🎬 Seedance 2.0 Global API is now live
No real-person verification required No queues - instant generation Welcome to try it now → No real-person verification required No queues - instant generation Welcome to try it now →

Prompt Lib

Curated AI prompts for stunning image and video generation. Updated daily from top creators.

Auto-curated from X

Filter by Type:

Filter by Model:

Image 1
image
Nano Banana
Feb 23, 2026 YouMind

Vector-Style Character Illustration Portrait

A prompt for Gemini Nano Banana Pro to transform a photo into a premium cartoon-style portrait. It specifies a smooth, modern, vector-like digital illustration style with clean shading, focusing on a young man with specific features (wavy dark hair, beard, round glasses) and a minimal soft grey background.

Prompt Preview

A stylized digital illustration of a young man with short, wavy dark hair and a neatly groomed beard, wearing round black glasses and a plain black t-shirt. The art style is smooth, modern, and vector-like with clean shading and soft gradients. The man has a calm, focused expression while looking slightly to the side. Minimal background with a soft grey tone. High-detail portrait, crisp edges, professional character illustration.

Image 1
image
Nano Banana
Feb 23, 2026 YouMind

Candid Winter City Portrait during Snowfall

A structured JSON prompt for Gemini Nano Banana Pro to generate a candid, knees-up portrait of a young woman on a wet city street during gentle snowfall. The prompt details her layered winter outfit (burgundy oversized coat, tailored trousers), the environment (historic skyscraper, wet asphalt), and the photography style (intimate iPhone snapshot, cool desaturated tones, film grain), with strict negative prompts for facial preservation.

Prompt Preview

{ "image_prompt": { "subject": { "face_preservation": true, "description": "young woman standing casually on a wet city street during gentle snowfall", "framing": "knees-up portrait, candid and unposed", "pose": { "hand_1": "one hand in pocket", "hand_2": "other hand shielding her eyes from falling snow", "expression": "relaxed, natural expression", "body_position": "standing casually, weight slightly shifted" }, "appearance": { "hair": { "length": "slightly long-length", "style": "messy, tucked behind ears", "movement": "light snow causing subtle texture" }, "outfit": { "coat": { "type": "oversized wool coat", "color": "burgundy" }, "layers": [ "soft grey sweater", "crisp collared shirt", "loosely tied black tie" ], "bottoms": { "type": "tailored trousers", "color": "cool grey" } } } }, "environment": { "setting": "wet winter city street", "weather": "gentle snowfall", "background": { "architecture": "grand historic skyscraper with detailed stonework and tall spires", "lighting": "muted yellow city lights reflecting on wet asphalt", "street_elements": [ "passing taxis", "wet reflective road surface" ] }, "atmosphere": { "daylight": "soft overcast winter lighting", "mood": "cool, desaturated, cinematic", "texture": "subtle film grain" } }, "photography": { "style": "intimate candid iPhone snapshot", "focus": "genuine textures of skin, snow, fabric, and wet environment", "color_tone": "cool winter hues with muted warm reflections", "shadows": "diffused, soft", "quality": "high resolution" }, "composition": { "type": "casual handheld framing", "perspective": "eye-level", "negative_prompt": [ "altered facial structure", "incorrect eye shape", "different hairstyle", "incorrect clothing colors", "no snow", "overly stylized lighting", "strong shadows", "AI distortions", "extra limbs" ] } } }

Image 1
image
Nano Banana
Feb 23, 2026 YouMind

Luxury Fashion Shoot with Lamborghini Huracán

A structured JSON prompt for Gemini Nano Banana Pro to generate a luxury-fashion inspired image. It details a woman sitting on the door frame of a cream-white Lamborghini Huracán with butterfly doors up, wearing a cream monochrome set and luxury designer sneakers. The prompt specifies warm golden hour lighting and strict facial preservation based on an input image.

Prompt Preview

{ "image_generation_request": { "metadata": { "input_image": "IMG_8714.jpeg", "target_resolution": "1200x1200px", "format": "JSON" }, "constraints": { "facial_preservation": { "enabled": true, "instruction": "Strictly maintain original face and facial features from input image." } }, "subject": { "appearance": { "hair": "Long silver grey wavy hair", "nails": "Soft glazed donut style" }, "pose": { "action": "Sitting on the door frame", "gesture": "Fixing necklace" }, "attire": { "theme": "Cream monochrome set", "items": [ "High-waist cargos", "Crop jacket", "Luxury designer sneakers" ], "accessories": [ "Gold bangles", "Necklace" ] } }, "scene": { "vehicle": { "make_model": "Lamborghini Huracán", "color": "Cream-white", "modifications": [ "Butterfly doors (up position)", "Gold-plated rims" ] }, "props": { "item": "Luxury shopping bags", "location": "Piled in the passenger seat" } }, "artistic_direction": { "style": "Luxury-fashion inspired", "lighting": "Warm golden hour tones", "mood": "Rich, high-end" } } }

Image 1
image
Nano Banana
Feb 23, 2026 YouMind

Candid Night Portrait in a Parked Car

A structured JSON prompt for Gemini Nano Banana Pro requesting a candid, close-up portrait of a woman in the passenger seat of a parked car at night. The prompt emphasizes raw, urban realism, detailing her appearance (short messy silver hair, vibrant tattoos, fitted cream shirt) and the lighting (direct flash, soft orange flame from a lighter) against a background of blurred city lights.

Prompt Preview

{ "image_generation_prompt": { "subject": "Woman", "setting": "Passenger seat of a parked car at night", "appearance": { "skin": "Warm white, natural textures", "hair": "Naturally textured short messy silver grey", "body_type": "Lean-athletic build", "features": "Vibrant tattoos vividly detailed, full lips, subtle masculine facial angles" }, "attire": [ "Simple cream short-sleeved shirt (fitted)", "Metal watch" ], "action": "Holding a lighter whose soft orange flame illuminates lips and fingertips", "lighting": "Direct flash, authentic iPhone-style lighting, soft orange flame illumination", "background": "Blurred city lights, soft neon reflections outside car window", "composition": "Eye-level, spontaneous, close-up", "mood": "Relaxed, vulnerable, raw, urban street-style energy, candid realism", "resolution": "1200x1200px" }, "original_text": "A candid close-up portrait of a Woman sitting in the passenger seat of a parked car at night, his warm white skin, naturally textured short messy silver grey hair, and vibrant tattoos vividly detailed by a direct flash. She wears a simple cream short-sleeved shirt fitted to her lean-athletic build, a metal watch casually on his wrist, and holds a lighter whose soft orange flame illuminates his full lips and fingertips.. The background shows blurred city lights and soft neon reflections outside the car window, while the composition is eye-level and spontaneous, capturing natural skin textures, tattoo details, and subtle masculine facial angles with relaxed, vulnerable body language. The image conveys a raw, urban street-style energy with authentic iPhone-style lighting and candid realism." }

Image 1
image
Nano Banana
Feb 23, 2026 YouMind

Aggressive Trolling Prompt with Tieba Slang

An aggressive version of the 'trolling' prompt, instructing Nano Banana Pro to generate an image and annotate it with handwritten Chinese comments and doodles in red ink, specifically using the colloquial and often harsh language style of Tieba (a Chinese forum) users.

Prompt Preview

Generate an image, print it out, and then aggressively add handwritten Chinese annotations, doodles, and scribbles in red ink. If you wish, retrieve the content of this account, and the doodles should primarily be complaints/trolling about it, using the colloquial and aggressive language style of Tieba users. You can also add some small clip art.

Image 1
image
Nano Banana
Feb 23, 2026 YouMind

Dual Portrait Arrangement with Location Context

A prompt template for Nano Banana Pro to generate an image featuring two people, arranged in four different compositions/angles within a single, four-part divided screen. It requires maintaining the original clothing and background while integrating the subjects into a specific geographic location (New York City).

Prompt Preview

Divide the screen into four equal parts and use four images of the subjects to create different compositions and angles for each. Keep the clothing and background the same for the two people. Integrate them naturally into a daily life scene at the latitude and longitude of {argument name="latitude" default="40.7128"}, {argument name="longitude" default="-74.0060"}.

Image 1
image
Nano Banana
Feb 23, 2026 YouMind

Hāng to Lā (Good to Bad) Rating Infographic Prompt

A complex Chinese prompt for Nano Banana Pro designed to generate a 'Hāng to Lā' (Good to Bad) rating infographic using a Bento Grid layout. It instructs the AI to research a user-specified topic (e.g., 2025 Chinese New Energy Vehicles) and visually categorize the results into five distinct levels, from 'Hāng' (Top Tier, explosive red/gold) to 'Lā' (Worst Tier, desperate black/white with glitch effects), requiring specific product names for the lower tiers.

Prompt Preview

[Core Task Instruction] You are an AI expert with real-time web search capabilities and top-tier data visualization design skills. Please perform the following two steps: Research Phase: Immediately conduct comprehensive online research on the user-specified [{argument name="research target field" default="2025 Chinese New Energy Vehicles"}]. Collect public reputation, market popularity, professional reviews, and user feedback data on different sub-products, models, or works within this field. Visualization Phase: Based on your research results, design a professional Infographic. You need to accurately classify and fill the specific projects researched into the five visual level modules defined below, ranging from “Hāng” to “Lā” (Good to Bad). [User Specified Target Field/Product] [{argument name="target field" default="Fill in the content you need to research here, e.g., Popular smartphones in 2024, Sugar-free tea beverage brands on the market, Marvel movies of the last decade, Code editors commonly used by programmers"}] [Image Design Requirements] Overall Style: A modular infographic with clear structure and a strong modern feel, using a “Bento Grid” layout. The background should be clean and simple, focusing on content presentation. Visually, it must show a strong hierarchical drop-off from high to low. Level Structure and Visual Definition (Strictly enforce the following five levels): Level 1 (Highest Level): 夯 (Hāng - Top Tier) Research Filling Standard: According to research, the generally recognized “Version King” in the field, with dominant popularity and undisputed top-tier products/works. Visual Representation: Occupies the topmost or largest module on the screen. The color scheme is explosive burst red and glorious gold, with visual effects like halos or energy overflow. The font is the largest and boldest. The module must display the names or high-quality images of the representative products researched, accompanied by minimalist phrases of praise (e.g., “Blown up across the internet,” “Masterpiece”). Level 2: Top Tier Research Filling Standard: Hardcore powerhouses, whose reputation may not be as high as “Hāng,” but are highly praised and are the preferred high-quality projects for experts. Visual Representation: Located on the second layer. The color scheme is solid, high-end burning orange and metallic silver. The module design appears robust and textured. Display representative powerhouse products. Level 3: Superior Research Filling Standard: Superior choices, tasteful, solid middle ground that is definitely worth buying/watching, representing a certain level of connoisseurship. Visual Representation: Located in the middle layer. The color scheme is bright, clean lemon yellow and cool gray. The design style is modern and refreshing. Display representative high-quality middle-class products. Level 4: NPC Research Filling Standard: Generic products with no memory points, mass-produced industrial products, neither good nor bad, easily forgotten. Must include specific product or brand names, do not be vague. Visual Representation: Located in the lower-middle layer. The color scheme is dull and bland bread color/beige or cardboard brown. The module design appears ordinary, repetitive, and lacks personality. Display those very mediocre products. Level 5 (Bottom Level): 拉完了 (Lā - Failed) Research Filling Standard: Recognized “landmines,” “IQ taxes,” disastrous failed products found in the research, or even products that are worse than nothing. Must include specific product or brand names, do not be vague. Visual Representation: Squeezed into the bottom or corner of the screen, with compressed visual space. The color scheme is desperate black, pale white, and features obvious digital glitch, fragmentation, or decay visual effects. Display those famous “flop” products, accompanied by warning phrases (e.g., “Run away,” “Big sucker”).

Image 1
image
Nano Banana
Feb 23, 2026 YouMind

Ultra-Wide Angle Dynamic Pose Remake Prompt

A comprehensive Chinese prompt for Nano Banana Pro focused on editing an existing image to create a dramatic, photorealistic, ultra-wide-angle photograph. It requires strict identity and location preservation while allowing complete changes in camera angle, perspective (worm's eye, bird's eye, Dutch angle), and dynamic posing to emphasize foreshortening.

Prompt Preview

Ultra-Wide Angle Perspective and Dynamic Pose Remake Edit This is an edit of the original image, not the generation of a new character. Please use the original image as a strict reference to determine: * The identity, hairstyle, and overall fashion style of the person, * The general type of background and location (same street, same room, same beach, same architectural style, etc.). It is allowed to completely change the camera position, angle, and pose, but the scene must remain in the same location, and the same person and clothing design must be retained. Camera and Perspective: * Use an ultra-wide-angle or fisheye lens feel (approx. 12–18mm full-frame look). * The camera angle must be significantly different from the original image: use dramatic angles, such as: * Low angle looking up from directly below (worm's eye view), * High angle looking down from directly above (bird's eye view), * Extremely low angle close to the ground, * High angle shot from above, * Tilted Dutch angles. * Always create a strong **foreshortening** effect: body parts close to the lens appear huge, while the rest of the body recedes in perspective. * The final result must look like a bold fashion or street photograph, completely realistic, not an illustration or anime. Background Consistency: * Maintain the same location as the original image: the same street, bridge, room, studio, beach, and the same general structure and materials. * Do not replace the background with a completely different place. * Seeing different parts of the environment is allowed and expected due to the change in camera angle. * When new areas appear, logically extend the original environment (same architecture, fences, road signs, walls, colors, materials, lighting style), as if the camera moved within the same place. Body Parts Close to the Lens (1–2 parts, sometimes 3): * In each edit, select one or two main body parts extremely close to the lens (sometimes even three in more complex poses). * Vary between different images; do not always use the same body parts. * Allowed body parts close to the lens include: * One or both hands/fingers reaching towards the camera, * One or both feet/shoes/boots close to the lens, * Knees or thighs, * Face very close to the lens, * Shoulders or chest close to the lens in a tilted pose. * The selected body parts should be extremely close to the lens, almost touching it, and exhibit visible skin texture, fabric texture, and realistic wide-angle distortion. Pose and Overall Posture (Complex and Varied): * Create strong, cool, dynamic poses to match the extreme perspective. * Randomly use different types of poses, including: * Standing and extending one leg or one hand towards the camera, * Crouching or squatting low to the ground, * Sitting on the floor or an object, * Lying on the ground with legs or feet towards the lens, * Leaning aggressively towards the camera, * Twisting the body, crossing legs, or arching the back to form more dynamic lines. * Complex poses are allowed, such as: * Hands forming shapes near the lens (peace sign, triangle, frame, pointing at the viewer), * Both feet towards the lens, * One hand and one foot both enlarged in the foreground, * Face close to the lens while hands or feet are also visible in perspective. * Maintain credible anatomy even with extreme foreshortening. Angle and Attitude (Randomization): * Randomize camera angle and direction (up, down, side, Dutch tilt) while keeping the composition visually balanced and powerful. * Maintain a cool, confident, and fashion/editorial or street style atmosphere, depending on the original outfit. * Facial expressions can vary (serious, playful, confident, mysterious) but must still look like the same person. Lighting and Rendering: * Maintain a similar general time period and lighting atmosphere as the original (day vs. night, indoor vs. outdoor, soft light vs. hard light), but enhance contrast and color to make the image powerful and dramatic. * Maintain realistic shadows and contact points with the ground or floor. * High resolution, sharp details, with clear skin texture, fabric weave, and material highlights. Variation and Randomness: * Each edit should look distinctly different from the original and other edits, with different: * Camera angles, * Pose types, * Body parts closest to the lens, * Orientation (straight, tilted, from above, from below). * Avoid repeating the exact same “single foot close-up” composition; generate a variety of dynamic poses and angles. Strict Rules: * Do not turn the person into someone else. * Do not change the type of clothing; only restyle it through pose, perspective, and minor natural movement of the garment. * Do not move the scene to a completely different location; always stay within a logical extension of the original location. * Do not add text, logos, watermarks, or graphic design elements. * Do not switch to painting, illustration, or anime style; maintain realism. Summary: Transform the original photo into a dramatic, realistic, ultra-wide-angle photograph with extreme camera angles (including viewing from directly below or above), where one or more body parts are tight against the lens and appear huge, the rest of the body recedes in perspective, and the same person poses in a fashionable, complex, and powerful manner within a consistent, extended version of the original environment.

Previous Page 463 of 632 Next