AI 提示词库

the classic Japanese Bosozoku ({argument name="gender" default="M"}) in the style of a 3D model asset

the Villain fairy performs the “you think because you say nothing You’re strong?”

a human VS. Yokai Haxtusyaku-sama in the style of an FPS game

soft, round face fuller cheeks small chin slightly larger, expressive eyes (but still identity-consistent) no beard, no sharp jawline, no adult features Expression should be innocent, warm, and slightly playful, with a gentle smile and direct eye contact. Body proportions should be cute and childlike (small, slightly chubby body, slightly larger head). Pose: relaxed standing with hands behind the back, with a subtle natural tilt in head and shoulders to avoid stiffness. Hair should match the reference but appear soft, slightly voluminous, and naturally styled, not overly sharp or artificial. Skin should be soft and stylized, with subtle subsurface scattering (SSS) for a warm glow, matte finish (no plastic shine), and gentle natural blush on cheeks. The character wears a half sleeves cotton sweater with a puzzle pattern, where: colors are soft but lively and slightly vibrant not oversaturated and not washed out The fabric shows a realistic knit texture and soft folds Lighting should be soft and cinematic: key light from upper-left gentle fill light subtle rim light on hair Background should be a rich blue gradient, brighter behind the subject and darker toward the edges, with smooth depth (not flat). Output should be: 1:1 aspect ratio mid-length framing (head to waist) high-detail, clean 3D render film-quality finish (not toy-like, not overly realistic)

Create a completely new ultra realistic Instagram vertical 4:5 image for Gemini 3 Pro Nano Banana of the same man with identical facial features inside the Angry Birds world during a dramatic escape moment. He jumps off a collapsing wooden platform as multiple TNT crates detonate behind him, red sparks and debris flying. Red is mid air flying beside him, Bomb is igniting, Chuck sprints ahead, Stella flutters above, and pigs are scattering everywhere in panic. Outfit: fitted white T-shirt, tactical brown cargo pants, and impact-ready white sneakers with red-yellow accents, all detailed and textured. Environment: broken glass, exploding stone blocks, rolling green hills blurred behind. Lighting: intense warm explosion glow from one side combined with cool sky light from the other, giving epic cinematic contrast. Feathers, dust, debris, and motion are ultra detailed. Shot on a dynamic slightly low 28 mm lens for powerful action depth, with sharp focus on the man and Red.

Full Armor Mecha Girl FAMG-002 Belthiera 1/7 scale figure

Create a 1/7 scale commercialized figurine of the person in the picture, in a realistic style, in a cozy artisan workshop environment. The figurine is placed on a wooden workbench. The figurine has a round transparent acrylic base, with no text on the base. The content on the computer screen is the Zbrush modeling process of this figurine. Next to it is a BANDAI-style toy packaging box printed with the original artwork. The packaging features two-dimensional flat illustrations.

A photorealistic hand holding a transparent zip bag containing a realistic collectible card. The card has exactly the same layout as shown in the attached screenshot. The header image at the top of the card is displayed as-is, without any transparency effects. Use true macro lens perspective (90mm–120mm macro lens look) with very shallow depth of field. Only a thin slice of the object should be in sharp focus while the rest fades into smooth blur (bokeh). The image should emphasize fine surface details, micro textures, reflections, scratches, fibers, or material structure. Lighting should be directional and dramatic, coming from one side to reveal texture and shape. Use deep shadows and controlled highlights so the object appears sculptural and cinematic.

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

A detailed technical blueprint of a high-performance AI GPU cluster placed on a polished brass drafting table, with a photorealistic miniature AI server system self-assembling from it — multiple GPU accelerator units (sleek black and metallic modules with neon green accents) rising from the dimension lines, high-speed interconnect bridges threading through the tolerance annotations, and dense compute nodes forming from the grid layout. Stacks of GPU cards slide into server chassis above the parts list, each unit locking in with precision. NVLink-style connectors and high-bandwidth interconnects assemble seamlessly between GPUs, forming a powerful parallel compute network. Rack-mounted AI servers emerge vertically, with layered compute blades building upward in perfect alignment. A liquid cooling system forms from exploded-diagram callouts — transparent cooling pipes with glowing coolant flowing through them, cold plates attaching to GPUs, and radiators assembling with high-performance fans. Heat dissipation fins and airflow channels dynamically shape around the system. A tiny engineer in futuristic protective gear stands on a GPU module inspecting circuits with a holographic diagnostic interface, while another miniature technician connects high-speed data cables into a switch unit. Fiber optic lines glow faintly, representing active data transfer. Functional details illuminate — GPU core lights pulsing softly, status LEDs blinking in synchronized patterns, data streams visualized as glowing lines moving between nodes, and monitoring panels activating during assembly. Signature tools of the trade — precision screwdriver, thermal paste applicator, anti-static tools, fiber connectors, and a digital diagnostic tablet — rest across the blueprint’s title block, partially integrated into the scene. All elements grow organically from the blueprint like a 3D mechanical diorama — circuit traces rising from printed schematics, GPU modules emerging from drawn outlines, cables threading through pencil grid lines. Seamless transformation from 2D blueprint into a fully operational AI infrastructure. LIGHTING: Soft studio lighting combined with strong neon green and cool blue glows from GPUs and data pathways. Subtle reflections from the brass surface and volumetric light enhancing depth. CAMERA & LENS: Shot on a full-frame camera, 35mm lens. Slight low-angle perspective to emphasize scale and power. Cinematic depth of field with focus on central GPU cluster. COMPOSITION: Vertical 2:3 format. Central stacked GPU cluster rising upward with symmetrical balance. Clean negative space around edges with layered depth. STYLE & MOOD: Futuristic, cinematic, high-end AI infrastructure aesthetic inspired by NVIDIA design language. Powerful, clean, and cutting-edge. DETAILS: Ultra-detailed textures — matte black metal, glowing accents, micro circuitry, cooling liquid reflections, cable braiding, LED indicators. 8K resolution, HDR,

Render_Target = ( Open_Book_3D_Pop_Up_Diorama * 2.0 ) + ( Inferred_3D_Environment_[COMIC_SERIES] * 1.5 ) + ( 3D_Vinyl_Toy_[HEROES] + 3D_Vinyl_Toy_[VILLAINS] * 1.8 ) + ( Translucent_Plastic_Energy_FX * 1.5 ) + ( Floating_3D_Text_"{argument name="sfx text" default="SFX_TEXT"}" * 1.5 ) + ( Floating_Yellow_Title_Box_"{argument name="comic series" default="COMIC_SERIES"} | {argument name="year" default="YEAR"}" * 1.2 ) + ( Vintage_Flat_Comic_Book_On_Wooden_Desk * 1.0 ) - ( 2D_Flat_Characters / 2.0 ) - ( Human_Realism / 2.0 ) - ( Life_Size_Scale )

Convert to hyper-realistic 3D CGI collectible figurine render. Physically-based rendering, octane render quality. Preserve the original character design, pose, and outfit exactly. Transform all surfaces into real-world materials: fabric with visible weave and drape, metal with wear, scratches and oxidation, synthetic matte skin. Pure white studio background, clean seamless white backdrop, soft diffused lighting with subtle rim light. No cel shading, no toon rendering. High-end statue/collectible photography aesthetic. Ultra detailed, 8K. Fix and reconstruct all hands and fingers with correct anatomy: natural finger count, proper joint articulation, realistic proportions, no fused or melted digits. Remove all 2D artifacts, compression glitches, and Midjourney inconsistencies. Ensure full anatomical coherence across the entire figure: symmetrical features, clean silhouette, no floating elements, no distorted limbs, no duplicated body parts. Hyper-detailed hair simulation: individual strand rendering, realistic hair clumping, natural flow and gravity, visible scalp at roots, micro flyaways, SSS translucency on hair tips. Every surface pushed to maximum realism: pore-level skin texture, fabric fiber micro-detail, specular highlights on every material, depth in shadows

ultra-detailed 3D tiny anime-style girl named Gugu, short fluffy hair, soft round cheeks, big sparkling eyes, wearing a pastel-colored oversized hoodie with little animal ears, tiny socks, small ribbon around neck, chibi-style proportions with round head, small body, expressive arms and legs, adorable and highly expressive, capable of cute gestures and exaggerated reactions, cinematic shallow depth of field, 8K UHD, soft warm sunlight, cozy pastel tones, whimsical playroom / nursery background, sequence of actions: Frame 1: sitting cross-legged on fluffy pastel rug, holding small stuffed bunny, shy expression Frame 2: standing slightly, tilting head, tiny hand raised in gentle wave, playful expression Frame 3: clapping tiny hands excitedly, eyes sparkling, happy squeak Frame 4: leaning forward, reaching toward small floating butterfly, cheeks rosy, curious Frame 5: jumping slightly, tiny feet off ground, arms raised in delight Frame 6: (optional placeholder for continuity) Frame 7: tilting head with one hand on cheek, playful and curious expression Frame 8: rolling slightly on rug, legs kicking gently, giggling with sparkling tears of laughter Frame 9: sitting back up, looking up with hopeful puppy-like eyes, floating sparkles Frame 10: giving a tiny wink and finger heart gesture, full adorable charm

{ "prompt": "A high-quality 3D rendered character of a young, friendly barista with big expressive eyes and styled brown hair. He is wearing a green apron over a plaid flannel shirt. The setting is a cozy coffee shop with wooden counters, espresso machines, and shelves of coffee beans in the background. The image features soft studio lighting, a clay render texture with cute and appealing shape language, reminiscent of Pixar or Disney animation styles, in 4k resolution." }

create a cartoon character design sheet from this image a man who performs confidence louder than he feels it. Chest forward, jaw up but something in the eyes gives him away. He's used to being watched, terrified of being seen

A cute 3D chibi-style cartoon sticker set featuring the same character in various emotions and poses (use the uploaded face as reference). Shiny, expressive eyes; soft round face; slightly oversized head; small body proportions. Wearing a leather jacket {argument name="jacket color" default="Blue"} over a white top. Each pose shows a different expression: surprised, sad, confused, happy, thinking, winking, peace sign, shrugging, playing guitar. 3D render inspired by Pixar/Disney, smooth plastic-like texture, soft lighting, pastel beige background. Clean white sticker outline around each character, minimal aesthetic, highly detailed, ultra cute, emoji-like expressions, high resolution, studio quality.

Full Armor Mecha Girl FAMG-001 Aurelith ⠀ 1/7 scale plastic model ⠀ The head is inspired by a "Jingasa" (samurai hat). It was created using a derived prompt from 'Warrior Mecha Girl' → 'Knight Mecha Girl'.

A high-quality 3D render of the designer toy from [Reference Image 1]. Requirement: The character must retain its exact original outfit . The Mask: Tightly fit a custom "Bat Cowl" ([Reference Image 2]) over the head. The Cowl: Must match the exact color, material, and design, with size adjusted as needed to fit the reference character’s head. Scaling: Tailored, bespoke fit with a shortened chin guard precisely following the character's jawline. Cowl size is adjusted to match the reference character exactly. The cowl fits seamlessly, with no gap between the head and the chin guard. Ears: Only the sharp bat ears are visible; hide original ears, headwears, horn, accessories, hat, helmet entirely. The Cutout: The cowl features a cutout area; through this opening, the underlying part of the reference character must be visible exactly as it is, with no additions, removals, or alterations. Eyes: Use the exact glowing eye effect from the reference cowl image. Constraint: No nose or eyes should be rendered on the cowl or the character's face. 8k, studio lighting, Background must match the reference character’s background exactly. Lighting Lighting should match the reference character’s original light behavior, and the cowl must follow and respond to the same lighting conditions. Character Likeness Integrity (CRITICAL) Maintain the exact eye shape, spacing, stylization, patterns, silhouette, and original color palette from the reference. Do not humanize. Do not alter anatomy. Do not modify facial structure. Identity must remain instantly recognizable. If the character wears a balaclava, mask, helmet, or covered face, don't invent facial anatomy. No added nose. No added mouth. No visible skin where the reference does not show it.

use the character turnaround format from [img1] to create {argument name="character name" default="[character name]"} in the same style prompt: show them in a scene together, ghibli style

use the character turnaround format from [img1] to create {argument name="character name" default="Nezha"} in the same style

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

use the character turnaround format from [img1] to create {argument name="character description" default="[character name / image]"} in the same style

a chicken in a T-Rex costume's on the way of homecoming in the style of an 8-bits #11

a sea iguana that is inspired by a LMGT3-class car