A detailed prompt for generating a POV video of a character singing during a video call while relaxing in a parked car, focusing on natural movements and cute expressions.
A dreamy sepia watercolor illustration of an intimate couple with floral hair ornaments and a beige censorship block over their faces.
A highly detailed multi-scene prompt for generating 90s-style cel-shaded anime cooking sequences, focusing on hand movements and the texture of ingredients.
Biological process: Cellular mechanism animation, organ system function, ecosystem interaction, life cycle visualization. Micro-macro connection, living system complexity, natural wonder
A high-detail prompt for a whiskey brand advertisement. It uses an uploaded face reference to create a sophisticated, powerful scene with cinematic lighting and premium textures.
A hyper-realistic, high-fidelity cinematic character portrait of Rikku from Final Fantasy X-2. A young blonde woman with dynamic, messy, braided hair flying mid-air, wearing a yellow scarf and green leather thief attire. She has a confident smile and is thrusting a glowing, intricate steampunk orb directly toward the camera lens. Extreme forced perspective with a shallow depth of field, sharp focus on her face, while the large glowing blue and gold mechanical orb in the foreground is slightly out of focus. High-end editorial character design, Unreal Engine 5 render style, PBR material textures, intense studio lighting, clean white background with floating water splashes and mechanical debris, 85mm lens look, photorealistic skin pores, 8k resolution, commercial advertising aesthetic.
A 30-second high-detail short film prompt following a Shanghai courier during a sunrise delivery involving a mysterious photograph.
A meta-prompt for generating professional business posters with olive green tones, city skylines, and clear typographic hierarchy using GPT Image 2.
A sci-fi sports prompt featuring an epic cricket match played by astronauts on a floating stadium on the moon.
A photo-realistic prompt for maintaining facial identity consistency in a Korean classroom setting.
A hyper-realistic portrait of a man in luxury attire leaning against a black Mustang, emphasizing class and confidence.
A medium portrait captured with a 50mm lens at f/2.0. The subject is a young East Asian woman, early 20s, with soft rounded facial features — high cheekbones, almond-shaped dark eyes, natural thin brows, and slight visible pores on the nose bridge. Her lips carry only a faint nude gloss, skin has a natural dewy texture with no digital smoothing applied. She wears an oversized white cotton button-down shirt that has slipped slightly off her left shoulder, hem at mid-thigh — the fabric draping with natural relaxed weight, not styled. She is positioned slightly left of center in a three-quarter body frame, arms raised loosely gathering loose black hair, head tilted softly to the right. The primary light source is cool diffused morning light entering through a Japanese shoji paper screen window directly to her left — blue-white color temperature approximately 5000K, no directional cast shadows, soft even wrap-around fill across her entire figure. The room behind her is a minimal Japanese interior: bare light oak wood floor, plain white walls with no decoration or furniture visible. Photographic texture and quality: subtle ISO 400 film grain visible in darker fabric folds and shadow areas, faint halation bloom in brightest window-side highlights, Kodak Ultramax 400 color profile — cool teal cast in shadows, desaturated neutral midtones, barely overexposed specular highlights. Avoid: AI-smoothed plastic skin, geometrically perfect hair placement, oversaturated colors, studio glamour lighting.
A detailed anime scene of a horned demon office worker drinking in a cozy sunlit apartment, useful for fantasy slice-of-life character art.
Lei Jun ARE YOU OK co-branded shoes, Xiaomi orange color scheme circuit board texture, "ARE YOU OK" shoelaces
A futuristic daily-life sequence inside an automated AI home with robotic arms and holographic interfaces.
A fantasy action prompt depicting evolved werewolves defending their office against invading vampire commandos.
Use the uploaded portrait as the strict identity reference. Preserve the person’s face, facial structure, eyes, nose, lips, skin tone, hairstyle, hair color, age impression, gender presentation, and overall recognizable vibe. Create a high-quality surreal mixed-style portrait featuring: 1. The uploaded person as a realistic human subject 2. A mysterious simple black line-doodle figure physically teasing or bothering them in a funny way The real person must remain realistic, attractive, natural, and recognizable — not cartoon or anime. Keep their original gender presentation and create a clean studio-photo look. The doodle character should be a minimalist black hand-drawn stick/line figure: - bold black outlines only - simple head and body - tiny dot eyes or blank face - no identity, color, shading, clothing, or realistic details - flat graphic style contrasting with the realistic person Choose one random playful “bullying” interaction each time, such as: - gently grabbing arms, legs, wrists, or shoulders - dragging or lifting them awkwardly - wrapping around or trapping them - carrying them like an object - squeezing them into a silly pose - covering their mouth playfully - making them sit or lie awkwardly The interaction should feel mischievous, annoying, absurd, cute, and meme-like — never violent, scary, sexual, or harmful. The person’s reaction should naturally match: annoyed, confused, tired, embarrassed, surprised, unamused, helpless, or mildly frustrated. Keep it funny and relatable, not exaggerated. Choose a simple clean outfit that fits the person: casual clothing, sweatshirt, knitwear, T-shirt, loungewear, minimal fashion, or neat everyday style. Use a plain white, gray, or neutral studio background. Avoid clutter and distractions. Composition: - vertical 4:5 or 9: 16 - full-body or 3/4-body framing - show both characters clearly - doodle figure must physically interact with the person Style goals: realistic photography + flat black doodle art, strong contrast, surreal meme humor, clean polished social-media aesthetic, realistic anatomy, strong identity match. Negative prompt: gore, blood, injury, horror, abuse, sexual content, creepy monster, realistic creature, detailed doodle face, colored doodle, messy background, cartoon human, anime style, weak resemblance, extra limbs, bad anatomy, floating body, no contact, text, watermark.
Generates a cute Japanese hot spring membership card profile illustration with a capybara soaking in a volcanic onsen.
Generate a high-fidelity "Urban Line Atlas Poster." The design is based on the visual language of a monochrome urban line-drawing travel poster, featuring a visual framework consisting of a top title, middle streetscape depth, core landmarks, flanking buildings, foreground figures, and a bottom footer. [Theme City Details] - City Name: [Insert Name] - Main English Title: [e.g., TOKYO RHYTHM / SHIBUYA PULSE / URBAN LINE ATLAS] - Local Language Title: [Chinese or native name] - Country/Region: [Location] - Core Landmark: [Representative landmark] - Street Scene: [Specific neighborhood or atmosphere] - Mood Theme: [Commuter morning / Rainy street / Weekend afternoon / Sunset cycling / Twilight walk] - Color Palette: [Vermilion / Black-gray / Deep indigo / Dark green / Umber / Burgundy] - Aspect Ratio: [3:4 or 2:3 vertical] [Positioning] This is a hybrid of a travel memorial, urban visual atlas, architectural manuscript, and editorial cover. It should feel like a high-end urban archive rather than a generic tourist brochure—combining city recognition with authentic street-life vitality. [Composition] 1. Top Title Area: Bold and striking English titles, potentially including city codes, series numbers, coordinates, or subheadings. 2. Middle Streetscape: Deep perspective view. The angle can be centered, slightly tilted, or a high-angle view to ensure a unique composition. 3. Visual Anchor: Core landmarks should be recognizable in the mid or background, integrated naturally into the daily street scene. 4. High-Density Details: Flanking buildings should feature local facades, shops, road signs, traffic lights, subway entrances, and wires. 5. Human Elements: Include natural foreground elements like commuters, cyclists, tourists, coffee cups, or taxis to add a sense of life. 6. Footer: A standalone area designed like a city tag, travel receipt, or archive index. [Typography & Style] Text must be crisp and integrated into the design system. Use monochrome or minimal duotone line-drawing style on paper textures (cream/light gray). Lines should be precise and restrained, resembling architectural pen sketches or screen prints. [Innovation & Constraints] Please innovate in title placement, street perspective, and information modules. Avoid: Watercolors, thick painting, cartoon/chibi styles, cyberpunk, large color blocks, or cheap souvenir aesthetics. Generate a high-definition, clean-lined, collectible vertical urban poster.
A prompt for Seedance 2.0 to generate a short promotional video for an iPhone. The prompt details the sequence: starting with the phone's front view showing 9:41, three discontinuous close-ups focusing on the Dynamic Island, the view entering the Dynamic Island, a black screen, a new iPhone rising from the bottom with a metal frame and three cameras, its disappearance in smoke, and finally the text 'Titanium' changing to 'iPhone 15 Pro.'
A detailed Seedance 2.0 prompt for generating a 15-second, single-shot, realistic office vlog video. The scene features a young woman walking and talking to her phone camera in a large internet company office, complaining about the OpenClaw AI tool's instability and cost.