GPT Image 2 提示词

Core Instruction: A Japanese Ukiyoe style collectible trading card design, vertical composition. The illustration style needs to closely mimic the visual aesthetics of "Demon Slayer", features include: ink outlines with varying thickness, traditional woodblock print color schemes, and dramatic dynamic composition. Subject Description: The card protagonist is {Character Name} (Title: {Hashira Name/Title}), in a dynamic fighting pose, holding {Weapon Description}. The character is performing {Breathing Style Move Name}, surrounded by {Visual Effect Description} (e.g., giant flames / water dragon / whirlwind), these effects need to be presented in Traditional Japanese Sumi-e style. Background and Material: The background needs to blend textured Holographic Foil effect, shimmering beneath the traditional ink elements. Border: The image should have a decorative border composed of Traditional Japanese Patterns (such as Seigaiha or Asanoha). At the bottom, there is a stylized banner with "{Japanese Kanji Name}" written in ancient Japanese calligraphy. Note: Replace fields in {} with your values before running.

Restore and colorize this photo. Note: Upload any old black-and-white photograph.

Change the character's style to [1970]'s classical [male] style. Add [long curly] hair, [long mustache], change the background to the iconic [californian summer landscape]. Don't change the character's face. Note: Upload a portrait photo. Replace values in [brackets] with your target era, gender, and scene.

Create a portrait depicting the person as an artist painting a miniature figure. The person is dressed in their most iconic outfit, looking confidently directly at the camera, holding a small paintbrush in one hand. A mini version of themselves is prominently placed on a clean workbench in front of them—make the figure slightly larger to be more visible than actual scale, thus standing out more. The figure is also wearing the same iconic outfit and striking an iconic pose. The painting supplies on the workbench are minimal to avoid clutter—only two or three small bottles of paint and a spare brush, keeping the focus on the person and the figure. Soft neutral white background, professional studio lighting, shallow depth of field. The composition highlights the person's facial expression looking at the camera and the figure they are painting. The style is clean and crisp, pursuing photorealistic effects, and details of both the person and the figure need to be highly restored. Note: Upload a reference photo of the person.

Draw a hand-drawn isometric diagram of this street Note: Upload a reference image of any street, building, or scene.

Enhance the resolution of this old image and add the appropriate texture details, reinterpreting it with modern anime techniques. Note: Upload any low-resolution reference.

Create an image at 40.7128° N, 74.0060° W, on September 11, 2001, at 08:46

Make Image Daytime and Isometric [Building Only] Note: Upload a photo or satellite view of a city block. Replace [Building Only] with [vehicles], [people], etc., to extract different layers.

Transform the person in the photo into a LEGO minifigure packaging box style, presented in isometric perspective. Label the box with the title "ZHOGUE". Inside the box, display the LEGO minifigure based on the person in the photo, along with their essential items (such as makeup, bags, or other items) as LEGO accessories. Beside the box, also display the actual LEGO minifigure itself, unpackaged, rendered in a realistic and vivid style. Note: Upload a reference photo. Change the title "ZHOGUE" to your own name.

A magnificent, highly detailed traditional Chinese ink and color handscroll painting on ancient silk, perfectly mimicking the artistic style, brushwork, and scattered perspective of Zhang Zeduan's masterpiece "Along the River During the Qingming Festival". Center Scene: Overlooking the bustling modern Chicago Riverwalk. The focus is the massive steel bascule bridge (DuSable Bridge/Michigan Avenue Bridge), with traffic, countless cars, yellow taxis, and Chicago Transit Authority (CTA) buses shuttling across, all depicted with precise traditional brushstrokes. Environmental Details: On the Chicago River below, modern architectural style cruise ships, water taxis, and kayaks shuttle back and forth. Skyscrapers of various styles line the riverbanks (resembling the Wrigley Building and Tribune Tower), painted using traditional "Jiehua" architectural painting techniques. Elevated railways and moving "L" trains are visible in the background. Human Activity: The Riverwalk and sidewalks by the bridge are crowded with hundreds of small figures in modern casual wear. Some are jogging, some are taking photos with smartphones, some are queuing at street food stalls (hot dog stands), and some are walking dogs. The whole scene is rich in detail, slightly chaotic, and presented in soft retro earth tones.

Convert a simple flat vector logo into a soft, fluffy 3D object. Use original colors. The object is completely covered in fur, with hyper-realistic fur texture and soft shadows. It is located in the center of a clean light gray background, floating gently in the air. The style is surreal, tactile and modern, creating a comfortable and playful feeling. Use studio lighting and high-resolution rendering. Note: Upload a reference logo image.

Based on the uploaded reference character, shoot a real-life scene in a spacious Tokyo girl's apartment — a bright, lived-in studio, spatial proportions close to 1LDK. The room should contain white walls, warm wooden floors, beige curtains, a low bed with soft bedding, a desk with cosmetics, bookshelves, plants, a standing mirror, a rug, scattered personal items, and a compact kitchen area at the back of the room. The room must have strong depth of field, with distinct foreground, middle ground, and deep background layers. Place about thirty characters identical to the reference character (face, hairstyle, clothing all identical to the reference character) in the room, each in a different action or interaction state. Adjust the distance, scale, height, and visibility between characters to make the room density look natural. Foreground: a person walking past the lens (slightly out of focus), a hand/shoulder entering the frame, one person approaching the lens, one half-hidden behind a large plant, one sitting in front tying hair, one kneeling by the table organizing items. Middle ground: one stretching by the bed, one checking phone, one lying on the bed, one reaching under the bed, one organizing cosmetics, one flipping through books, one standing in front of the mirror, one squatting on the rug, one leaning against the wall, one looking out the window, one adjusting curtains, one carrying clothes, one drinking water, one arranging pillows, one sitting on floor eating snacks. Note: Upload a reference photo of the character to use this prompt.

Create a hyper-realistic, high-resolution portrait infographic based on (your photo). Keep the identity, hairstyle, clothing, and natural skin tone unchanged; use a neutral studio background. Overlay a subtle semi-transparent facial analysis grid on the entire face, similar to a 3D facial scan grid: fine, soft white lines extending along facial contours, slightly glossy but not obscuring skin details. Add a clear vertical red laser line on one side of the face, like a futuristic scanning effect. Create a concise medical-beauty infographic with global-data percentages across 5 aging factors: 1. Fine lines and wrinkles 2. Skin texture and elasticity 3. Facial volume and sagging 4. Signs of aging around the eyes 5. Skin tone and pigmentation For each factor, place a small label with a thin line pointing to the corresponding facial area, and write a short title and a 0–100% actual score (e.g., "Fine lines and wrinkles — 18%", "Skin texture and elasticity — 72%"). Use concise, modern sans-serif fonts and small technical-style text. In the bottom center, display the estimated age in bold large characters: "Estimated Age: (number)". Overall style: futuristic AI-guided skincare analysis, minimalist, high-end editorial lighting, gender-neutral. Note: Upload a reference portrait photo.

Make an action figure of me that says ["AI Evangelist - Kris"] and features [coffee, turtle, laptop, phone and headphones]. Note: Upload a reference photo. Replace the label text and items list in [brackets] with your own.

Help me create a set of PPTs a middle school student can understand based on the article below. First write a PPT outline, planning the content of each page. Then render each page in "Anthropic/Claude style" — "Warm Academic Humanism" design. Background: warm beige/cream (#F3F0E9), mimicking high-quality paper texture. Font: elegant Serif for titles, modern Sans-serif for body. Color Scheme: main Terracotta Red (#D67052) and Mustard Yellow (#F0B857), Dark Navy Blue as accent. No neon or pure black. Visual Elements: typography-focused grid layout, abstract organic black hand-drawn line art on solid terracotta blocks, key info in card layout. Charts: flat minimalist bar charts, remove excess borders. Both text and images are generated directly in the same call. Do not collapse the deck into one image — one image per page. Article content: []

Generate a dark gothic tarot card featuring me from this image. Include ["AI Artist - Shira"] and [coffee, white fluffy chubby cat with pink bow, laptop, phone, headphones] as symbols, with moody shadows, intricate gothic borders, and mystical dark fantasy vibes. Note: Upload a portrait reference. Replace text in [brackets] with your name and symbols.

Based on the uploaded image, make a comic book strip, add text, write a compelling story. I want a superhero comic book. Note: Upload a reference photo.

A photorealistic, highly detailed image featuring [a 3D Polaroid camera] rendered in clear, highly polished transparent glass or crystal material. [The body has distinct thickness and dimensional depth, the iconic shape of a classic Polaroid camera — boxy body, front lens, top viewfinder, front shutter button, bottom film slot — presented in simplified yet extremely precise geometric structures]. All edges are treated with rounded chamfers and smooth curved surfaces, creating elegant refraction effects under light. The object is placed slightly tilted, as if floating above a clean, seamless pale beige or very light gray studio background. Lighting is bright, clean professional studio light, highlighting the transparency and specular reflections of the glass material. Sharp and delicate highlights appear on the body chamfers and edges. Subtle refraction, light bending and local distortion effects are produced when light penetrates the interior of the glass body. A soft, diffuse shadow falls below and slightly behind. Overall style: minimalist, modern, clean — high-end product photography with concept-art quality rendering. High-key with shallow depth of field. Note: Replace [item] with your object of choice.

Use the uploaded city photo as the base. Do not change the real buildings, streets, vehicles or people. Maintain photo realism. Add a very huge, stylized illustration creature in the sky above and behind the buildings, as if overlooking the city. Draw the creature in a flat graphic style with clear outlines and limited neon colors (soft neon green, neon yellow, lime green), similar to murals or poster illustrations. Creature Design: - Fantasy whimsical world, not horror or violent - Composed of layered shapes, scales, hair, or floral patterns - Long arms or hair hanging beside the buildings - Huge horns or peculiar features clearly visible against the sky Fusion with photo: - Place the creature behind the edge of the building (body partly occluded by buildings — correct perspective) - Use correct overlapping: building edge in front, creature behind - Subtle soft shadows or color reflections on nearby buildings if needed - Keep the original sky brightness so the illustration stands out Optional: a few small flat minimalist figures on the street (walking a dog, crossing the road) — do not block real people. Overall: dreamy surreal city scene with a huge friendly illustration creature above realistic buildings. Note: Upload a city reference photo.

Using this location, create an isometric HD-2D Minecraft-style image of the landmark (buildings only). Note: Upload a Google Maps reference image of any location.

Photograph this product in a dramatic modern scene accompanied by explosive outward dynamic arrangement of the key ingredients fresh and raw flying around the product signifying its freshness and nutritional value. Promo ad shot, without text, product is emphasized, with the key brand colors as background. Note: Upload a product reference image.

A 1080x1080 pixel close-up photo, hands holding a white newspaper, shot downwards. The background is extremely blurred and dark, making the newspaper stand out clearly. The newspaper occupies most of the picture, and its content is legible. The eye-catching headline is "[Headline]". In the center of the picture is a large black and white photo of [Photo Description]. The body text has multiple columns and is legible. Each generated shot maintains the same style, composition, lighting, characters, blur effect, layout and newspaper design — only the headline and photo change. Note: Replace [Headline] and [Photo Description] with your values.

An amateur photo from 1998, showing a middle-aged artist hand-copying an image from a computer screen onto a canvas with oil paint, but the image itself is a photo of the artist painting a recursive image.

Crop the head and create a 2-inch ID photo with: 1. Blue background 2. Professional business attire 3. Frontal face 4. Slight smile Note: Upload a portrait photo.

Hand-drawn style fashion concept breakdown diagram. Center: a full-body shot of a stylish, confident female character, with a natural and energetic pose. Surrounding (structured layout of her key elements): - Clothing layers — coat, underwear, leggings (lace, tulle material), shapewear, with zoom-ins on detail patterns. - Expression sheet — 3–4 facial expressions (neutral, shy, surprised, focused). - Close-up shots — fabric fold textures, skin details, hand gestures. - Lifestyle and accessories — opened handbag containing lipstick, perfume, compact powder, hand cream, diary, supplements. - Material annotations — handwritten-style notes next to each item ("soft lace", "matte leather", "shade #520"). Background: soft beige or parchment texture, design-sketch atmosphere. Lighting: clean and soft shadows. Output: 4K HD 2D illustration, combining elegance and fashion sense. Language: Chinese and English labels. Note: Upload a character image as the center reference.

Using the character from Image 2, generate [x] emoji stickers based on various poses from Image 1. Note: Upload a character reference (Image 2) and a pose reference sheet (Image 1). Replace [x] with the desired number.

Using the original image, recreate a pirate's wanted poster drawn on parchment. Brown monochrome, with the texture of aged parchment. Retain the style and character design of the original image down to the smallest detail, and paste it large at the top of the wanted poster. A close-up of the face. Have the character wear a pirate hat. Write the bounty amount at the bottom of the poster. The bounty amount will be random, and a fictitious currency unit will be used. Below the bounty amount, write the crime in small letters. Use a fictitious language. English or Chinese characters may not be used. Note: Upload a character reference image.

A wide celebrity quote card, brown background, serif light-gold text "Stay Hungry, Stay Foolish", smaller text "— Steve Jobs", a large faint quotation mark in front of the text, character portrait on the left, text on the right, text occupies 2/3 of the picture and the character occupies 1/3, character has a gradient transition feeling.

A photorealistic image of an ultra-detailed sculpture of the subject in image made of shining marble. The sculpture should display smooth and reflective marble surface, emphasizing its luster and artistic craftsmanship. The design is elegant, highlighting the beauty and depth of marble. The lighting in the image should enhance the sculpture's contours and textures, creating a visually stunning and mesmerizing effect. Note: Upload a reference photo of any subject.

Create a movie poster using the original image. The genre of the movie will be determined based on the atmosphere of the original image. Regardless of whether the original image is anime or live-action, the style and character design of the original image will be maintained as perfectly as possible. However, poses and expressions may be changed to match the poster design. Other people and objects may also be added at this time. The final generated image will be photorealistic. This does not apply to the poster design, as it will be based on the original image. The scenery of the underground passage of a Japanese station where the poster is posted will be recreated in a realistic image. People passing through the underground passage will be added. The reflection of the poster is angled to make it look more realistic. Note: Upload a reference image.