AI 提示词库

A cinematic, full-body shot of a battle-worn knight in detailed steel plate armor walking through a tall, golden grass field. The knight is draped in heavily tattered and shredded bright red robes that flow in the wind, with a longsword in hand and a secondary blade strapped to his back. A flock of black crows circles in the hazy, overcast sky above. Soft, diffused daylight creates a moody atmosphere with visible dust motes and particles. Shot on a Sony A7R IV with an 85mm f/1.4 lens, low angle, shallow depth of field focusing on the intricate textures of the weathered armor and frayed fabric. Hyper-realistic, 8k resolution, raw photo, gritty dark fantasy aesthetic, 9 : 16.

{ "format": "Single cinematic frame for GPT Image", "technical_specs": { "camera": "Low angle shot, shallow depth of field", "lighting": "Night scene, neon blue accent lights, wet surfaces", "quality": "Ultra-detailed, 4K, photorealistic CGI" }, "main_subject": { "type": "Large humanoid robot mecha, 15 feet tall", "construction": "Built from {argument name="mecha parts" default="black broadcast van parts"} - visible vehicle chassis panels, wheels converted to leg joints, satellite dish on chest", "details": [ "Matte black metal body with blue LED strips", "Two massive vinyl record discs (like DJ turntable platters) rotating slowly on shoulders - black vinyl with glowing blue label centers", "{argument name="brand logo" default="VTX logo"} glowing blue on chest center", "Mechanical legs with exposed pistons", "Head section has two bright blue headlight eyes", "Arms have DJ mixer faders and knobs as decorative panel details" ], "pose": "Standing upright, right foot planted on cracked pavement, left leg slightly bent" }, "person_on_mecha": { "position": "Standing on top of the mecha's head section", "identity": "{argument name="subject identity" default="Latin American man, early 40s, completely shaved head"}", "clothing": "Dark navy jacket, black pants, boots", "pose": "Standing confidently, one hand gripping a handle, other hand raised in fist", "expression": "Calm, confident, looking forward" }, "environment": { "location": "Wet asphalt road at night", "background": "Urban warehouses with neon signs, industrial buildings", "weather": "Heavy rain, puddles on ground reflecting blue lights", "ground": "Cracked pavement around mecha's foot, visible impact damage" }, "lighting_and_color": { "primary": "Cool blue neon glow from mecha LEDs and spinning vinyl centers", "secondary": "Warm orange sparks from mechanical joints", "atmosphere": "Dark moody night, rain, wet reflections", "key_colors": "Matte black, electric blue, dark grey asphalt" }, "action_frozen": "Mid-step stomp - right foot creating cracks in pavement, shoulder vinyl discs slowly rotating with blue light trails, sparks visible from leg joints, rain droplets frozen in air around the scene", "avoid": [ "Weapons of any kind", "Cannons or guns", "Fire or flames", "Organic dinosaur features", "Green colors", "Forest or trees", "Multiple people", "Handheld weapons", "Excessive flying debris" ] }

A hyper-realistic, 8k, high-fidelity close-up shot captured with a macro lens, showcasing a giant human hand holding a keyring against an extremely blurred background of a rugged outdoor forest range. The hand holds a rugged, olive drab paracord survival strap with a small metal dog tag reading "{argument name="dog tag text" default="DUET AI : One Shot"}". Attached is a miniature character lying in a prone firing position behind a highly detailed, tiny sniper rifle with a large scope. The character has a large head, [uploaded face as reference], and is wearing a full miniature ghillie suit (camouflage) that looks incredibly textured with tiny leaves and burlap. The miniature rifle has realistic metallic and polymer textures, bipod legs, and a tiny lens flare on the scope. Natural, dappled forest sunlight highlights the camouflage textures and the metal of the rifle.

Subject Description: A cinematic female warrior inspired by {argument name="inspiration" default="Mulan"}, strong, noble, and restrained beauty, calm yet determined expression Outfit: Elegant red ancient Chinese warrior costume inspired by traditional Han-style armor and flowing fabrics, minimal ornamentation, realistic textile texture, battle-worn yet refined Detail/Prop: Holding a long steel sword firmly in hand, simple and practical design, subtle reflections on the blade, heroic stance Setting: Quiet forest at early morning, soft mist among tall trees, muted natural colors, cinematic depth Style & Mood: High-end cinematic fantasy, realistic lighting, dramatic shadows, film still, epic yet poetic atmosphere, 35mm film look, cinematic color grading

A cartoonish ({argument name="animal name" default="Animal Name"}) in pixelated image format

Ultra-detailed cinematic macro render of an adorable miniature fuzzy bee character flying mid-air, holding a glossy translucent honey droplet container with tiny curved black legs, the bee has soft golden-yellow fur with black stripes, oversized shiny black glass-like eyes, small delicate antennae, and semi-transparent wings frozen mid-flap, expressive and charming personality, stylized Pixar-quality character realism vertical 9:16 composition, subject centered slightly above middle, optimized for mobile viewing, strong vertical depth and motion direction dynamic motion blur background with streaked green foliage and soft natural colors to emphasize speed and flight, vertical motion streaks, shallow depth of field, subject perfectly sharp while background heavily blurred, creamy bokeh, strong subject isolation warm sunlight illuminating the bee’s fur, soft rim lighting around the edges, subsurface scattering in wings, honey droplet glowing amber with realistic translucency, refraction, and viscosity, physically accurate materials, global illumination macro photography look, 100mm macro lens, f/1.8 aperture, extreme detail in individual fur fibers, cinematic portrait orientation, premium animated film quality, octane render, unreal engine quality, nano banana pro style, ultra clean, high realism, 8k resolution, aspect ratio 9:16

Dark gothic alley at night, wet brick wall and rain-soaked pavement reflecting a dim street lamp. Heavy fog drifts slowly through the alley. A pale elegant vampire woman in a long black coat and dark red dress leans against the wall, motionless and mysterious. Cinematic horror lighting, dramatic shadows, shallow depth of field, ultra-realistic, 35mm film look, film grain, volumetric fog. The camera begins at her black leather boots and performs a slow cinematic vertical dolly shot upward, moving smoothly from her feet → legs → waist → shoulders → lips → eyes. Suspense builds as the camera rises. When the camera reaches her face, she slowly tilts her head and gives a cold villain smile. Her long sharp vampire fangs slide into view, fresh blood dripping slowly from the tips. Her eyes glow subtly in the darkness. She whispers softly: “Welcome to the night…” Immediately after, she lets out a quiet sinister villain laugh as the fog thickens and the lighting darkens. The scene begins to slowly fade to black, while the camera continues pushing forward into an extreme close-up, zooming closer and closer until the camera enters her mouth, ending in darkness. Style keywords: cinematic horror, gothic vampire, slow camera movement, dramatic lighting, suspenseful, photorealistic, moody atmosphere, shallow depth of field, film grain, volumetric fog.

Change the character in the reference image to a deformed character illustration. Have the character take various poses within a single image. The background is white.

An image explaining the internal structure of a robot. Analyze the internal structure of the machine. Be sure to correctly display the skeleton and frame. Always keep the surface and maintain the background.

subject: The original character from the single reference illustration, represented as a highly detailed collectible PVC action figure. The character’s design, proportions, facial features, hairstyle, outfit, and colors are preserved exactly. composition: A single 3:4 frame divided into multiple clearly defined rectangular panels. Each panel presents the same action figure posed differently. Panels are separated by thin, clean borders in a neutral tone. Each figure is centered within its own panel. action: Dynamic action poses made possible by articulated action-figure construction. Poses emphasize balance, tension, and expressive movement, clearly reading as intentionally posed action figures rather than static statues. location: Neutral studio background with a seamless white to light gray gradient. Each panel maintains consistent studio conditions. style: Photorealistic collectible PVC action figure. Realistic articulation-friendly sculpting suitable for dynamic posing. camera_lighting: Professional studio lighting consistent across all panels. Controlled highlights, sharp focus, shallow depth of field. Soft shadows beneath each figure within its panel. colors: Exact color reproduction from the original illustration, unchanged. edit_instructions: Transform this illustration into a photorealistic PVC anime figure. Keep the original character’s design, action pose, and colors exactly the same. Render it as a collectible figurine made of PVC plastic, with realistic painted surface and detailed shading. Apply glossy highlights on areas such as the hair and clothing. Use a matte finish on the skin. Add subtle seam lines as seen in real manufactured figures. Include transparent plastic figure stands supporting dynamic action poses. Do not include opaque bases or decorative display platforms. extras: High-resolution, catalog-quality product image.

based on the attached image, generate a Side by side photo of a close up face, and half body character design (both views are different view of an identical design) of a woman with long, flowing dark hair and a gentle, warm smile. Her face is adorned with delicate freckles, and her striking blue almond-shaped eyes exude kindness. She wears an ornate, deep-blue hooded cloak embellished with intricate gold patterns resembling swirling waves or dragons, evoking a sense of fantasy or ancient nobility. The fabric appears rich and textured, fastened with an elaborate golden clasp at the shoulder. Underneath, glimpses of armored plating suggest a warrior or royal status. The overall aesthetic blends elegance with strength, set against a soft, neutral background that highlights her serene yet powerful presence. close up face on the left, half body on the right, on a flat plain white background, photography with edge lighting for depth, 16:9, 2K

{argument name="subject one" default="king salmon"} VS. {argument name="subject two" default="grizzly"}

Convert the subject in this image into a stylized 3D caricature portrait with {argument name="head shape" default="an elongated rectangular head"}, {argument name="facial feature" default="oversized nose"}, and pristine studio lighting. Use a sculpted, high-end 3D CGI character treatment with strong identity preservation, while amplifying the facial geometry into a bold editorial caricature without changing the subject’s existing hair. CHARACTER: Build the subject as a tall, narrow caricature bust with a stretched rectangular skull, compressed cheek planes, and a dominant forward-projecting nose that anchors the face. Preserve the subject’s recognizable hair volume by translating it into clean, sculpted strands. Keep the clothing simplified, modern, and rendered as a refined secondary form that supports the face. FACE & ANATOMY: Use a severe angular facial construction with planar transitions, heavy brows, deep-set eyes, and a long tapered lower face. Keep the expression serious and slightly weary, with a rigid jaw rhythm and exaggerated vertical proportions. The body should remain secondary and understated, with the head as the primary silhouette. ENVIRONMENT: Change the background into a {argument name="background style" default="minimal 'dark gradient' studio"} that isolates the portrait and enhances its sculptural clarity. Keep the scene clean, controlled, and distraction-free, with no props or narrative clutter. Add subtle depth falloff so the character reads as a premium character-study render. RENDER PIPELINE: Use stylized 3D CGI with a polished sculpt-first workflow, crisp edge definition, and clean subdivision surfaces. Apply controlled toon-leaning shading with smooth form transitions, disciplined specular response, and no photoreal skin microdetail. Finish with a premium character-render presentation, sharp silhouette readability, and zero photographic camera artifacts. COLOR & LIGHT: Use a restrained palette of 'deep charcoal', 'cool blue' shadows, 'warm peach' skin tones, and 'soft amber' rim accents. Light the face with perfect studio key lighting, gentle fill control, and a balanced rim that carves the silhouette cleanly. Preserve high contrast in the facial planes while keeping the exposure elegant and even. MATERIALS & TEXTURES: Render skin as clean, stylized character material with smooth surface behavior and subtle form shading, not realistic pores. Hair should read as sculpted clumped strands with controlled gloss, and the beard (if presented) should appear as carved fiber-like grooves with crisp separation. Clothing and background surfaces must stay matte and simplified, supporting the caricature focus. DETAILS: Emphasize the rectangular head geometry through faceted forehead planes, sharp temple breaks, and a strong nose bridge structure. Add refined studio-finish highlights along the cheek planes, brow ridge, and hair contours to heighten the premium 3D look. Keep all detail language native to stylized character sculpture, with no comic halftone, no painterly brushwork, and no l

A wooden tiki statue with a carved, smiling face and intricate details is depicted against a tropical background. The tiki is wearing a vibrant orange and pink Hawaiian shirt adorned with white hibiscus flowers. In its right hand, it holds a red cocktail garnished with a slice of orange, a cherry, and a small umbrella. The tiki's left hand is raised in a thumbs-up gesture. The overall style is illustrative and cartoonish, with a textured appearance suggesting wood grain.

create a screenshot of the overworld for this game in the same area, with one pokemon following the player, fit the vibe of the reference

A cinematic evolution sequence of the 3d toy character shown as multiple identical instances progressing from primitive to fully realized form across a single frame. 🔒 LIKENESS INTEGRITY (ABSOLUTE PRIORITY) All instances must preserve exactly: • proportions • eye shape, spacing, stylization • silhouette • material identity No redesign. No added features. No anatomy change. Only pose progression is allowed. 🧠 EVOLUTION STRUCTURE (MANDATORY) The character appears repeated in a left-to-right progression of 6–8 stages: • earliest stage: crouched, compressed, almost animalistic or inactive • mid stages: gradual spine lift, awareness, balance emerging • final stage: fully upright, confident forward motion Each stage must feel like a natural transformation, not separate poses. Motion must read as a continuous evolution. 🎥 CAMERA & PERSPECTIVE Low-angle cinematic shot, slightly below mid-body height of the final character Shot with a 28–35mm lens to create subtle perspective compression and depth Camera positioned closer to the final evolved character, making it dominant in frame The earliest forms recede into the background along a diagonal progression ⚖️ COMPOSITION (CRITICAL) Diagonal layout from back-left (primitive) → front-right (evolved) Foreground dominated by the final form, partially cropped for tension Earlier stages progressively smaller and more compressed into depth No centered symmetry 🎯 DEPTH OF FIELD (MANDATORY) Primary focal plane locked on the most evolved character Mid stages slightly softer Earliest stages fall into progressive blur No full-frame sharpness 💡 LIGHTING Strong directional light from the side or rear Rim light increases progressively across evolution stages Primitive forms sit more in shadow Final form is clearly defined with sculptural light separation 🌫 ATMOSPHERE Subtle haze or volumetric light to enhance depth layering Light falloff increases toward background Optional faint dust or particles to create dimensional space 🎨 COLOR CONTROL Primitive stages slightly desaturated and darker Color richness increases toward the final evolved form Controlled contrast, no oversaturation 🧱 SURFACE & MATERIAL Maintain exact original material identity Enhance micro-detail only on the focal character No texture reinterpretation 🔥 EMOTION Inevitable transformation From instinct → awareness → dominance The final character feels like the destination of a journey 🚫 NEGATIVE CONSTRAINTS No random poses No redesign No symmetry No flat lighting No full-body sharpness everywhere No equal importance across all stages Aspect Ratio: ar 16:9

Cinematic 3D composition centered on a {argument name="object" default="[OBJECT]"}, frozen at the instant it releases something far bigger than itself. From within it, an entire {argument name="world style" default="[WORLD STYLE / THEME]"} reality unfolds, spilling outward into sweeping environments, towering forms, and dynamic motion that suggests this world was hidden there all along. The object doesn’t just contain the world — it becomes part of it, with its shapes transforming into terrain, architecture, and symbolic landmarks. Small figures, machines, or creatures navigate the scene, adding life, scale, and narrative. The moment balances between dream and physics, where visual logic holds even as reality stretches. The scene is charged with [ATMOSPHERE: glow, fog, particles, smoke, energy], amplifying the sense of rupture and emergence. A subtle hint of the real world remains visible around the edges, anchoring the spectacle in realism. Hyper-detailed textures, dramatic lighting, cinematic depth, ultra-realistic, 8K, concept art finish.

A cinematic, dutch angle, full body shot of a {argument name="subject" default="young woman"} as in <<<image_1>>> cooly walking in profile, using both hands to put on an off-white, mobile suit pilot helmet with metallic black visor. She wears a tight, detailed, {argument name="outfit" default="futuristic white mobile suit pilot suit"} with subtle signs of wear and tear, including scuffs and grime textures. The lighting is {argument name="lighting" default="soft, cool, and diffused"}, creating a melancholic and introspective mood with a palette of pale blues, stark whites, and pops of muted grey. The background is a blurred, minimalist sci-fi interior with sterile, light-toned architecture. Shot on a 35mm lens with a shallow depth of field, focusing sharply on her face and body, high-quality digital photography, hyper-realistic, intricate details, soft cinematic highlights, ethereal atmosphere. Loose messy hair style. Visor should have no reflection of the photographer. Lazily gazing at the camera.

A {argument name="subject" default="burlap voodoo doll"} with a {argument name="heart detail" default="red heart stitched in the center"}. The doll has black cross-shaped eyes and a stitched mouth. Several {argument name="pins" default="pins are stuck into the doll: one pink pin in its left leg, one blue pin in its right leg, and one red pin in its right arm"}. The doll is covered in small, dash-like stitches, giving it a textured appearance.

Ninjago characters and scenes remastered in UE5 animation style

A grid of twelve stylized cat faces, arranged in four rows and three columns, fills the frame. Each cat face is distinct, featuring a unique color palette and decorative elements. The cats have large, round eyes, small noses, and prominent whiskers. Some wear floral accessories, bows, or other playful adornments on their heads. The overall style is whimsical and childlike, with bold outlines and flat colors, reminiscent of children's book illustrations or stickers. The background is a plain white, making the colorful cat faces stand out.

Generate a surface normal map from the input artwork image. Output one RGB image where each pixel encodes the surface normal direction in standard tangent-space format: • R = X direction • G = Y direction • B = Z direction Requirements: • Maintain the same resolution and aspect ratio as the input image. • Normal directions must follow the local geometry implied by brush strokes, shading, and contours. • Do NOT add new artistic elements or repaint the scene. • Only infer plausible micro-geometry and surface orientation. • Ensure smooth, consistent normal transitions without noise. Generate a depth map from the input artwork image. Output a single grayscale depth map where: • White = near to the viewer • Black = far from the viewer Requirements: • Maintain the same resolution and aspect ratio as the input image. • Depth must be smooth, continuous, and physically plausible. • Infer only geometric depth that could reasonably exist in the original artwork. • Do NOT add new objects or details. • Do NOT stylize, repaint, or reinterpret the scene. • Avoid texture noise; focus solely on depth structure.

create a version of this character made entirely of sliced vegetables and fruits vegetables and fruits: should match the uploaded character’s colors as closely as possible, without changing their natural look slices: slightly misaligned, with visible separation between layers structure: a small bite taken out of the top of the head, forming a clean cut surface ambience: kitchen setting, on a cutting board with scattered vegetables and a knife nearby camera: slightly top-down angle effect: tilt-shift 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 Character Compatibility Rules: If the uploaded character is 2D, convert it into a believable realistic 3D render while preserving the original design, proportions, colors, and visual identity Do not modify facial structure Do not add a mouth or nose if the uploaded character does not have them 👟 FOOTWEAR & ACCESSORY MATERIAL OVERRIDE (CRITICAL FIX) All parts of the character, including footwear and clothing, must follow the same fruit and vegetable slice construction. • shoes must be made entirely of stacked fruit and vegetable slices • preserve the exact shoe shape, proportions, and design • recreate panels, sole, and details using layered slices Material examples for shoes: • sole → dense stacked potato or root vegetable slices • upper panels → fruit/vegetable slices arranged to match original color blocking • edges and seams → visible slice layering and separation 📷⚠️ 0px; letter-spacing: normal; orphans: 2; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px;"> IMPORTANT: No original materials should remain (no fabric, rubber, or leather). Everything must be converted into fruit/vegetable slice construction while keeping the original design recognizable. ar 1:1

A full-body 3D cartoon girl character in a Pixar/Disney-style render, standing confidently against a solid bright {argument name="background color" default="yellow"} background. She has big expressive brown eyes, a cute smiling face, and light brown curly hair tied in a messy high bun, with white round goggles resting on her head. She is wearing an oversized knitted sweater in cream and mustard yellow stripes, with the name “{argument name="name on sweater" default="NOOR"}” clearly knitted into the fabric across the chest (woven yarn texture, not printed). Loose knitted beige cargo pants with side pockets, white chunky sneakers with subtle yellow accents. Soft studio lighting, smooth textures, high detail yarn knit realism, warm color palette, playful pose with arms slightly spread, ultra-high quality, 4K, sharp focus, clean background, character centered.