Prompts de Imagem para Game Asset

Please capture a realistic screenshot from a fictional next-generation 3D open-world {argument name="game genre" default="romance RPG"}, presented from the male protagonist’s first-person perspective. On the {argument name="location" default="beach"}, {argument name="character" default="Morrigan Aensland from Darkstalkers"} invites the protagonist to help her apply sunscreen. The overall visual style must feature high-quality cartoon-rendered 3D characters combined with Unreal Engine 5-level graphics, achieving AAA-quality visual fidelity. It should include ultra-detailed character modeling, realistic skin shading, cinematic lighting, PBR materials, high-precision clothing textures, and finely rendered classroom environments. The final image must look like an actual playable game screenshot, including a complete game user interface: minimap, quest display, character status bars, interaction prompts, dialogue subtitles, HUD elements, and more.

Goal: Create an elegant anime character design sheet for {argument name="character name" default="a handsome rabbit gentleman"}, a pale silver-haired male with tall white rabbit ears, shown as a refined fantasy noble with moon-and-clock motifs. Canvas: Wide horizontal character reference sheet, soft lavender-gray background, delicate celestial UI-frame decorations, thin white geometric lines, dangling stars, moons, clock circles, leafy botanical silhouettes, and a pastel palette of navy, ivory, lavender, silver, and muted violet. Layout: Use exactly 3 full-body turnaround views on the left: 1 side profile facing left, 1 front view, and 1 back view. On the right, include exactly 2 large portrait panels: the upper portrait shows a calm, cool expression while holding a pocket-watch chain near his face; the lower portrait shows a shy blushing expression with one hand near his neck and one rabbit ear drooping forward. Between the full-body views and portraits, include exactly 6 vertical detail close-up panels: 1 cravat and brooch at the collar, 1 ear and earring detail, 1 pocket watch and chain detail, 1 cuff embroidery detail, 1 coat hem embroidery detail, and 1 fluffy tail plus boot detail. Add exactly 1 vertical color palette strip on the far left with 6 round swatches: deep blue, off-white, lavender, charcoal black, pale pink, and white, plus small crescent icons below it. Subject details: The character is a slim, tall, elegant young man with very pale skin, long messy layered {argument name="hair color" default="silver-white"} hair, narrow lavender-gray eyes, soft eyelashes, and long white rabbit ears with pale pink inner fur. His expression is aloof, melancholic, and beautiful. He wears a formal fantasy outfit: a dark navy long tailcoat with silver piping, asymmetrical ivory shoulder cape draped over one side, high white ruffled shirt, pale lavender cravat tied with an oval gemstone brooch, charcoal vest, fitted black trousers, white gloves, black knee-high heeled boots, decorative chains, a pocket watch, clock-face ornaments, crescent and star accents, and leaf embroidery along the cuffs and lower coat panels. The back view must show the cape, split coat tails, harness-like waist straps, and a small round white fluffy rabbit tail. Visual style: Highly polished Japanese anime illustration, character sheet / concept art presentation, delicate linework, clean cel shading blended with soft painterly gradients, porcelain skin, intricate clothing ornamentation, elegant otome-game aesthetic, dreamy moonlit atmosphere, muted pastel lighting, crisp details in the close-up panels. Text content: No readable title text or labels; use decorative bars and interface-like shapes only. Constraints: Keep the image as a single cohesive character reference sheet, not a comic. Preserve the exact counts of views, portrait panels, detail panels, and color swatches. Avoid extra characters, avoid modern streetwear, avoid heavy saturated colors, and do not add watermark or logo.

Goal: Create a clean 4x4 pixel-art sprite sheet of {argument name="character name" default="a stylish street girl"} skateboarding, suitable for animating into a GIF. Canvas: Square canvas, white or transparent background, no borders, no text, no watermark. Arrange exactly 16 separate full-body sprites in an evenly spaced 4 columns by 4 rows grid, each sprite isolated with consistent scale and generous white space. Visual style: High-quality retro pixel art with crisp blocky edges, limited palette, soft cel shading, cute chibi proportions, expressive face, dynamic hair motion, and a video-game character sprite-sheet feel. Character details: A young streetwear girl with {argument name="hair color" default="long messy blonde hair"} blowing with motion, small blue eyes, peach skin, silver hoop earrings, chunky silver chain necklace, oversized dark olive bomber jacket, black cropped top, baggy black pants, and white sneakers. Keep her proportions and outfit consistent across all frames. Skateboard details: A black skateboard with a tan wooden edge, small beige wheels, and pixelated trucks. The board angle changes with the trick, but the design remains consistent. Sprite count and poses: Include exactly 16 sprites, ordered left to right, top to bottom: 1. Standing upright on the skateboard, rolling forward, hair streaming left. 2. Beginning to crouch on the board, knees bent, one hand low. 3. Deep crouch preparing for a trick, body leaning forward. 4. Very low crouch, face focused, one hand near the board. 5. Rolling with board slightly tilted upward, crouched and balanced. 6. Popping the board upward, front foot lifting, hair flying. 7. Midair trick with board angled diagonally, arms out for balance. 8. Higher midair trick, board steeply angled, tongue sticking out playfully. 9. Peak jump pose, arms wide, tongue out, board crossing diagonally beneath her. 10. Descending from the trick, board nearly level, arms extended. 11. Landing crouch, board angled slightly, focused expression. 12. Stabilizing after landing, low stance with arms out. 13. Low rolling landing with small motion marks beside the wheels. 14. Rising from crouch while rolling forward, side profile. 15. Upright cruising pose, side profile, relaxed expression. 16. Rear-view cruising pose, showing her back and flowing hair. Constraints: Keep all 16 sprites the same character and scale, preserve a tidy grid layout, avoid extra props, avoid background scenery, and make the sheet readable as an animation sequence.

Goal: Create a cinematic anime game announcement key visual for {argument name="title text" default="月蝕綺譚"}, featuring a cheerful young swordswoman in front of a dark lunar eclipse. Canvas: Wide 16:9 horizontal poster, 1200x675 composition, dark navy night-sky background with high contrast red and gold accents. Layout: Place the character on the right half, cropped from mid-thigh upward, leaning slightly forward with confident energy. Put the large vertical Japanese title on the left in metallic gold calligraphy, with a red crescent brushstroke behind it and small vertical romanization reading “LUNA OCCULTA” beside the title. Add the release line {argument name="release date text" default="9月19日 正式リリース予定"} in gold along the lower left. In the upper center-left, show one large black solar/lunar eclipse disk with a glowing crimson corona. Subject details: One anime swordswoman, teenage to young adult, bright smile, large brown eyes, fair skin, long black hair in a high ponytail flowing dramatically leftward, tied with a red ribbon whose two long tails stream in the wind. She wears a vivid pink short-sleeved kimono-style ninja/samurai top with black trim, a wide black obi belt tied with a small gold cord bow, black forearm guards, and a short dark underlayer visible at the hem. She grips one katana horizontally across her waist with both hands; the handle is black with subtle diamond wrapping and the blade/scabbard extends toward the lower right. Visible counted elements: Include exactly 1 character, 1 katana, 1 red hair ribbon with 2 trailing ribbon tails, 1 eclipse, 1 red crescent brushstroke behind the title, 1 vertical title block, 1 small vertical romanization label, and 1 release-date text line. Scatter exactly 24 glowing pink petal shapes across the scene, with the largest cluster on the right side and a few drifting near the title; add exactly 8 tiny orange ember flecks for depth. Visual style: Polished modern anime illustration, crisp linework, dramatic rim lighting, saturated pink petals, glossy black hair highlights, subtle wind motion, dark fantasy promotional poster atmosphere, clean readable typography, no watermark, no logos other than the specified text.

Goal: Create a complete 2D pixel-art RPG walking sprite sheet for a Zelda-like game character, ready to cut into animation frames. Canvas: Square white background, clean sprite-sheet presentation, evenly spaced grid with no borders, no labels, no shadows outside the sprites. Use a consistent top-down three-quarter RPG perspective. Layout: Arrange exactly 64 discrete character sprites in an 8 columns by 8 rows grid. Each row is one walking direction and each column is one animation frame. Keep identical scale, centered alignment, and consistent spacing across all cells. Directions and frame count: Include exactly 8 walking directions with 8 frames each: 1 front-facing walking toward camera, 2 front-right diagonal, 3 right side profile, 4 back-right diagonal, 5 back-facing walking away, 6 back-left diagonal, 7 left side profile, 8 front-left diagonal. The character identity, proportions, outfit, hair, face, cape, pouch, boots, and colors must remain consistent in all 64 frames. Animate legs, arms, cape swing, and body bob naturally without changing the character design. Character details: A cute young fantasy adventurer boy named {argument name="character name" default="brown-haired cape adventurer"}, chibi proportions with a large head and small body, tousled {argument name="hair color" default="warm brown"} hair, blue eyes, fair skin, determined neutral expression, teal tunic, brown leather belt with gold buckle, dark trousers, brown boots, small brown satchel pouch at the hip, and a flowing {argument name="cape color" default="brown"} cloak fastened around the shoulders. Outfit style should feel like a classic action-adventure RPG hero. Visual style: High-quality pixel art with crisp edges, hand-painted sprite detail, subtle cel shading, warm fantasy colors, readable silhouette, small-game-character scale, polished indie RPG look. Use a consistent light source and consistent pixel density across every frame. Constraints: Exactly 64 sprites total, exactly 8 rows and 8 columns, no text, no UI, no weapon, no extra characters, no background scenery, no duplicated wrong-facing limbs, no flipped-inconsistent accessories, no changes in head shape or outfit between frames, no cropping.

Create a cinematic vertical sci‑fi fashion illustration of {argument name="character name" default="JFC-01, the woman of the Gravity Lane"} walking through a futuristic megacity where architecture and gravity seem to bend to open a path for her. The main subject is a tall, elegant young woman in the lower-left foreground, full body, striding confidently toward the viewer while looking slightly up and to her left with a calm, distant expression. She has very long wind-swept {argument name="hair color" default="silver-white"} hair flowing dramatically behind her, pale skin, refined facial features, subtle makeup, and small dangling earrings. Her outfit is high-fashion gothic cyberpunk: a long black layered coat with wide sleeves, structured shoulders, black high-collar inner dress, flowing asymmetrical skirt panels, pale patterned lining visible inside the coat, slim belts and hanging metallic charms, a small glowing cyan pendant-like accessory, and polished black heeled boots. The setting is a vast vertical futuristic city of steel, glass, and concrete, with towering cylindrical skyscrapers, skybridges, floating circular platforms, and suspended transit structures disappearing into misty depth. A massive segmented metallic pedestrian lane rises and curves upward on the right side of the composition, as if gravity has shifted; it has articulated panels, railings, mechanical joints, glowing cyan details, and warm vertical light bars. The ground is a wet reflective metal walkway with panel seams, grates, rails, and embedded cyan light strips, creating strong perspective lines toward the background. Include exactly 5 small distant pedestrians: 3 silhouettes on the elevated curved bridge and 2 silhouettes on the lower walkway in the distance. Use bright overcast daylight with soft clouds, atmospheric haze, rim lighting on the hair, glossy reflections on metal, and a premium concept-art/anime-realism hybrid style with ultra-detailed materials. Color palette: black, graphite, silver, pale concrete, cyan accent lights, and warm white lamps. Camera: low-angle full-body fashion shot, 3/4 view, wide architectural depth, dynamic leading lines, sharp foreground detail and slightly hazy background. No visible title text, no logo, no watermark, no extra characters in the foreground.

添付キャラクターの顔・髪型・衣装・配色・体格を統一し、ゲームで映える4種類のドット絵モーションを、各最大4フレームで1枚のスプライトシート画像に生成して。{argument name="フレームサイズ" default="1フレームのサイズは256x256px"}。 ・{argument name="モーション1" default="走る：体を前傾させ、手足を大きく交互に動かす。"} ・{argument name="モーション2" default="ジャンプ：しゃがむ → 跳び上がる → 空中で手足を広げる → 着地。"} ・回転攻撃：正面 → 横向き → 後ろ向き → 反対の横向きと、全身を一回転。 ・倒れる：よろめく → 横に傾く → 寝転ぶ → 目を閉じて動かなくなる。 1行に1動作を横一列で配置し、全セルの大きさ、足元、中心、縮尺を揃える。背景は完全な単色とし、影、文字、枠、番号、UI、ぼかし、半透明、グラデーション、アンチエイリアスは使用しない。ループ動作は最初と最後が自然につながるようにする。

Goal: Create a 3:4 vertical cinematic visual poster of a futuristic design studio on the top floor of a Tokyo high-rise during blue hour after heavy rain, featuring a plush whale character designing a mechanical butterfly. Canvas: Vertical 3:4 composition, ultra-detailed cinematic realism, shallow depth of field, glossy reflections, warm desk lights contrasted with cool rainy blue city light. The camera looks slightly downward across a cluttered designer’s desk toward floor-to-ceiling windows. Main subject: A large cute plush {argument name="character name" default="blue whale"} mascot sits in a black office chair at the desk, wearing a dark gray hoodie with white drawstrings. It has soft fuzzy blue fur, a white belly and muzzle, small black glossy eyes, side fins, and a small rounded fin on top. The character holds a stylus and draws on a large pen-display tablet. Scene and environment: Behind the character, huge rain-covered windows show a vivid Tokyo night skyline with wet glass, bokeh neon reflections, skyscrapers, and Tokyo Tower glowing orange in the distance. Realistic raindrops streak down the glass. Add indoor plants, shelves, desk lamps, and metallic studio equipment. On the left wall, place a minimalist poster with a black circular logo and Chinese text reading 「更快・更锐利・更智能」. Desk contents: Include exactly 9 distinct desk items: 1 large pen-display tablet showing butterfly concept sketches, 1 black keyboard, 1 transparent glass mug of water, 3 Polaroid photos of the whale character, 1 open notebook, 1 black pen lying in front of the notebook, and 1 black cylindrical pen cup. The three Polaroids should show: the whale wearing sunglasses, the whale wearing a red cap, and the whale drinking from a cup. Butterfly design: Show exactly 2 prominent mechanical butterflies: one larger glowing orange-and-glass butterfly floating in front of the tablet, and one smaller transparent glass-wing butterfly shown in a floating UI card. The larger butterfly should have a metallic orange body, delicate transparent wings with mechanical vein structures, warm LED highlights, and sparkling reflections. The tablet screen should also show multiple drawn stages of the butterfly design, including pencil line sketches and colored mechanical renderings. Interface overlay: Add exactly 2 floating translucent UI bubbles on the right side. The top bubble contains a small round icon of the whale and Chinese text: 「只把蝴蝶翅膀改成透明玻璃，其他部分保持不变。」 The lower bubble contains the smaller glass-wing butterfly preview. Use rounded rectangles, subtle blue-gray glassmorphism, and soft glow. Notebook text: On the open notebook in the lower right foreground, write large handwritten Chinese text: 「想象，不止于提示词。」 and below it write “GPT-Image 2.5”. Visual style: Hyperrealistic 3D cinematic advertising poster, immaculate material rendering, wet glass, polished black tabletop, metal edges, water droplets, soft plush fur, transparent glass wings, orange neon glints, blue ambient city light, volumetric lamp glow, high contrast but clean, almost no noise. Constraints: Preserve the exact counted items and text placements, keep all text legible, do not add extra characters, avoid cartoon flatness, avoid watermark or logo overlays beyond the described wall poster and notebook text.

Using the provided reference sketch as the composition guide, turn it into a highly detailed cinematic dark-fantasy illustration of {argument name="scene subject" default="a warrior confronting a fire-breathing dragon"}. Keep the same basic layout: one warrior in the lower foreground facing one huge winged dragon above. Replace the simple line drawing with realistic epic concept art: the warrior wears battle-worn armor, a torn red cape, and holds a raised sword; the dragon is massive, horned, spiked, with wide leathery wings, clawed feet, glowing eyes, and a torrent of fire blasting from its mouth toward the battlefield. Add a dramatic environment not present in the sketch: burning ruined castle/city, collapsing towers, banners, smoke-filled storm clouds, flying embers, lava-like orange firelight, and jagged black rocks in the foreground. Style should be {argument name="visual style" default="ultra-detailed cinematic fantasy game key art"}, with intense contrast, dynamic perspective from behind the warrior, warm orange flames against dark gray smoke, no UI elements, no sketch lines, no text, no watermark.

Goal: Create a single square character reference sheet showing {argument name="character name" default="MiniMax H3"} as a chibi anime girl in 16 different dance poses, arranged like a numbered pose grid. Canvas: Square 1:1 image, off-white paper background, divided into an exact 4 by 4 grid with thin dark brown lines. Each panel is clean and uncluttered, with one full-body chibi character centered in the panel. Add small dark red panel numbers 1 through 16 in the top-left corner of each cell. Character design: The same cute chibi girl appears in all 16 panels: large head, small body, peach-blonde bob haircut with blunt bangs, one long curved ahoge strand looping above the head, purple eyes, rosy cheeks, small mischievous smile. Add a decorative dark brown flower-and-gear hair ornament on the viewer’s right side of her hair and a small circular gear clip near the bangs. Outfit: oversized {argument name="hoodie color" default="warm brown"} hoodie with long sleeves and a pale emblem printed on the chest, black choker, layered brown plaid pleated skirt with a tied plaid shirt or sash around the waist, black knee-high socks, chunky black loafers. Use consistent colors and proportions across all panels. Visual style: polished kawaii chibi illustration, clean thick brown line art, soft cel shading, warm muted brown palette, expressive anime face, subtle pink oval shadow under the feet in most panels. Add simple motion lines, sparkles, flowers, hearts, or bubbles where appropriate, but keep the background blank. Layout and exact 16 panel contents: 1. Wide-legged energetic stance, one fist raised forward, determined expression. 2. Loose zombie-like sway, both arms drooping outward, sleepy half-lidded face. 3. One knee lifted, one arm raised overhead, small motion lines around the body. 4. Body tilted dramatically sideways with one leg crossed behind, arms bent above and across the head. 5. Graceful dance step with eyes closed, arms extended softly, two small flower doodles. 6. Low squat pose, hands held near cheeks like paws, confused expression with one question mark. 7. Back-facing spin pose, head turned slightly, one arm extended forward, skirt flaring. 8. One-leg cute pose, both arms overhead forming a rounded shape, winking, small star doodles. 9. Deep side lunge with one hand on the floor and one arm arched high, sly face. 10. One knee lifted, eyes closed, both hands forming small horns or a crown shape above the head, tiny accent marks. 11. Confident wide stance, both hands pointing outward like finger guns, sparkles nearby. 12. Sleepy backward lean, eyes closed, arms hanging loosely, bubbles and motion arcs. 13. Shy over-the-shoulder pose, one hand near mouth, hip turned, small heart doodle. 14. Crawling or low all-fours pose, one leg lifted slightly, playful sideways gaze, motion marks. 15. Joyful midair jump with both arms spread wide, smiling with closed eyes, flower doodles and motion lines. 16. Sassy finishing pose, one hand making a V sign near one eye, the other hand on hip, one eye winking, sparkles around her. Constraints: Use exactly 16 panels and exactly one character per panel. Keep the grid numbering visible and sequential from 1 to 16. Maintain the same outfit, hairstyle, hair accessories, and color palette in every pose. No extra text besides the panel numbers and optional simple symbols like the question mark.

Using the provided reference image as the rough silhouette and color guide, transform the simple blue dolphin sketch into a cinematic dark-fantasy underwater boss encounter. Keep the same front-facing rounded dolphin/whale-like body, central dorsal fin, side fins, blue upper body, and pale lower mouth area, but render it as a massive realistic sea monster with cracked glowing electric-blue markings, bioluminescent blue eyes, wet rough skin, barnacles, grime, and ornate ancient-gold markings running down the forehead. Scene: Place the creature in a vast abyssal ruined city with dramatic blue shafts of light from above, floating debris, bubbles, schools of tiny fish, broken stone arches, pillars, statues, and a ruined shipwreck silhouette on the left. Add a tiny explorer/diver figure near the lower left to emphasize the monster's enormous scale. Make the composition widescreen and centered, with the monster looming directly toward the viewer. Game UI addition: Add exactly 1 boss health bar at the bottom center: a long red bar in an ornate dark-metal fantasy frame, labeled in Chinese with {argument name="boss name" default="深渊歌者"}. Do not add any other UI panels. Style: Ultra-detailed AAA game key art, dark souls-like fantasy atmosphere, underwater volumetric lighting, high contrast, moody teal-blue palette, cinematic realism, dramatic scale, sharp focus on the creature's face. Customizable details: creature glow color {argument name="glow color" default="electric blue"}, environment theme {argument name="environment theme" default="abyssal ruined city"}, mood {argument name="mood" default="ominous and epic"}, aspect ratio {argument name="aspect ratio" default="16:9 widescreen"}.

Mine pulses red beneath a {argument name="shell color" default="black shell"}. {argument name="model id" default="JFC-01"}｜{argument name="name" default="VOID FANG"}

为该角色创建一个战斗动作精灵图。采用 {argument name="pixel size" default="128px"} 的简约像素艺术风格，布局为 {argument name="grid layout" default="4x4=16 帧"}，并使用透明背景。包含 {argument name="motions" default="4 个待机 / 4 个拳击 / 4 个踢腿 / 4 个受击"} 动作。

Goal: Create a clean 3D chibi fighting animation sprite sheet for a cute mascot character, suitable for making a looping GIF. Canvas: Square 1:1 canvas, about 1200 x 1200 px, with a transparent-background preview shown as a light gray checkerboard. Arrange the sprites in an evenly spaced 4 columns by 4 rows grid, for exactly 16 separate animation frames. Leave generous padding around each character and keep all frames at a consistent scale. Character: A toy-like glossy 3D chibi mascot with a peach-colored round onion/droplet-shaped head and a small pointed top, tiny smiling mouth, rosy cheeks, oversized black sunglasses, and the black number {argument name="forehead number" default="29"} printed on the upper forehead. The body is small and heroic, wearing a bright {argument name="suit color" default="blue"} long-sleeve bodysuit with a white belt stripe, a red scarf/capelet at the neck, a small white circuit-like emblem on the chest, red gloves or rounded fists, and shiny red boots. Use soft studio lighting, smooth plastic/vinyl toy material, rounded proportions, and a cheerful confident expression. Sprite actions: Depict exactly 16 frames of a simple battle motion sequence, all facing mostly forward with slight 3/4 turns. Count and show these frames in order from left to right, top to bottom: 1 neutral guard stance with both fists raised; 2 wider guard stance; 3 right-arm straight punch beginning; 4 right-arm punch fully extended; 5 reset guard stance; 6 guard stance leaning slightly; 7 long straight punch across the body; 8 return to guard; 9 left knee lift preparation; 10 higher knee lift; 11 side kick fully extended to the right; 12 second extended side kick frame; 13 knee lift recovery; 14 neutral guard stance; 15 neutral guard stance variation; 16 final neutral guard stance. Visual style: High-quality cute 3D render, Nintendo-like mascot toy aesthetic, crisp edges, saturated primary colors, soft shadows, consistent camera angle, consistent character size, no motion blur, no outlines except natural 3D shading. Constraints: No text labels other than the forehead number. Do not add weapons, backgrounds, UI elements, frame borders, watermarks, or extra characters. Keep the checkerboard transparency preview visible behind every frame.

Using REFERENCE_0 as the realistic landscape/detail base and REFERENCE_1 as the city-layout and sketch/worldbuilding reference, transform the scene into {argument name="style request" default="人工衛星から撮影したGoogleマップのような写真。"} Render it as a true vertical top-down satellite image, like a Google Maps capture, not an oblique fantasy illustration. Preserve the invented medieval city arrangement while making it look geographically real. Keep exactly 5 major layout elements recognizable: 1) the walled oval/rounded city footprint, 2) the large castle district on the upper-left hill, 3) the central cathedral and radial plaza, 4) the lake in the upper-right/background area, and 5) the river or moat curving around the lower edge with a bridge/gate approach. Style: photorealistic satellite imagery with natural terrain textures, muted earth colors, tiny roof grids, streets, vegetation, water, fields, and realistic atmospheric clarity. Remove the close foreground tower viewpoint from REFERENCE_0 and eliminate painterly/fantasy perspective. The result should feel like an authentic overhead map photo of {argument name="city type" default="a Central European medieval walled city"}, with believable scale and urban density.

Using REFERENCE_0 as a rough childlike layout sketch, transform it into a highly detailed, polished fantasy anime landscape illustration. Interpret the simple gray drawing as a large Japanese castle on the left foreground, the blue outline as surrounding water or moat, the green mountain lines as lush forested mountain ranges in the background, the green jagged shape as islands or shoreline across a bright lake, the brown grid shapes as fields and town blocks, and the cyan lines as a broad blue lake or river. Preserve the overall spatial arrangement from the sketch, but replace all crude marker strokes with an expansive aerial panorama. Style: vibrant high-resolution Japanese anime background art, Studio Ghibli-like atmosphere, intricate architectural detail, crisp sunlight, rich greens and blues, soft mist, sparkling water, painterly but clean. Scene additions: create a fortified castle town with many traditional tiled-roof buildings, stone walls, bridges, canals, docks, small boats, sailboats on the lake, tiny roads and courtyards, dense forests, scattered islands, distant layered mountains, white summer clouds, and patches of low morning mist. Use a wide elevated viewpoint looking down over the castle town and lake. Constraints: no visible sketch lines, no text, no modern objects, no people as the focus; make the final image look like a complete professional fantasy background derived from the reference composition.

Goal: Create a cinematic character design sheet labeled in Spanish for {argument name="character name" default="FICHA DE PERSONAJE"}, showing an elderly wandering Japanese hermit musician and his instrument accessory. Canvas: Wide horizontal 16:9 concept-art presentation on warm off-white paper, thin gray divider lines, museum catalog / film production design style, realistic photographic rendering with soft studio lighting and subtle shadows. Layout: Split the sheet into two main columns. The left two-thirds is the character sheet, titled “FICHA DE PERSONAJE” in large spaced serif capitals at the top. The right third is the accessory sheet, titled “ACCESORIO: KOTO” in the same serif style. Use clean rectangular panels, fine borders, and centered small uppercase captions beneath each view. Character section: Show exactly 5 character views: 3 full-body turnarounds and 2 portrait insets. The 3 full-body views are, from left to right, front labeled “FRENTE,” back labeled “ESPALDA,” and side profile labeled “PERFIL.” The 2 portrait insets are stacked vertically to the right of the full bodies: a tight face close-up labeled “PRIMER PLANO,” and a chest-up three-quarter view labeled “VISTA 3/4.” The character is an elderly man with very long tangled {argument name="hair color" default="gray-white hair"}, a massive flowing white beard, dark sunglasses, weathered tan skin, and a calm stoic expression. He wears a wide conical woven straw hat, a shaggy straw rain cloak made of long dry fibers, layered ragged brown robes, a wrapped sash belt, loose trousers, and worn brown boots. The costume should feel ancient, dusty, handmade, and textured, with frayed hems and natural earth tones. Accessory section: Show exactly 5 views of the instrument accessory: 3 full instrument views across the top labeled “FRENTE,” “PERFIL,” and “ESPALDA,” plus 2 close-up detail panels along the bottom labeled “DETALLE CABEZA” and “DETALLE CUERPO.” The accessory is a rustic vertical string instrument inspired by a koto or shamisen, made from aged dark wood and pale stretched hide, with visible scratches, stains, pegs, strings, and worn varnish. The front view shows the pale hide-covered body, the profile view shows the thin side depth, and the back view shows a dark reddish-brown wooden body. Visual style: Hyperrealistic fantasy costume reference, high-detail fabric and straw fibers, muted browns, sepia tones, ivory background, elegant editorial spacing, no modern props except the sunglasses. Use Spanish captions exactly as specified, with refined serif typography and thin horizontal rules at the top and bottom. Constraints: Keep the sheet clean and symmetrical, include exactly 10 labeled visual panels/views total, avoid extra text, avoid watermarks, avoid logos, avoid cartoon styling.

Create two separate ultra-detailed cinematic fantasy portraits from one prompt, both using the exact same deep blue cosmic galaxy theme and visual style. IMAGE 1 — WOMAN: Create a beautiful clearly adult woman with long flowing black hair, luminous smooth skin, glamorous blue-and-silver celestial eye makeup, glossy lips, and sparkling star-like details across her face. Add elegant crescent moon and star jewelry, subtle crystal accents, and glowing cosmic particles around her. Her expression is confident, mysterious, and attractive. Surround her with deep blue nebula clouds, glowing stars, large planets, moons, cosmic dust, and electric-blue light. The galaxy energy should naturally blend around her face, hair, shoulder, and clothing. IMAGE 2 — MAN: Create a handsome clearly adult man in the exact same blue cosmic theme. He has thick slightly messy black hair, a neat dark beard, strong facial features, intense glowing blue eyes, and a confident mysterious expression. Add subtle galaxy-like glowing patterns and tiny stars across one side of his face. His hand is near his chin in a stylish fashion pose with an elegant dark metallic ring. Surround him with the same deep blue nebula clouds, glowing planets, moons, stars, cosmic dust, and electric-blue energy. IMPORTANT: Generate the woman and man as two separate images, not together in one frame. Keep the same lighting, same blue galaxy color palette, same premium fantasy fashion style, same level of detail, and matching visual identity so both images look like a coordinated pair. Ultra-realistic, premium cinematic lighting, high contrast, glossy luxury fantasy look, sharp focus, detailed skin and hair, magical blue glow, no text, no watermark. Vertical portrait composition, 9:16 for both images.

基于我上传的图片，设计一套 3D 表情包 1:1 透明贴纸页，包含 9 个各不相同的贴纸，按 3X3 网格排列每个贴纸呈现不同的表情、姿势或反应。贴纸之间留出较宽且完全透明的间隔。无背景、阴影或重叠元素，融入{argument name="表情符号" default="🚀🎉🥳🤟"}

turn {argument name="target" default="it"} into a {argument name="style" default="future building"}

Goal: Create a dark-background comparison board showing character asset sheets for three office-dressed people, comparing two image-generation systems side by side. Canvas: 16:9 landscape presentation image, approximately 2048×1152, with a deep navy-black background, clean white typography, and six large white image panels arranged in a 3-row by 2-column grid. Header text: At the top left, place the large Chinese title {argument name="headline text" default="3组 女生人物资产 · 同提示词对比"}. Under it, add a smaller subtitle line: {argument name="comparison subtitle" default="左：历史 GPT Image 2 右：ChatGPT Images 2.5 网页"}. Layout: Use exactly 6 rectangular white panels with thin spacing: left column represents the older model, right column represents the newer model. There are exactly 3 character rows: Clara, Julian, and Evelyn. Each row has a small Chinese row label above the left panel: “纯文字角色资产 - Clara”, “纯文字角色资产 - Julian”, and “纯文字角色资产 - Evelyn”. Each of the 6 panels contains exactly 4 character depictions on a white studio background: 1 large cropped head-and-shoulders portrait on the left, plus 3 smaller full-body turnaround views on the right: front view, side profile view, and back view. Total visible character depictions: exactly 24. Row 1 subject details: Clara, a young fair-skinned woman with long wavy dark brown hair, soft natural makeup, neutral serious expression, wearing a cream ribbed turtleneck, brown cropped blazer, high-waisted wide-leg cream trousers, a black belt, and low heels. In each Clara panel show 4 views: close portrait, full-body front, full-body side, full-body back. Row 2 subject details: Julian, a young slim fair-skinned man with light brown/blond swept hair, rectangular glasses, calm serious expression, wearing an off-white linen suit, white open-collar shirt, narrow trousers, brown belt, and tan loafers. In each Julian panel show 4 views: close portrait, full-body front, full-body side, full-body back. Row 3 subject details: Evelyn, a middle-aged woman with medium tan skin, dark hair pulled back into a low bun, composed neutral expression, wearing a black business suit, dark gray blouse, small gold necklace, small earrings, black trousers, and black flats. In each Evelyn panel show 4 views: close portrait, full-body front, full-body side, full-body back. Visual style: Realistic photography-like character asset sheets, clean studio lighting, white seamless backgrounds inside each panel, consistent professional wardrobe styling, neutral expressions, no decorative graphics except the dark board and labels. The left and right columns should be visibly similar but not identical, as if comparing outputs from two systems. Footer text: At the bottom left, add two small Chinese notes: {argument name="footer note one" default="历史成品 2048×1152 / 网页新图 1672×941 · 仅排版缩放，无修图、无超分。"} and {argument name="footer note two" default="提示词正文相同，两页端仅补充16:9比例。"}. Constraints: Keep the exact 3-row by 2-column comparison layout, exactly 3 named characters, exactly 6 panels, exactly 4 depictions per panel, with no watermark, no extra logos, and no additional characters.

Using the provided reference image as the exact room base, generate a contact-sheet collage showing {argument name="number of views" default="10"} different camera viewpoints of the same self-defense classroom, as if the camera is rotating around the room. Preserve the room identity, furniture, wall poster text, training mats, punching bag, shelves, window, doors, shrine shelf, lighting, colors, and anime background style. Do not add people or new objects. Layout: Arrange the views in a vertical collage with {argument name="collage layout" default="2 columns and 5 rows"}. Each panel should be a wide interior shot, with consistent perspective and lighting, showing different angles of the same space rather than different rooms. Camera variation: Rotate the viewpoint around the room in small increments, including views facing the window, doors, poster wall, equipment shelves, punching bag, and mat area. Keep the geometry believable and maintain continuity between panels. Style constraints: Match the clean illustrated anime interior look of the reference, with soft sunlight through the window, fluorescent ceiling lights, polished blue-and-cream mats, warm wooden wall paneling, and no text overlays outside the poster already in the room.

Create a cinematic ultra-realistic aerial wide shot of a {argument name="castle type" default="grand medieval Gothic stone castle"} standing alone on a rocky hilltop in a vast natural highland landscape. The castle has weathered gray masonry, crenellated curtain walls, arched gatehouse, a stone bridge and winding dirt road leading to the entrance, red vertical banners, narrow lancet windows, steep dark slate roofs, and an inner courtyard. Include exactly 10 prominent roofed vertical structures: 5 large round curtain-wall towers with conical slate roofs around the perimeter, 4 tall corner turrets on the central keep, and 1 smaller rear spire. The central keep should rise highest, with cathedral-like Gothic windows and a dramatic fortified silhouette. Surround it with rolling hills, scattered rocks, sparse grasses, small streams, distant mountains, and a wide cloudy sky. Lighting is {argument name="time of day" default="golden hour near sunset"}, with warm low sunlight from the left breaking through dramatic clouds, cool blue-gray shadows, and atmospheric haze over the distant valleys. Use a high-end fantasy film production look, photorealistic materials, detailed stone texture, realistic terrain, volumetric clouds, natural color grading, 16:9 landscape composition, viewed from a slightly elevated drone perspective. No people, no modern objects, no text, no watermark.

Create a cinematic anime-style sci-fi bedroom scene at night, wide 16:9 composition, richly detailed and atmospheric. A futuristic teenage/young adult girl with very long {argument name="hair color" default="aqua blue"} twin-tail hair stands slightly right of center, wearing a white high-tech lab coat or expedition coat with dark cybernetic panels, blue glowing accents, white stockings, and white ankle boots. She holds a small translucent holographic tablet in one hand and looks toward a huge floating hologram on the left. The room is dark navy and illuminated by cool blue neon edge lights, rain-speckled reflections, and warm bedside lantern light. On the left side, show one enormous rectangular holographic projection with clipped futuristic corners and a bright electric-blue outline, rising from a circular floor projector. Inside the hologram is a dramatic fantasy mountain landscape: jagged black peaks, rocky foreground, distant mountain ranges, a brilliant {argument name="sky gradient" default="sunrise-to-starry-night gradient"} with orange dawn on the horizon blending upward into violet, indigo, and a dense star field/Milky Way. In front of the holographic landscape, include exactly one small mechanical bird companion flying, with white and pale-blue feathers, tiny goggles or visor, a small harness pack, and glowing blue crystalline tail feathers. On the right side of the room, place a bed under large floor-to-ceiling windows; through the windows show a rainy futuristic city skyline at night with countless blue lights, vertical rain streaks, and reflections on glass. Include exactly one small wall-mounted holographic frame showing snowy mountains. Foreground and room details should include a glossy reflective floor, a circular rug, a desk with blue-lit edges and a transparent map-like display, one office chair, one bedside table with one warm lantern, one potted plant near the window, one potted plant blurred in the lower left foreground, one glowing star-shaped lamp, and one small bird plush or figurine near the foreground. Visual style: ultra-detailed anime key visual, cyberpunk but cozy, deep blues with magenta-orange dawn contrast, volumetric glow, crisp linework, soft bloom, realistic reflections, high depth of field with slight foreground blur, no visible text, no watermark.