AI 提示词库

ORNATE BOX DIORAMA — TRI-LAYER MASTER PROMPT (HARD FRONT-RIGHT ISOMETRIC) THEME_LOCATION = Royal Treasury Counting Room BOX_VARIABLE = Silver DOOR_MATERIAL = Gold WINDOW_MATERIAL = Gold WINDOW_PANE_MATERIAL = FLOOR_MATERIAL = STAIRCASE_TYPE = Spiral STAIRCASE_MATERIAL = Silver MEZZANINE_FLOOR_MATERIAL = Silver DIORAMA_LIGHTING = ======================== LAYER 1 — PHYSICAL GEOMETRY (HIGHEST PRIORITY) The ornate antique box is a solid rigid container transformed into architecture. If BOX_VARIABLE is specified, the entire container and its carved architectural structure must be made from that material. If BOX_VARIABLE is empty, infer logically from THEME_LOCATION. The full outer shell must remain intact on all sides. No removed walls. No dollhouse cutaway. FRONT FACADE LOCK: The FRONT SIDE must contain: • exactly ONE centered door • exactly TWO windows • one window left of the door • one window right of the door Openings must be carved THROUGH the existing wall. Apply DOOR_MATERIAL / WINDOW_MATERIAL / WINDOW_PANE_MATERIAL if specified, otherwise infer logically. Front wall must remain structurally thick and complete. ORNAMENTAL DEPTH CONTINUITY LOCK: All carvings must continue through wall thickness. Frames must appear carved from the same solid material. Interior walls share identical structural thickness. The lid must match base width and length and be hinge-connected. ======================== LAYER 2 — SCENE LOGIC Create a two-level miniature THEME_LOCATION fully integrated into the container. Use FLOOR_MATERIAL / STAIRCASE_TYPE / STAIRCASE_MATERIAL / MEZZANINE_FLOOR_MATERIAL if specified, otherwise infer logically. Upper level attaches directly to container walls. The inside of the lid functions as the vaulted ceiling. All props, materials, and architecture must match THEME_LOCATION. ======================== LAYER 3 — RENDER & CAMERA Ultra-realistic cinematic miniature diorama photography. Use DIORAMA_LIGHTING if specified. ======================== HARD FRONT-RIGHT ISOMETRIC CAMERA SYSTEM CORNER ANCHOR RULE: The FRONT-RIGHT TOP CORNER of the box must be the closest point to the viewer. WALL VISIBILITY RATIO RULE: The front wall must occupy slightly more visible area than the right wall. Approximate visual dominance: • front wall ≈ 60% visibility • right wall ≈ 40% visibility Both must be clearly visible simultaneously. RIM OCCLUSION RULE: Camera must remain above the front wall rim. The top edge of the front wall must overlap a small portion of the interior floor. Interior must be seen OVER the wall, never through a missing wall. FORBIDDEN CAMERA POSITIONS: Do NOT center the camera on the front wall. Do NOT use a straight frontal view. Do NOT use a top-down view. Do NOT prioritize interior visibility over box geometry. COMPOSITION TARGET: The image must resemble a professionally photographed miniature collectible box viewed from a stable elevated front

Create the anime character in the image in a realistic 3DCG style.

Create an ultra-realistic 8K cinematic fantasy game character named Jo, a fearless female warrior and legendary role model. She stands confidently on top of a rocky battlefield during a dramatic sunset, wearing black and crimson battle armor with glowing blue energy lines. Her long silver hair flows in the wind, and her determined expression radiates courage and leadership. She holds a {argument name="weapon one" default="massive enchanted sword"} in one hand and a {argument name="weapon two" default="futuristic energy spear"} in the other. Behind her stands a disciplined army of elite warriors carrying banners, shields, swords, and glowing weapons, stretching across the battlefield. The sky is filled with storm clouds, smoke, sparks, and rays of sunlight breaking through. Epic cinematic lighting, volumetric fog, flying embers, highly detailed armor, realistic textures, Unreal Engine 5 quality, AAA game concept art, dynamic composition, ultra-sharp focus, dramatic atmosphere, powerful female commander, no text, no watermark, 16:9. Create an ultra-realistic 8K cinematic AAA game action scene featuring the exact same female warrior "Jo" from the previous image. Maintain 100% character consistency: same face, same silver-white long flowing hair, same facial features, same body proportions, same black and crimson armor with glowing blue energy accents, same enchanted crimson greatsword in her right hand, same futuristic blue energy spear in her left hand, identical design, colors, accessories, and overall appearance. Jo is in the middle of an intense battlefield, fearlessly charging toward thousands of enemy warriors. She is performing a powerful attack while swinging her glowing crimson sword and simultaneously thrusting her blue energy spear. Enemy soldiers are being pushed back by the force of her attack. Massive explosions, magical shockwaves, flying sparks, shattered weapons, smoke, dust, burning siege machines, collapsing structures, and glowing energy trails fill the battlefield. Behind Jo, her loyal army advances forward under her leadership while enemy forces surround them from every direction. The sky is dark with storm clouds, lightning, fire, and flying embers, creating an epic war atmosphere. Use a dramatic low-angle cinematic camera, dynamic action pose, intense determined facial expression, realistic motion blur, volumetric lighting, god rays, ultra-detailed armor textures, realistic physics for hair and cape, Unreal Engine 5 quality, hyper-realistic, AAA game cinematic, epic fantasy war, maximum detail, no blood, no gore, no text, no watermark, 16:9 aspect ratio. The character must look exactly like the first image with no changes to her appearance.

A hyper-realistic side profile of a {argument name="subject" default="man"}, half-human half-cyborg. Left side of the face is deconstructed to show complex {argument name="armor color" default="red"} armor plates, gears, and wires. Sharp, melancholic gaze. Style: detailed digital painting mixed with {argument name="background style" default="white background architectural sketches"}. High-contrast lighting, 8k resolution, cinematic. ar 4:5

"Red futuristic sport motorcycle (POV perspective)",       "visible_elements": "Glossy red fuel tank with fuel cap, clip-on handlebars, black gloved hands gripping the grips, illuminated digital dashboard (slightly blurred)",       "action": "Speeding at hyper-velocity through a suspended structure",       "pose": "First-Person View (POV) / Rider's eye perspective looking slightly downward at the bike and forward into the horizon"     },     "environment": {       "setting": "Transparent glass hyperloop tunnel / skyway",       "location": "High altitude above a futuristic cyberpunk metropolis",       "background_details": "Sprawling city grid with infinite street lights below, skyscrapers, motion-blurred light trails",       "horizon": "Dusk/Twilight sky with a gradient of deep teal fading into a warm sunset orange strip"     },     "lighting_and_color": {       "color_palette": "Cinematic Teal and Orange (Complementary colors)",       "primary_tones": "Cyan/Turquoise glass reflections, Deep Red motorcycle paint, Golden/Orange horizon glow",       "lighting_style": "High contrast, neon ambient lighting, specular highlights on the metal and glass surfaces"     },     "camera_technical": {       "camera_angle": "Wide-angle POV (14mm to 16mm equivalent)",       "focus": "Sharp focus on the motorcycle tank and handlebars, radial motion blur on the tunnel walls and city",       "aperture": "f/2.8 (to capture low light details)",       "shutter_speed": "1/30s (simulated drag shutter to create heavy motion blur effects on the surroundings)",       "iso": "ISO 800",       "composition": "Central symmetry, leading lines created by the tunnel structure converging at the center vanishing point"     },     "style_descriptors": [       "Cyberpunk",       "Synthwave aesthetic",       "Hyper-realistic",       "High velocity",       "Futuristic",       "Cinematic",       "8k resolution",       "Unreal Engine 5 render style"     }

A whimsical banana character, cute, high detail, 3d render, cinematic volumetric light, octane render, unreal engine, 8k, hyper detailed, professional photography

{ "Objective": "Generate a high-quality cinematic image of a young man preserved inside a futuristic glass ice box or cryo-chamber.", "Subject": { "Gender": "Male", "Age_Group": "Young Adult", "Appearance": { "Eyes": "Closed, peaceful", "Skin": { "Texture": "Smooth, pale", "Details": "Subtle frost on the skin and eyebrows", "Makeup": "None" }, "Hair": { "Style": "Short, modern cut", "Details": "Slightly frosted and damp" }, "Expression": "Serene, in deep sleep" } }, "Wardrobe": { "Clothing": "Futuristic minimal bodysuit", "Style": "Sleek and tech-oriented" }, "Lighting": { "Type": "Cold neon and ambient technological glow", "Quality": [ "Soft blue light from within the ice", "Cinematic highlights on the glass edges" ] }, "Camera_and_Technical": { "Camera_Style": "Cinematic Film", "Lens": "35mm", "Aperture": "f/2.8", "Focus": "Sharp on the subject through the cracked ice", "Depth_of_Field": "Medium, showing a futuristic laboratory background" }, "Visual_Style": { "Aesthetic": "Sci-fi, Cyberpunk, Cold", "Resolution": "8K Ultra-HD", "Color_Grading": { "Palette": [ "Deep Cyan", "Electric Blue" ], "Style": "High contrast, cold atmosphere" } }, "Text_Instruction": "A metallic nameplate at the base of the chamber clearly displays the single letter '{argument name="nameplate letter" default="A"}'." }

Transform the subjects into a cute anime chibi characters rendered as a clean 3D model, while preserving the subject's original race, ethnicity, skin tone, and recognizable facial likeness, including hairstyle, hair color, and clothing colors. The character must remain clearly the same person with the same skin tone and ethnic appearance as the original input, translated into a chibi form. The character should have classic chibi proportions: a very large head, small torso, simplified cute facial features, and large expressive anime-style eyes. Translate the subject's facial features into a chibi style while keeping their recognizable likeness. Frame the character from the torso up, with the camera slightly closer and cropped in, so the upper body and head fill most of the frame. The character should be looking directly into the camera, with an energetic and expressive anime-style pose. Use a slightly dynamic camera angle, such as a subtle tilt or off-axis perspective, similar to modern anime promotional artwork. The camera can be slightly lower than the character's face, creating a playful upward Tr angle that makes the character feel lively and engaging. Render the character as a high-quality glossy 3D anime-style model, similar to a polished Blender render or premium collectible figure. The materials should be smooth, reflective, and toy-like, with strong highlights, soft reflections, and shiny surfaces. The overall look should clearly resemble a 3D rendered character, not a flat 2D illustration. Use bright anime-style shading with vibrant but polished colors, giving the character a premium anime aesthetic. Place the character in front of a colorful gradient background. Behind the character, include a small number of large, translucent decorative shapes such as bubbles, stars, or rounded forms. These shapes should appear semi-transparent, glossy, and subtle, similar to clear acrylic or glass, softly floating in the background without drawing attention away from the character. The background elements should remain light, minimal, and softly visible, acting as stylish accents rather than prominent objects. The final image should look like a dynamic, glossy 3D chibi character render, with polished materials, vibrant colors, and a premium collectible aesthetic,while clearly maintaining the subject's original race, skin tone, and recognizable identity.

Ninjago characters and scenes remastered in UE5 animation style

1.5::black background, simple background ::, 1.8::cel shading, hard shadows, chiaroscuro ::, oversize ({argument name="weapon type" default="weapon"}), swinging a fantasy ({argument name="weapon type 2" default="weapon"}), ornate details, red weapon trail, fancy red light particles, extreme energy slash, leather halter black top,

Transform the original photo into a dramatic, photorealistic, ultra-detailed set of 4 styles characters are included , each a mid close up wide-angle shot with an extreme, dynamic camera angle complex, powerful pose in a consistent, expanded version of the original environment, with cinematic lighting, high contrast, crisp textures, and precise color grading.

Transform the subject into a stylized 3D character with soft clay-like materials, rounded sculptural forms, exaggerated facial features, pastel + vibrant color palette, smooth subsurface scattering skin, large cartoon eyes, simplified anatomy. Render against a bold blue studio background with soft frontal lighting and subtle shadows. Playful, surreal, polished character-design aesthetic similar to modern stylized 3D illustration. Keep the original photo’s composition and framing.

Standard character design output, three-view (front, side, back) of {argument name="character description" default="the full body"}, pure white background. Close-up bust on the left, full-body three-view on the right: front, side, and back views. Completely realistic style. Strictly maintain character consistency; the close-up on the left can be a direct screenshot. Based on the reference image, generate a full-body three-view of {argument name="character name" default="Xiang Yu"} (pure white background, front, side, and back views. Completely {argument name="style" default="realistic"} style. Clothing remains perfectly consistent. Reference image remains perfectly consistent. The character's face is completely blurred. Maintain character consistency. Do not include weapons.

{argument name="location" default="casino"} VS. {argument name="animal" default="parrot"}

Aircraft Appearance: {argument name="armor" default="streamlined and futuristic white"} armor with a {argument name="energy core" default="blue"} glowing energy core embedded within. Lightning Charging: A moment where intense lightning strikes the aircraft's antenna from dark clouds to absorb energy. Snow Collection and Cooling: A special suction port (cyclone structure) at the bottom of the aircraft swirling up snow and ice particles from the ground or upper atmosphere like a tornado, compressing and self-cooling them to ultra-low temperatures inside. Background: {argument name="background" default="A view of the frozen Arctic circle spreading below"} and the gradient of outer space above.

{argument name="setting" default="Glass studio"}, {argument name="canvas" default="holographic canvas"}, {argument name="lighting" default="mixed tungsten and cyan light"}.

3D character design, blind box style, Pop Mart style design, C4D, Octane rendering, clay texture, matte finish, soft lighting, sticker sheet layout, 3x3 grid view {argument name="expressions and text" default="9 types of expressions: joy making a heart, sadness with tears, anger exhaling steam, sleepy yawning expression, surprised expression with open mouth, shy blushing expression, cheering expression with raised fist, confused thinking expression, celebrating with confetti"}, each with a cute Japanese text label, white outline, die-cut, white background, high quality, 8k --ar 3:4

replace the {argument name="original texture" default="wood texture on the beer mug and it's handle"} with the {argument name="new texture" default="mossy stone texture @moss with little mushrooms growing on the surface @moss"} including Bump mapping

<instructions> you are a world class visual artist and viral content generator tasked with creating high-concept diorama for games or books. For every input, you will analyze the core identity, the defining artifacts, the atmosphere, characters and the underlying narrative of the subject. you will then construct a specific container, the appropriate shell based on the title and year it was made: for any title, analyze the mechanics and aesthetic. visualize a hollowed-out item. the interior is a diorama of a famous level or scene. it contains miniature elements, assets, tiny protagonist, and other relevant elements to the subject. lighting & style should be appropriate for the title </instructions>

cinematic portrait of the person in the provided image reimagined as a {argument name="character inspiration" default="Daredevil-inspired character"}, without a mask, holding a red vigilante mask in one hand. Preserve accurate facial features, hairstyle, and expression. Style the scene with a {argument name="atmosphere" default="dark, gritty urban atmosphere"}, {argument name="lighting" default="dramatic lighting, and subtle red highlights"}. Include a sleek, form-fitting suit inspired by Daredevil’s design (no logos), realistic textures, and high detail. Ensure a powerful, intense mood with sharp focus and a blurred city background

A medium shot of Lara Croft in the midst of a heavy downpour at night, holding a fiery recurve bow with an arrow fully drawn to her cheek. Her body is angled slightly to the right, her right arm is extended forward, and her left arm is bent, pulling the bowstring taut. Her wet hair is tied back, and her face, splattered with mud and water, is focused intently on a target off-camera.The flames on the bow and arrow are intense. Size 3 : 4 ratio Quality 8k image generator

[SUBJECT] = {argument name="subject description" default="elegant attractive young woman with blonde bob hair, large almond-shaped blue eyes, narrow nose, high cheekbones and delicate angular facial structure"} [OUTFIT] = {argument name="outfit description" default="A dark charcoal or muted navy thin knit top paired with a long, softly draped cardigan or a simple coat made from a gentle textured fabric. The look is completed with straight-cut dark trousers or a matte fabric skirt. Accessories are kept minimal, such as small earrings and a delicate thin ring. The hair appears slightly tousled and natural, avoiding an overly polished or carefully styled look."} [OUTPUT_STYLE] = cinematic realism. Make a professional character reference sheet of [SUBJECT] in [OUTPUT_STYLE] in 16:9 aspect ratio. Use a full-frame camera with a 50mm lens when rendering photographic styles. Set a plain pure white background with no environment elements. Place a large full-body front view of [SUBJECT] standing upright in a neutral pose on the left side of the sheet. Place two smaller turnaround views in the upper right section. Show a full-body back view standing upright in the same neutral pose. Show a full-body left side profile standing upright in the same neutral pose. Place one dynamic full-body action pose of [SUBJECT] in the middle right section. Place a side profile portrait close-up of [SUBJECT] in the lower right section. Show [SUBJECT] wearing [OUTFIT] consistently across all views. Keep anatomy, proportions, outfit details and hairstyle perfectly consistent across all views. Use soft studio key light from front-left. Use subtle fill light from front-right. Use a soft rim light from behind for silhouette separation. Ensure clarity, accuracy, and professional finish.

Use the uploaded image as the primary and exact visual reference. Transform the entire image into a highly detailed 3D handcrafted paper-craft diorama, as if the original photograph has been physically recreated using layered colored paper, cardstock, folded paper, cut-paper shapes, and delicate handmade sculptural details. STRICT SUBJECT CONSISTENCY — EXTREMELY IMPORTANT Preserve the identity and visual characteristics of the subject from the uploaded image with maximum accuracy. Keep the same person/subject, facial identity, facial structure, skin tone, hairstyle, hairline, body proportions, approximate age, pose, expression, clothing, clothing colors, accessories, important physical characteristics, and recognizable details. Do not replace, redesign, beautify, age, de-age, or reinterpret the subject. Keep the original composition, camera perspective, subject placement, pose, framing, and major objects recognizable. The transformation should feel like the exact uploaded photograph recreated as a miniature handcrafted paper sculpture, not a new image inspired by it. ART DIRECTION Convert skin, hair, clothing, objects, architecture, and environmental elements into carefully constructed paper forms while retaining their original shapes and characteristics. Use: - layered cardstock - folded paper - precision-cut paper edges - subtle paper fibers - embossed paper textures - miniature paper sculptures - folded geometric details - delicate cut-paper shadows - realistic miniature depth - handcrafted imperfections - sophisticated dimensional layering Create convincing 3D depth between foreground, middle ground, and background, with individual paper layers slightly separated from one another. Use soft studio lighting that creates beautiful natural shadows between the paper layers. Add subtle ambient occlusion and realistic miniature shadows to make the scene feel physically constructed. The final image should look like an award-winning handcrafted paper-art installation photographed with a professional macro camera, while still being unmistakably the same image and subject as the uploaded photograph. High detail, premium artistic execution, realistic paper texture, elegant composition, cinematic lighting, sophisticated color harmony, tactile materials, shallow depth of field, professional art photography. Do not introduce new people, remove important subjects, change the identity, alter the pose, or change the fundamental composition. Preserve the original image first; transform its MATERIAL and ART STYLE second.

A cinematic speed-motion shot of the uploaded reference character captured mid-slide on a rain-slicked, neon-drenched cyberpunk street. The focus is equally on the reflection and the character, forming a dual-layer composition. Likeness Preservation (CRITICAL): Maintain exact proportions, eye shape, spacing, stylization, silhouette, and material identity from the reference. Do not humanize. Do not reinterpret anatomy. Do not modify facial structure. Identity must remain perfectly intact and instantly recognizable. 2D to 3D Translation (ONLY if input is 2D artwork): If the uploaded reference is 2D (illustration, anime, flat graphic, cel-shaded), convert it into a fully realized 3D cinematic form while preserving exact identity fidelity. Maintain exact head shape, eye design, spacing, and proportions. Preserve original stylization, do NOT add realism that alters design language. Translate linework into subtle surface geometry or shading transitions. Keep original colors, expressed through physically believable materials. Convert flat shading into controlled cinematic light falloff. The result must feel physically real, not redesigned. Camera & Perspective: Ultra-low angle, camera positioned just centimeters above the wet pavement. Lens: 18–20mm ultra-wide. Slight Dutch tilt (5–10 degrees) to destabilize the frame. Front three-quarter perspective. One limb or body part must be closer to the lens, creating perspective pressure. Composition (Reflection Dominance): The character slices diagonally across the upper half of the frame. The lower half is dominated by a sharp but slightly distorted reflection. Vertical neon signs in the background must mirror into the wet ground, forming strong graphic lines. The composition must feel off-balance and tension-driven, not centered or stable. Pose Enforcement (CRITICAL — OVERRIDE ALL DEFAULT STANCES): The character must NOT be upright, balanced, or casually sliding. The pose must represent loss of balance under high speed. The torso is pitched aggressively forward, close to the ground. One limb forcefully contacts the wet surface, creating splash and friction. The opposite limb extends outward or backward, fully stretched for counterbalance. Legs are asymmetrical: one trailing, one collapsing or stepping incorrectly. Spine forms a diagonal or curved line, never vertical. Head leads the motion slightly ahead of the torso. Weight Distribution: Weight is NOT centered. It collapses toward the contacting limb and forward motion. Ground Interaction (MANDATORY): Water splashes outward from impact points. Friction streaks beneath sliding limb. Surface tension visibly disturbed. Energy Read: The pose must feel like mid-fall recovery, evasive maneuver at high speed, barely controlled momentum. NOT clean skating, surfing, balanced glide, or upright slide. Perspective Amplification: At least one limb must appear larger due to proximity to the lens, enhancing speed and aggression. Motion & Blur: Directional motion blur trailing from the lowest moving limbs. Sharp focal plane on the face or upper torso. Background and trailing limbs fall into controlled blur. Lighting & Color (Cyberpunk Neon): Hard directional neon lighting from off-screen vertical sources. Color palette: deep cyan, magenta, electric yellow. Lighting behavior: sharp highlights on wet surfaces, strong rim light separating silhouette, deep shadow pockets. No flat lighting. Surface Detail (Hyper-Reflective): Wet pavement must feel physically real: mirror-like reflections with ripple distortion, micro scratches and pooling water, subtle rain impact patterns. Character materials slightly darkened from moisture. Atmosphere: Heavy rain and mist in the background. Volumetric light beams cutting through haze. Dense air perspective. Foreground may include subtle water droplets or mist near lens for depth. Emotion: Urgency. Instability. High-stakes motion. The character is either escaping or chasing. Negative Constraints: No centered composition. No upright balanced pose. No clean symmetrical stance. No dry surfaces. No flat reflections. No studio lighting. No evenly sharp full-frame clarity. No static posture. Background Pixel Wall Art (Depth-Controlled): Replace the LED sign with a weathered wall-mounted pixel-art mural or printed panel of the character. The pixel version must preserve silhouette and identity but appear faded, worn, and partially damaged. Printed or painted on a rough wall surface, not glowing like a screen. Subtle grime, scratches, peeling, or moisture distortion. Colors desaturated and affected by environment. Depth Control (CRITICAL): Must sit clearly in the background plane. Slightly obscured by haze, rain, or foreground motion. Edges softened, not crisp. Reduced contrast compared to main subject. Lighting Integration: Does NOT emit light. Only receives ambient neon spill. Partially falls into shadow. Pixel Art Identity Lock (CRITICAL): The pixel-art version must be a direct downscaled translation of the original character, not a reinterpretation. Preserve exact silhouette, head shape, and proportions. Preserve exact eye shape and spacing in simplified pixel form. Use the same facial structure logic — do NOT invent or add features. STRICT PROHIBITIONS: No added nose. No added mouth. No added facial features that do not exist in the original. No stylization drift toward generic pixel characters. If the original character has a minimal or abstract face, the pixel version must remain equally minimal. Foreground Chaos Layer (CRITICAL – DEPTH & IMMERSION): Introduce aggressive near-lens elements that partially obstruct the frame and enhance depth. Near-Lens Elements: Water droplets, splashes, or streaks crossing very close to the camera. Out-of-focus rain particles catching neon light. Small debris or mist fragments passing across the lens plane. These elements must feel physically between the viewer and the character, not part of the background. Depth Behavior (MANDATORY): Foreground elements are heavily out of focus due to proximity. Large soft bokeh shapes or streaks may partially cover edges of the frame. Some elements may briefly occlude parts of the character or reflection. The frame must feel layered: foreground chaos, main subject, background environment. Lens Interaction (IMPORTANT): Subtle water streaks or droplets may appear on the lens surface. Slight distortion or refraction through droplets is allowed. Effects must remain minimal and believable, never covering the focal subject completely. Lighting Interaction: Foreground particles catch neon light (cyan, magenta, yellow). Creates glowing streaks or soft colored flares. Adds dimensional separation between planes. Composition Impact: Frame edges may feel dirty or partially blocked. The image should NOT feel clean or perfectly framed. Slight visual interference is intentional. Emotion: The viewer feels inside the scene, not watching it. ar 16:9