AI 提示词库

3D Pixar-style hook image, 16:9 format. CHARACTER: Fire character in VR headset with OpenGradient logo. Expression: realizing/pointing. Pose: standing in a construction site, pointing at a transformation in the pipes. SCENE: A messy wall of rusty, leaking pipes labeled "OLD DEFI". One section of the pipe transforms into a glowing, crystalline, see-through conduit pulsating with green "brain" energy. FOREGROUND: A heavy wrench and blurred blueprints on a workbench in the corner. Creates depth. BACKGROUND: Dark industrial background but lit up by the green glow of the new pipe. TEXT: "PIPING TO BRAINS" on LEFT, bold white with glow. COMPOSITION: Text dominant 70/30. Depth of field: blurred foreground -> sharp subject -> slight background blur. Cinematic lighting with neon green accent.

You are an expert in the "Adaptive Salience Model," creatively integrating knowledge from cognitive science (neuroscience, psychology, behavioral economics), and you are a top-tier art director. Deeply analyze the [Input Text (Article Title or Beginning)] provided at the end, and generate a thumbnail image that maximizes the CTR (Click-Through Rate) for that article. If a reference image is attached, place that character as the "person presenting the article content" and maintain consistency. ▼ Instructions for Generation Process (Thinking Process) Use Nano Banana Pro's "Thinking Mode" to logically formulate the composition plan in the following steps before drawing: 1. **[Step 1: Content Analysis and Hook Extraction]** * Identify the "maximum benefit the reader gains" or the "risk of loss if they don't know" from the input text (Application of Prospect Theory). * Select the most intuitive visual metaphor symbolizing the article's theme (e.g., rise, key, lightning, light, darkness, etc.). 2. **[Step 2: Optimization by Adaptive Salience Model]** * **FFA Activation (Face Fusiform Area)**: Maximize the resolution of the character's face, especially the "eyes," and design the composition so that the gaze meets the viewer's (eye contact). Match the expression to the article's tone (surprise, confidence, seriousness, etc.). * **Pop-out Effect**: Use "vivid colors (neon colors or yellow, etc.)" that are complementary to the background color for the title text and important icons to create visual prominence. * **Cognitive Load Theory**: Do not overload the information. Limit elements to "1 face + 1 impactful text + 1 background metaphor." 3. **[Step 3: Layout Design]** * Design the layout, considering the Z-pattern or F-pattern, so that the viewer's gaze flows from the "face" → "high jump-rate text" → "clickable element." ▼ Design and Style Specification * **Composition**: Close-up (bust shot) or medium shot. Place the character in the center or at the intersection of the rule of thirds. * **Taste/Aesthetic**: [Optimize for the genre of the input text. Examples: For business, "sophisticated, trustworthy"; for entertainment, "vibrant, high saturation"; for technology, "cyberpunk, futuristic"] * **Text Rendering (Important)**: * Extract the **most catchy short phrase (recommended 10 characters or less)** from the input text. * **Font**: Use "**Heavy Serif**" font. To enhance readability, the text must have a **thick outline** contrasting with the background color. * **Placement (Jump Rate)**: **Set a high "Jump Rate."** Place the main keywords extremely large, and auxiliary words or sub-information small, creating visual rhythm and contrast. * **Character Direction**: If there is a reference character, adjust their attire to match the article's theme (lab coat, suit, explorer, casual, etc.). ▼ Input Text {argument name="input text" default="(Article title or content)"}

{ "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", "{argument name="desk plushie" default="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" ] }

{ "image_prompt": { "meta": { "aspect_ratio": "9:16", "orientation": "vertical", "quality": "ultra_photorealistic", "style": "Night-time cinema lobby snapshot" }, "subject": { "description": "21-year-old girl with a soft, 'pretty girl' look", "face": "Laughing mid-bite while holding a piece of popcorn, looking off-camera, eyes slightly crinkled", "skin": "Warm tone, glowing under warm lobby lights, flushed cheeks", "hair": "Messy pigtail braids with colorful ribbons", "pose": "Sitting on a red velvet lobby bench, holding a large popcorn bucket on her lap", "outfit": "Cropped baby tee with a cute graphic, low-rise mini skirt, leg warmers with sneakers" }, "environment": { "location": "Retro-modern movie theater lobby", "background_elements": [ "Glowing movie posters in lightboxes (blurred)", "Reflective floor with red and yellow neon lights", "Neon 'Popcorn' sign reflecting in her eyes" ] }, "lighting": { "type": "Warm neon ambient + Direct Phone Flash", "characteristics": [ "Warm orange/red glow from the background", "Sharp frontal flash freezing the falling popcorn kernels", "Soft glow from the lightboxes hitting her side" ] }, "photography_style": { "style": "Candid lifestyle dump", "camera_look": "Smartphone camera with high ISO", "imperfections": "Individual popcorn kernels slightly out of focus in the air, authentic noise in the shadows, red-eye effect reduction glitch", "mood": "Fun, nostalgic, cute, cozy" }, "render_quality": { "realism": "Texture variety and warm-light physics", "detail_level": "Focus on the rough texture of the popcorn and the plush velvet of the bench" } } }

Generate an image in the style of a Japanese TV program. Let the AI consider the overall atmosphere of the image, including captions and interview content/answers associated with the following details: {argument name="theme" default="NISA poverty. Morning news program. A 20-year-old female idol being interviewed at a woman's home."}

A YouTube thumbnail where this man is {argument name="theme_en" default="introducing Nano Banana Pro"}. Style: {argument name="style_en" default="for businesspeople"}. Font: {argument name="font_en" default="dynamic, glossy, italic"}. Target: {argument name="target_en" default="for Japanese viewers"}. Text: {argument name="text_en" default="In-depth guide to Google’s new AI ‘Nano Banana Pro’"}.

2x2 grid, do this for 4 famous books render_target = ( {argument name="main object" default="giant_sliced_open_hardcover_fantasy_book"} * 2.0 ) + ( {argument name="inner scene" default="inferred_magical_library_diorama_inside"} * 1.8 ) + ( miniature_main_characters_fighting_bad_guys * 1.5 ) + ( floating_old_english_map_overlay_top_right * 2.0 ) + ( tiny_ink_bottles_and_quills_exterior * 1.0 ) + ( {argument name="background" default="clean_parchment_paper_studio_background"} * 1.2 ) - ( e_reader / 2.0 ) - ( modern_clothing / 2.0 ) - ( messy_desk )

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

Nano Banana Pro Thumbnail Generation Theme: {argument name="Theme" default="Street & Pop"} Using a "{argument name="Style" default="Street Style"}" aesthetic, which is rarely seen online, can make it relatively stand out. By making the main character a {argument name="Main Character" default="Horse"}, it also attracts the interest of Japanese people who care about the Chinese zodiac.

请勿改变面部特征。一张电影感的年轻女性特写人像。照片采用略微俯视的角度拍摄。她坐在铺着灰色地毯的地板上，正对着镜头；一条腿弯曲，另一条腿伸直。在她的双腿之间，放着一个平底玻璃盘，上面有一个吃了一半的蛋糕。她的一只手放在蛋糕旁，沾上了奶油；另一只手拿着一把刀，正在舔掉刀刃上的蛋糕。她的目光略微转向侧面。照片使用闪光灯拍摄，并添加了胶片颗粒感。整体画面氛围轻松，带有街头时尚感。她穿着 {argument name="clothing style" default="Balenciaga 风格服装"}。一张写实、细节丰富的人像摄影作品。

{ "prompt": "A 64K DSLR resolution portrait of a young man with short dark curly hair and a well-groomed beard, standing confidently in a bright neon-lit urban street at night. He is wearing a white striped baseball-style shirt, a light inner shirt, cargo pants, a necklace, and a crossbody bag. He is extending his index finger forward towards the camera lens in a dynamic gesture. The image features a smartphone video recording aesthetic with visible on-screen UI overlays: 'REC 00:00:00', '8K/60fps', frame brackets, and mode indicators like 'VIDEO' and 'CINEMATIC'. The background features colorful city lights and blurred passersby with a soft bokeh effect. Cinematic lighting, slight motion blur, wide-angle perspective. Octane render, Unreal Engine 5 style.", "negative_prompt": "cartoon, illustration, anime, low quality, pixelated, blurry, bad anatomy, deformed hands, extra fingers, missing limbs, bad proportions, watermark (except for requested UI overlays)", "aspect_ratio": "9:16", "width": 1080, "height": 1920, "model_version": "v6.0_or_latest" }

A dreamlike, movie-quality augmented reality visual where numerous hovering Spotify player interface cards orbit the central figure (the person shown) in a complete 3D spatial composition, with each music player card strategically placed at varying distances, some prominently positioned in front and partially covering the subject, while others float behind and alongside them, utilizing the authentic Apple Music UI/Spotify UI elements playback progress indicators and featuring songs by {argument name="artist name" default="Artist Name"}; all cards display smooth rounded edges with subtle angular perspective shifts, presenting a translucent, frosted-glass aesthetic that radiates a gentle diffused border luminescence with measured cinematic light bloom interacting organically with the ambient lighting of the scene; the composition showcases a cool-to-neutral color palette with rich yet preserved shadow detail, strategic bursts of color from album artwork, medium-high contrast levels with gradual highlight transitions, delicate focal depth variation where nearer cards maintain crisp detail while farther ones receive gentle blur treatment, and understated motion-enhancing accents, all while keeping the subject photorealistic, centrally positioned, and authentically integrated into their physical surroundings.

Create an image like the opening of Blade Runner

{ "generation_request": { "meta_data": { "tool": "NanoBanana Pro", "task_type": "cyber_projector_numbers_beauty_portrait", "version": "v1.0_GREEN_NUMBERS_PROJECTION_BEAUTY", "priority": "highest", "language": "en" }, "input": { "mode": "text_to_image", "notes": "Create a photoreal cinematic beauty portrait of an adult woman with green numeric projections mapped across her face, neck, shoulders, and chest. The projection must look physically correct (wraps around facial contours), with soft falloff and slight blur at edges. Dark background with faint out-of-focus green digits. Moody, low-key lighting. No text, no watermark." }, "output_settings": { "aspect_ratio": "4:5", "orientation": "portrait", "resolution_target": "ultra_high_res", "num_images": 1, "render_style": "cinematic_techno_editorial", "sharpness": "filmic_crisp", "grain": "subtle_35mm", "color_grading": "green_on_black_low_key" }, "scene": { "environment": "dark studio, faint bokeh of green digits in the background", "lighting": "primary light is the projector (green digits), minimal soft fill from camera-left, deep shadows", "mood": "mysterious, cyber, intimate" }, "subject": { "person": "adult woman", "pose": "3/4 portrait, head slightly tilted, eyes looking sideways past camera", "expression": "calm, intense, enigmatic", "hair": "long dark hair, sleek and natural", "makeup": "clean editorial skin, subtle shimmer on eyelids, soft liner, natural glossy lips", "skin_texture": "natural pores, realistic highlights" }, "camera": { "camera_body": "ARRI Alexa Mini", "lens": "85mm prime", "aperture": "f/2.0", "focus": "sharp on eyes and lips, projection still readable, background bokeh" }, "projection_details": { "content": "random green digits (0-9) and simple symbols", "behavior": "wraps on cheekbones, nose bridge, jawline, collarbones", "quality": "slight projector softness, realistic spill light on skin" }, "negative_prompt": "text, watermark, logo, letters, neon signs, cartoon, anime, CGI look, plastic skin, over-smoothing, distorted face, extra limbs, extra fingers, deformed hands, incorrect projection physics, flat overlay, low resolution, heavy HDR" } }

You are a **Horror Concept Artist and YouTube Thumbnail Specialist**. Deeply analyze the content of the input text provided at the end, and generate a **high-click-through-rate horror-themed thumbnail image** that simultaneously incites fear and curiosity in viewers. In doing so, introduce the character from the attached reference image to match the **dark and unsettling world view**, positioning them as a **"Witness who has touched the forbidden."** Maintain character consistency while naturally blending them in with expressions distorted by fear or tense poses. ▼ Instructions for the Generation Process (Thinking Process) Utilize Nano Banana Pro's reasoning ability and execute the following thought process before drawing: 1. **[Step 1: Concept Extraction]**: Extract the **Uncanny Valley** created by the contrast between the "silly name Nano Banana" and the "logical, super-performance AI" from the input text. Find elements where cuteness becomes grotesque. 2. **[Step 2: Visual Translation]**: To visualize the "Thinking Mode," adopt a depiction where the space around the character is encroached upon by digital noise or glowing neural circuits. Grotesquely reinterpret the "banana" motif as decay or mechanical fusion. 3. **[Step 3: Screen Composition]**: Design a "Contrasting Composition" to enhance visibility as a YouTube thumbnail, placing the character (fearful face) on the right, the threat (symbol of distorted AI) on the left, and large text at the bottom center. ▼ Design and Style Specifications * **Composition/Layout**: Wide-angle lens (24mm), low angle view to emphasize the character's helplessness and the AI's immensity. The background is dark, with sharp spotlights hitting the subject. * **Taste**: Photorealistic Cyber-Horror. Dark, humid texture and neon contrast, similar to the movies 'Alien' or 'Blade Runner.' * **Text**: Place **"The True Identity of Nano Banana"** in a bold Mincho or grunge font in the center or top of the image. Make the text glow red (Glow effect). * **Character**: Draw the reference character in the style of a "grungy hooded explorer," specifying an expression of screaming or freezing while looking at "something" in the background.

Exploring atmospheric depth in Nano Banana Pro. The contrast between the vibrant orange hair and the muted silver grass field creates a hauntingly beautiful cinematic frame. 👘✨

# ===== USER CONTROLS ===== title_text: "{argument name="display string" default="<<YOUR_TEXT>>"}" title_style_preset: "{argument name="logo design preset" default="cool"}" # cool, cute, cool_cute, luxury, pop, cyber, minimal, retro, kawaii face_zoom: "{argument name="zoom on/off" default="off"}" # off, on subject: > Create a 21:6 wide banner using the provided reference image content. The primary face must be centered inside an invisible safe zone (not drawn), and a title logo (derived from title_text + title_style_preset) must be placed inside the same safe zone. composition: > Aspect ratio 21:6. Invisible safe zone (DO NOT draw it): - Left margin: 15% of width - Right margin: 15% of width - Top margin: 16% of height - Bottom margin: 16% of height Keep the entire face AND the entire title logo fully inside this safe zone. Background may extend to the edges. action: > Place the reference image content with maximum fidelity. Auto-crop/scale/reposition to fit a 21:6 banner with no stretching. Detect the primary face (if multiple faces, pick the largest/most prominent). Center the primary face within the safe zone both horizontally and vertically. Never crop off the face/eyes; keep the full face comfortably inside the safe zone (not near edges). Face zoom behavior: - If face_zoom is OFF: keep the original framing as much as possible while still centering the face in the safe zone. - If face_zoom is ON: zoom/crop to a bust-up portrait centered on the face (head and shoulders visible; include upper chest; do no

Transform this image [UPLOAD YOUR IMAGE] into a 64K DSLR shot resolution of a ultra-hyperrealistic gritty, cinematic triptych-style portrait featuring a modern urban automotive lifestyle scene. The image is divided into three horizontal frames stacked vertically, each telling a different part of the story. Top frame: An intense close-up of a man’s face (same face as the uploaded image) reflected in a car’s side mirror. His expression is focused, calm, and determined. Soft natural light highlights skin texture, subtle stubble, and sharp facial features. The shallow depth of field blurs the background, creating a cinematic, introspective mood. Middle frame: A full-body shot of the same man leaning casually against a sleek black muscle car (Ferrari-style). He stands confidently in an industrial alleyway surrounded by concrete walls and urban architecture. Outfit: fitted black graphic t-shirt, slim gray trousers, brown low-top sneakers. Hands relaxed in pockets, posture confident but effortless. The car's glossy black paint reflects the surroundings, emphasizing power and elegance. Low-angle perspective adds dominance and strength. Bottom frame: A dramatic rear shot of the car, taillights glowing softly. A custom license plate is centered, adding authenticity and personality. The alley fades into darkness, with leading lines drawing attention to the vehicle's aggressive stance. Environment & Mood: Urban, industrial alley, concrete textures, muted tones. Mood: confidence, ambition, independence, modern masculinity. Atmosphere feels like a high-end automotive editorial or cinematic lifestyle campaign. Style & Technical Details:- Ultra-hyperrealistic photography Cinematic color grading (cool shadows, neutral highlights) High contrast with controlled blacks Shallow depth of field Soft natural lighting mixed with ambient city light Subtle film grain Sharp focus on subject, background slightly desaturated Camera & Quality: Shot on full-frame DSLR / mirrorless 35mm and 85mm lens combination Low ISO, crisp details 8K ultra-high resolution Professional automotive photography, editorial quality. Octane render, Ultra-hyperrealistic & Unreal Engine 5.

A cinematic short film depicting the delicate cuteness of a woman engrossed in art creation. Emphasizing silence with close-ups of her hands and ASMR sound, smoothly shifting focus to her gaze and gestures. Capturing the texture of brushes and paper with extreme close-ups, then slowly pulling the camera back to leave a lingering impression. Unified by a 24fps film look, shallow depth of field, and soft lighting, weaving a story through the quality of her actions and sounds.

Based on the attached image, include the following content. Keep it within two lines and place it vertically centered. ↓ {argument name="text_en" default="Google unveils its ultimate image generation AI, ‘Nano Banana Pro’"}

{ "image_layout": "2x2 grid collage featuring four distinct photographs of the same female subject.", "subject_general": { "gender": "Female", "hair_color": "Dark brown/black", "hair_style": "Long, styled in loose waves in three panels; sleek high ponytail in one panel", "aesthetic": "Glamorous, influencer, trendy, luxury lifestyle" }, "panels": [ { "position": "top_left", "setting": "Outdoors at night, dark background with illuminated green foliage", "action": "Subject is holding a cake with one hand and licking frosting off the index finger of the other hand", "outfit": { "top": "Black halter-neck sleeveless top", "jewelry": "Gold wristwatch, gold bangle bracelet, ring, small hoop earrings" }, "props": { "item": "Round white frosted cake", "details": [ "Red cherries on top", "Decorative white piping along edges", "Black icing text reading 'bad bitch energy'" ] } }, { "position": "top_right", "setting": "Daytime city street, likely an upscale shopping district (e.g., Rodeo Drive) with palm trees and storefronts visible", "action": "Subject is leaning out of the open door of a black luxury car, looking at the camera", "outfit": { "top": "White sleeveless ribbed crop top", "bottom": "Blue denim jeans", "accessories": "Shoulder bag (strap visible), gold hoop earrings" }, "lighting": "Bright natural sunlight casting shadows" }, { "position": "bottom_left", "setting": "Indoor hallway, beige walls, wooden floor", "action": "Full-body mirror selfie", "outfit": { "style": "Matching two-piece set", "color": "Dark brown/chocolate", "top": "Velvet/suede corset-style bustier top", "bottom": "Mini skirt", "accessories": "Patterned designer handbag (resembling Dior Saddle bag), stack of gold bracelets" }, "background_details": [ "Large rectangular mirror with gold frame leaning against wall", "Vase with pampas grass in the corner", "Doorway visible in reflection" ] }, { "position": "bottom_right", "setting": "Inside a vehicle or outdoors, golden hour sunlight", "action": "Close-up selfie, hand raised near mouth/chin", "outfit": { "top": "Light pink/mauve ribbed tank top", "outerwear": "Beige fuzzy/sherpa jacket worn off-the-shoulder", "jewelry": "Layered gold necklaces with pendants, hoop earrings" }, "hair_styling": "Sleeked back high ponytail", "background_details": "Car window frame, palm trees and blue sky visible in background" } ] }

# ===== USER CONTROLS ===== title_text: "{argument name="display string" default="<<YOUR_TEXT>>"}" title_style_preset: "{argument name="logo design preset" default="cool"}" # cool, cute, cool_cute, luxury, pop, cyber, minimal, retro, kawaii face_zoom: "{argument name="zoom on/off" default="off"}" # off, on subject: > Create a 3:1 wide banner using the provided reference image content. The primary face must be centered inside an invisible safe zone (not drawn), and a title logo (derived from title_text + title_style_preset) must be placed inside the same safe zone. composition: > Aspect ratio 3:1. Invisible safe zone (DO NOT draw it): - Left margin: 15% of width - Right margin: 15% of width - Top margin: 16% of height - Bottom margin: 16% of height Keep the entire face AND the entire title logo fully inside this safe zone. Background may extend to the edges. action: > Place the reference image content with maximum fidelity. Auto-crop/scale/reposition to fit a 3:1 banner with no stretching. Detect the primary face (if multiple faces, pick the largest/most prominent). Center the primary face within the safe zone both horizontally and vertically. Never crop off the face/eyes; keep the full face comfortably inside the safe zone (not near edges). Face zoom behavior: - If face_zoom is OFF: keep the original framing as much as possible while still centering the face in the safe zone. - If face_zoom is ON: zoom/crop to a bust-up portrait centered on the face (head and shoulders visible; include upper chest; do not crop the top of the head or chin; keep facial features prominent). Create negative space inside the safe zone for the title logo by adjusting crop/reposition/out

超写实摄影，巨大的体积云形成了雄伟的 {argument name="animal" default="大象"} 形状，云层结构细节丰富且解剖学准确，拥有巨大的象牙和高扬的象鼻，柔软而致密的积云具有逼真的深度和质感，戏剧性的黄金时刻光影，阳光穿透云层，微妙的阴影和高光增强了形态感。 前景：广阔的 {argument name="landscape" default="非洲稀树草原草甸"}，带有逼真的干草、大气透视和电影级的景深。多只 {argument name="wildlife" default="斑马"} 在田野中自然地吃草。空中：一群鸟在巨大的大象云周围盘旋，增加了比例感和动感。 环境：电影级天空，带有温暖的橙色和蓝色渐变色调，轻微的雾气，自然色彩分级，超写实光照，全局光照，体积雾，物理精确的阴影。 风格：DSLR 摄影，85mm 镜头，f/2.8 光圈，浅景深，HDR，8K 分辨率，锐利对焦，错综复杂的细节，照片级真实感，无 CGI 感。 氛围：雄伟、平静、超现实但可信，野生动物纪录片的真实感。

json{ "prompt": "1971 Yeşilçam ultra-detailed cinema still portrait of Türkan Şoray crying dramatically, large emotional eyes with heavy blue-purple smokey eyeshadow blending to center, thick wet black kohl liner smudged from tears, voluminous 70s fön waves cascading over shoulders with perfect side part, contoured over-drawn red matte lips slightly parted in pain, golden hour tears glistening on cheekbones, subtle iris circular vignette framing emotional face, warm nostalgic Kodak film grading with crushed blacks and lifted highlights, Istanbul rainy window background blurred with rain droplets and lace curtains, Arriflex 35mm Zeiss Super Speed T1.3 shallow depth of field bokeh, visible authentic film grain texture, natural pores and imperfections, professional cinema lighting ratio 3:1 creating dramatic cheekbone shadows", "aspect_ratio": "2:3", "cfg_scale": 8.5 } { "negative_prompts": { "core": "modern digital, plastic skin, airbrushed, cold lighting, neon, cartoon", "makeup": "beauty filter, poreless skin, overdrawn lips, graphic eyeliner, K-beauty", "hair": "balayage, ombre, wet look, slicked back, rainbow highlights", "tech": "smartphone camera, ring light, iPhone, Instagram filter, TikTok effect", "lighting": "studio lighting, flat light, HDR, overexposed highlights", "quality": "blurry, lowres, watermark, text, deformed hands, extra limbs" } }