argument name="creation intent" default="Entertainment or Joke"}", "generation_logic": "Rule, structure, system driven", "subject_kit": { "primary_subject": "{argument name="subject" default="Fashion Model & 3D Mascot"}", "secondary_elements": [ "Interactive pose", "Matching accessories", "Mascot props" ] }, "stage_context": "Retail shelf close-up", "lighting_rule": "Colored filter spotlight", "imaging_assumption": "Mixed commercial composite", "deliverable_type": "{argument name="deliverable type" default="Advertising main visual"}" }

I gave it appropriate correction instructions, and it became a proper handheld device even in high-speed mode. Additionally, I requested corrections for the fingers and the removal of a mysterious cable, and it worked well.

It is not raining. Write only this as the system message.

A young Chinese woman in her late teens to early twenties, looking back over her left shoulder with her body slightly turned away, gazing directly and intensely at the camera with a slightly melancholic, contemplative expression. She wears a loose, light-colored down jacket or coat ({argument name="coat color" default="soft tones such as off-white, light gray, beige, cream"}), layered over a dark turtleneck sweater or black hoodie, with a loosely draped black scarf around her neck — classic dark inner + light outer winter layering style. Her hair is deep brown to black, styled in a slightly messy low bun or low ponytail, wind-swept with several loose strands naturally falling beside her face, giving a natural, slightly disheveled feeling. Fair, delicate, smooth skin with soft natural texture. Refined Korean-style makeup: subtle gradient eyeliner, gentle aegyo-sal (under-eye highlight), glossy lips. Large, expressive brown eyes slightly narrowed, looking straight at the viewer with depth and emotion. Neat straight bangs resting on her forehead, soft straight eyebrows, overall soft and gentle facial features. She carries a black backpack with clearly visible shoulder straps. Location: {argument name="location" default="Nanjing Road pedestrian street in Shanghai"}, bustling commercial district, at dusk or right after rain in overcast, damp weather. Background: heavily blurred crowds of people, dense rows of Chinese neon signs and illuminated billboards on both sides, distant silhouette of the Oriental Pearl Tower visible in the background. Wet, reflective ground with puddles. Strong colorful reflections of neon lights, street lamps, traffic lights, and car tail lights in the water. Blurred reflections of signs, buildings, and the Oriental Pearl Tower in the puddles. Overhead wires and decorative lights, rich bokeh light spots created by traffic lights and car headlights. Lighting: soft diffused cinematic light with slight grain feeling, overall cool blue-cyan ambient tone from overcast sky, contrasted by warm yellow, red, orange, pink-purple neon light spots reflected on wet surfaces — high contrast in background reflections, low contrast soft lighting on her face. Camera: medium close-up portrait, eye-level angle, extremely sharp focus on eyes and face, shot on Hasselblad XCD 3,4/75P (equivalent to ~50mm), creamy beautiful bokeh, rich light spots and reflection details preserved in background. Style: cinematic, emotional, urban life slice-of-life mood, street photography + emotional portrait, classic {argument name="color grading" default="teal-orange complementary color grading"}, overall cool low-saturation tones with warm neon highlights, soft dreamy atmosphere. Vibe: nostalgic, lonely, melancholic yet romant

Create a home-style cooking step infographic for 【{argument name="dish name" default="Sweet and Sour Pork"}】. 【Overall Style】 - Style: 8K ultra-HD realistic photography style, professional quality suitable for a food magazine - Image Quality: 8K resolution, sharp details, professional food photography lighting - Background: Real kitchen scene/marble countertop/wooden cutting board, shallow depth of field blur - Color Palette: Natural and realistic colors, true colors of ingredients, warm lighting - Layout: Horizontal 16:9 【Top Title Area】 - Main dish title (elegant Chinese font) - Subtitle: Cooking time / Difficulty level / Serving size - Background can use a blurred close-up of the finished dish 【Left or Top - Ingredient List Area】 - Title: "Ingredient Preparation" - All ingredients arranged realistically, neatly organized from a top-down view (flat lay) - Each ingredient labeled with name and quantity - Style: Instagram-style ingredient flat lay photography 【Main Body - Cooking Steps Area】 - 6-8 steps, arranged in a grid or timeline - Each step includes:   * Step number (simple numeric identifier)   * Close-up photo of the actual cooking process:     - Cutting meat: Knife skills details, meat texture     - Blanching: Boiling water, foam     - Caramelizing sugar: Caramel color, oily sheen     - Stir-frying: Dynamic movement in the wok, flame     - Stewing/Simmering: Sauce bubbling, steam rising     - Reducing sauce: Thick sauce, glossy meat pieces   * Brief descriptive text (1-2 sentences)   * Heat/Time notation 【Bottom - Finished Dish Display Area】 - 8K high-definition photo of the finished dish - Professional plating, exquisite tableware - Shot at a 45-degree angle or top-down view - Visible food texture: Gloss of the sauce, fibers of the meat, rising steam - Background: Dining table setting, chopsticks, small side dishes for garnish 【Photography Specifications】 - Lighting: Side-back light/natural window light, creating appetite appeal - Depth of Field: Subject sharp, background naturally blurred - Texture: Visible ingredient texture, oil sheen, reflection of the sauce - Steam: Real steam visible in hot dish steps - Color Temperature: Warm tone (5500-6000K), enhancing appetite 【Auxiliary Elements】 - Tips notation: Key techniques (e.g., "Blanch in cold water to remove odor," "Simmer slowly for 40 minutes") - Heat icon: 🔥 notation for heat level in each step - Timer notation: Duration for key steps - All ingredient quantities, step details, time, and heat should be automatically generated accurately based on the dish

Placing a “mini-sized version of myself” on the palm of my hand.

1. painterly quality 2. realistic version 3. Pixar-like animation style 4. the modern American comic style