AI 提示词库

Choose one impressive word from my past conversation history, design a female villain leader from a Tokusatsu show that strongly reflects that word, and draw it photorealistically in the style of an 80s TV program. Reproduce the world view with photorealism. Size 9:16

A cinematic 3×3 grid presenting multiple camera angles of the same female subject outdoors at dusk. A young woman wearing a patterned black shirt stands beside a car on a rural road, surrounded by open fields and distant hills. Each frame shows a distinct shot: extreme close-up, medium shot, over-the-shoulder, wide shot, high-angle top-down, low-angle, profile, three-quarter rear view, and full back view. Natural blue-hour lighting, soft sky gradients, realistic colors, shallow depth of field, cinematic framing. Consistent subject appearance across all frames, film-still aesthetic, professional cinematography reference sheet style, ultra-realistic photography.

Create a dramatic digital painting style portrait of a young male a reference image without glasses looking upward with a strong, determined expression. The artwork should feel bold and textured, with energetic brush strokes and a limited color palette of black, white, red, and yellow. The background is split vertically with abstract red and yellow paint streaks, giving a powerful and intense mood. Focus on ambition and confidence in the player’s gaze, with a clean design that has no text, no slogan, and no logo anywhere in the frame. The composition should feel motivational and poster ready, high detail, 8K resolution, image aspect ratio 4:5.

A VFX comparison image based on a scene described by the theme or specific content (Example: {argument name="theme" default="A woman flying over the sea"}), featuring the person in the attached image. VFX comparison composition with a split screen accurately aligned by a central vertical line. **IMPORTANT: The number of characters, gender, and appearance must exactly match the provided input image. Do not add or remove characters.** **Left Half (Finished Shot):** A photorealistic movie scene perfectly depicting the theme "**[Enter Theme]**". * **Character:** The person from the input image is performing actions (pose and expression) suitable for the theme "**[Enter Theme]**". * **Background:** A detailed and realistic environment (outdoor or indoor) suitable for the theme, with cinematic lighting and atmosphere. **Right Half (Green Screen Shooting):** Standing in a studio with a giant blue/green screen (chroma key) in the **exact same composition and pose** as the person in the left half. Visible white cyclorama wall, complex lighting rigs overhead, cables, black marks (tape) indicating standing positions, dolly tracks for camera rails, harsh studio lighting that is not blocked, faint shadows of the film crew visible at the edges. The background is a completely flat, solid green screen for compositing. Look and feel of VFX before-and-after from early 2000s Japanese cinema, texture of extremely degraded, low-quality analog video, noise, and color fading.

Read the motif depicted in the attached image, generate multi-angle shots, and create four scenes divided into a 2x2 grid. [Action 1] The senior colleague (senpai) is looking at books on a shelf. The photographer presses a button on a remote control in their hand, and a distinctive electronic sound/chime rings. [Dialogue 1] The senpai is surprised, immediately turns to the camera, and playfully says, "Stop it." [Action 2] The photographer rings the electronic sound again. [Action 3] The senpai looks down shyly, squats momentarily, then stands up, laughing and covering their face with their hands. [Text Overlay] "{argument name="text overlay 1" default="Tried pressing the senpai's switch while they were shopping at the bookstore"}" "{argument name="text overlay 2" default="#This feeling is too cute www"}" "{argument name="text overlay 3" default="#Definitely inviting me www"}"

A miniature diorama showing tiny {argument name="PEOPLE / CHARACTERS" default="PEOPLE / CHARACTERS"} struggling with an oversized {argument name="EVERYDAY OBJECT" default="EVERYDAY OBJECT"}. Exaggerated scale contrast, expressive poses, cinematic lighting. Ultra-detailed props, handcrafted realism, macro lens perspective.

[ { "fileName": "1000586027.png", "name": "{argument name="first celebrity" default="Addison Rae"}", "description": "A woman kneeling in deep snow with a mountain and cabin background. She is wearing yellow earmuffs, a green and yellow crop top, and yellow shorts. A fox is sitting in the snow behind her.", "location": "Snowy Mountains", "outfit": "Winter Sportswear", "dimensions": "1080x1920" }, { "fileName": "1000586028.png", "name": "Celebrity", "description": "A woman posing in the snow with the Matterhorn mountain in the background. She is wearing brown earmuffs, a black and white t-shirt, and black shorts with 'MATTERHORN' and a Swiss cross. A deer is resting in the background.", "location": "Zermatt, Switzerland", "outfit": "Themed Sportswear", "dimensions": "1080x1920" }, { "fileName": "1000586030.png", "name": "{argument name="third celebrity" default="Ana de Armas"}", "description": "An edited version of the gym selfie with a heavy snowfall overlay effect. The woman is in the same pose and outfit, but the entire scene is covered in falling snow flakes.", "location": "Indoor Gym (Snow Effect)", "outfit": "Sportswear", "dimensions": "1080x1920" }, { "fileName": "1000586025.jpg", "name": "Sydney Sweeney", "description": "A woman kneeling in a snowy landscape with a wooden cabin and a wolf in the background. She is wearing blue earmuffs, a green tie-dye shirt, and green shorts with 'ASPEN' printed on them.", "location": "Aspen, Colorado", "outfit": "Winter Sportswear", "dimensions": "1080x1920" } ]

Today's theme is Let's Gargle (English Version)

Design a viral video thumbnail using the person from Image 1. Face consistency: keep the person's facial features exactly the same as in Image 1, but change their expression so they look excited and surprised. Action: place the person on the left side, pointing their finger toward the right side of the frame. Subject: on the right side, place a high-quality image of a delicious {argument name="food" default="avocado toast"}. Graphics: add a bold yellow arrow connecting the person’s finger to the {argument name="subject" default="toast"}. Text: overlay massive, pop-style text in the middle: '{argument name="thumbnail text" default="Done in 3 mins!"}'. Use a thick white outline and drop shadow. Background: a blurred, bright {argument name="background scene" default="kitchen"} background with high saturation and contrast.

Based on the word “{argument name="word" default="[WORD]"},” design an original decorative cinematic title font that visually evokes the meaning of the word. Use your imagination to create a unique and original design without being limited by existing typefaces. Choose the background color according to the design.

Panning shot of a mysterious soccer player in {argument name="jersey color" default="red"} professional soccer jersey mid air kicking a ball, motion blur, cinematic lighting against a Light green gradient background with streaking lights --ar 4:5 --raw --stylize 700

A detective's evidence board investigating {argument name="subject or mystery" default="[SUBJECT/MYSTERY]"}. Cork surface covered with pinned items: polaroid photographs with handwritten dates, a street map with circled locations, newspaper clippings with highlighted passages, sticky notes with theories and question marks, and printed documents with redacted black bars. Red string connects related evidence across the board, creating a web of connections. Thumbtacks in primary colors. A single bare bulb casts dramatic shadows. Coffee ring stains on some papers. The atmosphere is obsessive, late-night, noir—someone has been piecing this together for months. A few pins have fallen, suggesting frantic recent activity.

Make a json of a tier list (S-F scale) for: {argument name="category" default="[*insert-here*]"} Now generate image with the classically seen style/color scheme and representative thumbnail images for each list item

A hyper-realistic vertical tilt-shift photograph of a cross-section of a typical building in {argument name="city name" default="{city_name}"} during {argument name="current time" default="{current_time}"}. The current weather is {argument name="current weather" default="{current_weather}"}. The scene looks like an intricate miniature diorama. The lighting and sky color accurately reflect the {argument name="current time" default="{current_time}"}, while the street textures and atmosphere visually demonstrate the {argument name="current weather" default="{current_weather}"} conditions. At street level, the environment is lifelike. Tiny detailed figures are visible going about their activities. Strong miniature effect with heavy blur at the top and bottom. 8k resolution, volumetric lighting. --ar 9:16

{ "scene": "Modern high-rise trading workspace at sunset", "setting": { "location": "High-rise apartment or office", "time_of_day": "Golden hour / sunset", "environment": "Floor-to-ceiling windows with city skyline view" }, "subject": { "type": "person", "gender_presentation": "female", "appearance": { "hair": "long blonde hair", "outfit": "cream and light-yellow striped fitted dress", "pose_variations": [ "standing at desk looking at monitors", "seated in office chair facing camera", "leaning forward typing on keyboard", "turned slightly toward camera with relaxed expression" ], "expression": "confident, focused, calm" } }, "objects": { "desk_items": [ "multiple widescreen monitors", "laptop", "keyboard", "mouse", "white notepad", "blue water bottle", "small pink penguin plush" ], "screens_content": [ "financial trading charts", "candlestick graphs", "market indicators", "technical analysis dashboards" ] }, "composition": { "layout": "four-panel collage", "camera_angles": [ "medium shot", "side profile", "seated frontal view", "close-up working angle" ], "lighting": "natural warm sunset light with soft indoor lighting" }, "mood": [ "professional", "high-performance", "modern", "aspirational" ], "themes": [ "financial intelligence", "trading culture", "focus and discipline", "tech-driven workflow", "urban success" ], "use_cases": [ "marketing visuals", "fintech branding", "AI trading platform promotion", "social media content", "lifestyle-tech crossover" ] }

Create cinematic, ultra-realistic film stills inspired by Interstellar (Christopher Nolan vibe). Look like real movie screenshots with consistent color grading, Output as an aesthetic storyboard: visually cohesive, no text

Please illustrate the features of ChatGPT 5.2 using perfect Japanese fonts. The ratio should be 16:9. Please also add cute illustrations.

Cinematic 3D action-packed advertisement for {argument name="product brand" default="[INSERT PRODUCT/BRAND HERE]"}, captured in an intense mid-motion moment with dramatic studio lighting, dynamic particle effects, and high-impact slow-motion energy. Ultra-hyperrealistic rendering, razor-sharp details, glossy commercial finish, atmospheric depth, and powerful contrast. Viral-ready composition with the brand logo seamlessly integrated into the scene and a sleek, modern slogan positioned cleanly beneath. High-end blockbuster commercial aesthetic

Read the motifs depicted in the attached image, generate multi-angle shots, and create four scenes divided into a 2x2 grid. 【Action 1】 Santa Claus, with a serious expression, is looking at documents (thick books) on a bookshelf in a Christmas-decorated warehouse. The book title is left to the AI's interpretation in a way that suggests a story. The photographer presses a button on a remote control in their hand, making a unique 'Pikoon!' electronic sound or a cute chime sound. 【Dialogue 1】 Santa jumps in surprise and immediately turns toward the camera (photographer). While shaking his white beard, he says a word or phrase that is slightly embarrassed yet playful (left to the AI's interpretation in a way that suggests a story). 【Action 2】 The photographer grins and immediately presses the 'Pikoon!' electronic sound again. 【Action 3】 Santa looks down shyly with an expression of "Oh, come on!" He curls his large body and squats momentarily in a "moe-costume" (instead of moe-sleeves), then stands up, laughs heartily, and covers his face with red gloves to hide his embarrassment. Caption: "{argument name="caption" default="I pressed the switch on Santa preparing in the warehouse 🎅✨"}" Two hashtags. The content of the hashtags is left to the AI's interpretation in a way that suggests a story.

Tilt-shift 3D model diorama in 4:5 aspect ratio, highlighting {argument name="landmark" default="Tokyo Tower and the Shibuya Crossing"} at {argument name="time of day" default="sunset"}. Tiny pedestrians and cyclists navigate the bustling streets, while cherry blossoms drift gently from nearby trees. Neon signs and LED billboards glow softly in the background.

I want a youtube thumbnail prompt. split screen. On the right, {argument name="figure 1 name" default="trump"} looking angry at the camera, pointing towards the left side. On the left is a scene of {argument name="figure 2 name" default="mark carney"}, visibility in shock. behind mark carney is a canadian flag scene. At the top of the frame in high contrast yellow "{argument name="headline text" default="THE REAL TARGET"}"

Create a "Weekly Schedule" template image for VTubers and streamers. Horizontal 16:9, size 1920x1080, flat, neat, print-like design (vector style). The overall look should be cute pastel tones (gentle colors like pale pink, mint, lavender), prioritizing readability without clutter. Layout specification: ・Place the schedule section top-aligned on the left 60% of the screen. ・7 rows (Days of the week: "Mon, Tue, Wed, Thu, Fri, Sat, Sun"). ・Each row consists of a "Day label (small round badge)" + "Horizontal blank box for writing plans." ・The blank box must be completely empty. Absolutely do not include sample text (e.g., 'Plan here', 'SAMPLE', 'MEMO', etc.). ・The right 40% of the screen is empty space for later synthesis of a standing character image. Do not draw people, animals, mascots, or silhouettes. The background should only be a faint gradient and subtle abstract patterns of small stars/hearts/dots. Text specification: ・The only text to include is "Weekly Schedule" and "Mon Tue Wed Thu Fri Sat Sun" (in Japanese). ・Do not include any other text (SNS, date range, warnings, logos, hashtags, watermarks). ・The font should be rounded Gothic style, easy to read, and legible even on a white background. Finishing: ・Ensure ample margin around the perimeter, and elements on the left and right sides do not overlap. ・No logo.

Purpose: (example) {argument name="purpose_en" default="Create a thumbnail to use for a Note article"} Theme: (example) {argument name="theme_en" default="Why I, a 30-year-old office worker, decided to go independent after evaluating my side job"} *Please insert your own purpose and theme!* Your role is “graphic designer and marketer.” Create designs that make readers want to click instinctively. First, output three design option images.

A professional {argument name="host description" default="podcast host sitting at a wooden desk in a modern studio setup"}, facing the camera with a confident and friendly expression. He is wearing a {argument name="clothing" default="fitted black shirt"} and sitting in a comfortable chair. A high-quality podcast microphone on a boom arm is positioned close to his mouth. On the desk are a notebook with handwritten notes, a coffee mug, and an audio interface with connected cables. The background features {argument name="background lighting" default="stylish indoor plants and warm red-orange accent lighting"}, creating a clean, cinematic studio atmosphere. Soft key lighting on the face, subtle rim lighting, shallow depth of field, ultra-realistic details, 50mm lens, f/1.8, professional color grading, high contrast, 8K, YouTube podcast aesthetic.