Model:
Tags:
Tìm thấy 16,474 prompts
Trang 1 / 687
东方武侠浮世绘人物画风格提示词模板
ChatGPT

Mẫu từ gợi ý phong cách tranh vẽ nhân vật Ukiyo-e của võ thuật phương đông

[Character] Fill in the name of the martial arts character [Core Action] Fill in representative martial arts, postures, or combat actions [Visual Anchor] Fill in signature elements such as weapons, long hair, Dharmachakra, snakes, silk threads, etc. [Main Colors] Fill in 2–4 main colors [Inscription Text] Fill in the character's name or a four-character short title Create a 9:16 vertical Oriental martial arts Ukiyo-e character painting. Reshape the character image based on [Character], without referring to any film or television actor's face or specific film or television styling. The character is performing the [Core Action], using exaggerated perspective, strong torsion, and large dynamic cropping, so that the body, robes, hair, and [Visual Anchor] together form a clear large shape and strong momentum. The character occupies about 75%–85% of the frame, and parts can naturally go out of frame, so that the character and action can still be identified at a glance even in a thumbnail. The overall style adopts the visual language of traditional Musha-e and woodblock color printing: clear black woodcut outlines of varying thickness, flat large color blocks, exaggerated human proportions, and ancient woodblock-style spatial compression. Use [Main Colors] as the main color scheme; colors are saturated, stable, and complete, avoiding modern gradients, CG highlights, and game concept art textures. The composition includes at least one strong visual anchor and a clear hard axis or large curve, such as a weapon, arm, hair bundle, robe, silk thread, Dharmachakra, or snake body. All elements must have clear directions and connection relationships, and are not randomly stacked. Keep the background low density, mainly with warm ivory rice-white paper surface, adding only a small amount of rocks, withered wood, distant mountains, clouds, or environmental hints, with large areas of white space, making the character the absolute subject. Add traditional vertical title labels, small inscriptions, and 1–2 vermilion seals at the edges of the image. The [Inscription Text] is naturally integrated into the border of the ancient painting, without using modern large titles, numbering, or UI decorations. The overall temperament should have martial arts, grotesque, strong action, and ancient woodblock tension, while maintaining character recognition. Each character forms a different visual motif based on their own martial arts, weapons, hairstyles, clothing, and actions, but the entire set must maintain the same paper, lines, color sets, inscriptions, and woodblock texture. Avoid: film and television actor faces, modern ancient-costume photography, Xianxia mobile game character art, anime faces, 3D rendering, photographic texture, standard standing poses, modern metal highlights, neon effects, magic light effects, complex backgrounds, severe aging yellow spots, random noise, modern Typography, watermarks, numbering.

No tags
初秋日系街头时尚咖啡馆外日本女性全景人像
ChatGPT

Chân dung toàn cảnh phụ nữ nhật bản bên ngoài quán cà phê thời trang đường phố nhật bản vào đầu thu

Use the uploaded reference image as the STRICT PRIMARY AND HIGHEST-PRIORITY visual reference for the clearly ADULT Japanese woman’s FACE, HAIRSTYLE, BODY PROPORTIONS, OUTFIT, POSE, CAMERA ANGLE, FRAMING, café exterior and lighting. If anything conflicts, ALWAYS follow the reference image. Create an ultra-photorealistic LIVE-ACTION iPhone 17 Pro vertical 2:3 Japanese street-fashion snapshot of the same clearly ADULT Japanese woman in her 20s standing outside a stylish modern glass-front café on a bright early-autumn day. SUBJECT: Preserve her recognizable facial identity. Long dark chocolate-brown hair tied into a loose LOW-TO-MID ponytail around shoulder level, with soft waves, airy wispy see-through bangs and delicate face-framing strands. Fair realistic skin, natural brown eyes, very light pink-beige makeup, softly rosy cheeks and muted glossy pink lips. Gentle relaxed expression with direct eye contact. OUTFIT — COORDINATE 18: Cream / ivory loose-knit sweater with bold horizontal black stripes, relaxed slightly wide neckline naturally exposing ONE shoulder and a thin white inner strap. Long oversized sleeves extending slightly over the hands. High-waisted charcoal-gray pleated mini skirt with crisp structured pleats. White ribbed crew socks and glossy black chunky platform loafers. Small structured black shoulder bag. POSE: Standing upright casually beside the café’s outdoor wooden counter, NOT leaning forward. One hip rests very lightly near the counter. Legs naturally crossed at the ankles. One hand loosely holds a clear plastic cup of iced coffee with a black straw at chest height; the other arm hangs naturally beside her. Relaxed shoulders and natural body balance. CAMERA: 24–28mm equivalent, NOT a selfie, eye-to-waist-level camera position with subtle natural perspective. Full-body framing from head to shoes, both feet completely visible. Subject fills approximately 85–90% of the vertical frame. Fashion-focused composition showing the entire outfit clearly. BACKGROUND: Minimalist urban café exterior with exposed gray concrete, large black-framed glass windows, narrow wooden outdoor counter and tall stool. Small green plants and olive tree beside the entrance. Black café menu board near the sidewalk. Subtle street reflections and softly blurred city details behind her. Clean Japanese/Korean-inspired café aesthetic. LIGHTING: Bright soft early-autumn daylight with warm sunlight filtering through nearby trees, realistic dappled shadows on the pavement, gentle highlights on her hair and skin. Apple Smart HDR, natural dynamic range, subtle background bokeh. Ultra-photorealistic skin texture, individual hair strands, realistic knit fibers, skirt pleats and leather reflections. Authentic Japanese SNS street-fashion photography. Avoid forward-leaning pose, high ponytail, hair worn fully down, oversized head, extreme body proportions, distorted hands, extra fingers, fused limbs, warped legs, cropped shoes, excessive beauty filtering, plastic skin, anime appearance or studio lighting.

No tags
东亚女性近距离情感人像摄影
ChatGPT

Cận cảnh bức ảnh chân dung đầy cảm xúc của phụ nữ đông á

9:16 tight chest-up portrait of an adult East Asian woman with a small oval face, moist-looking almond-shaped brown eyes staring directly into the lens as if looking into her lover’s eyes, a straight nose, slightly parted glossy nude-pink lips, fair skin with flushed cheeks, and long black hair falling messily around her face with many loose strands across her cheeks. An atmosphere of restrained desire, as if only a single breath remains between them. A coaxing, pleading mood, her breath almost reaching the frame. She wears a wide-neck off-white cotton T-shirt. She lifts her face very close to the camera, her eyelids lowered, her moist eyes looking at him as if asking him not to lower the camera. Her lips are glossy and damp; she has just lightly licked the corner of her lips before parting them again. Her cheeks and collarbones are softly flushed. She leans her upper body straight toward the lens, with her left shoulder slightly lower and her collarbone pushed closer to the camera. Completely unposed. The camera is pushed in extremely close, using a 50mm lens, approximately 28 cm from her face. The subject fills around 93% of the frame, tightly cropped from her hair and cheeks down to her collarbones, with her face positioned slightly left of center. The gray background is completely blurred and indistinct. Neutral lighting, with highlights catching the moisture on her lips and at the corners of her eyes. The approximate color distribution is 55% skin tones, 21% off-white, 16% black hair, and 8% background. Low saturation, with the bridge of her nose appearing slightly soft due to the extremely close camera distance. Photorealistic snapshot. Do not make negative assumptions.

No tags
俏皮吐舌头复古机车盔女性自拍
ChatGPT

Cô gái tinh nghịch đội mũ bảo hiểm xe máy kiểu cổ điển chụp ảnh tự sướng với tư thế thè lưỡi

Subject: A playful selfie of a young woman with a medium-short, auburn hair, looking directly at the camera with her tongue playfully sticking out. Attire & Accessories: She is wearing a matte black vintage-style open-face motorcycle helmet with exposed rivets and a chinstrap. Large, black-frame sunglasses conceal her eyes. She is wearing a light-wash distressed denim jacket with distinct black spray-paint or airbrush-style lettering (partially visible, resembling "H - I - T"). Underneath the jacket, a black and white crewneck shirt is visible. Setting & Background: The photo is taken from a low angle, looking slightly up. The background is a bright, clear blue sky with thin, wispy white clouds. Overhead power lines and wooden utility poles crisscross the frame. There is a red and white flag and some low-rise building rooftops visible in the distance on the right, suggesting an outdoor, street-level location. Lighting & Style: The image is a natural, daylight photograph with soft, direct sunlight. The perspective is a close-up, first-person selfie shot. The mood is casual and spontaneous. Key Action/Pose: Tongue sticking out (playful expression). Use the uploaded photo as the facial identity reference for an adult woman. Preserve his recognizable facial features, natural skin tone, facial proportions, and overall appearance. make the aspect ratio 3:4

No tags
健身房杠上向前翻转姿势摄影
ChatGPT

Chụp ảnh tư thế lật người về phía trước trên thanh tập gym

TITLE: Gym Forward Rotation Bar Pose IDENTITY LOCK: None. STYLE: Ultra-realistic photorealism. Authentic handheld iPhone 16 Pro photography. Casual Instagram-style gym photo. Natural HDR with minimal retouching. Authentic skin texture. SUBJECT: Beautiful Japanese woman in her early 20s. Long dark brown hair tied back, with loose strands falling forward. Natural makeup. Healthy fair skin. BODY: Pronounced feminine hourglass figure. Naturally very full bust. Natural feminine curves. Realistic anatomy. OUTFIT: Fitted white ribbed spaghetti-strap thin tank top with a deep scoop neckline. Very short gray-and-white striped drawstring gym shorts. Beige workout gloves. Barefoot. SCENE / ENVIRONMENT: Modern indoor gym with weight-training equipment and mirrors. A sturdy fixed horizontal metal exercise bar. POSE / EXPRESSION: She is beginning a natural forward rotation around the bar, using her lower abdomen as the pivot point. Her lower abdomen rests firmly on top of the bar and acts as the pivot point. The bar is positioned very low, clearly below her navel and directly at the top edge of her shorts. Her entire navel remains clearly visible above the bar. The lower edge of the bar visually overlaps the shorts waistband, with no bare skin visible between the bar and shorts. Her upper body folds deeply forward and downward over the bar. Her shoulders, chest, head, and loose hair naturally hang forward with gravity. Her hips remain close to the bar and her legs descend naturally below. Both hands grip the bar near her hips for balance, with naturally bent elbows. CAMERA: Vertical 3:4 composition. Close front three-quarter view. Natural handheld smartphone framing. Frame mainly from her head to around the knees or lower legs. Feet do not need to be visible. The navel, bar, and shorts waistband are clearly visible. LIGHTING: Bright neutral gym lighting. Natural realistic shadows. DETAILS: Natural body weight and compression against the bar. Candid realistic gym atmosphere. NEGATIVE / CONSTRAINTS: No CGI. No illustration. No anime. No plastic skin. No text or watermark. No malformed anatomy or extra limbs. No distorted arms or hands. No upright or rigid torso. No gap between her body and the bar. No bar at or above the navel.

No tags
韩国酷飒女孩精品酒店CCD直闪私房人像
ChatGPT

Khách sạn boutique cô gái mát mẻ hàn quốc ccd flash trực tiếp chân dung phòng riêng

9:16 vertical composition, ultra-photorealistic live-action photography, Korean Instagram hot girl / Korean bad girl private portrait, set in a boutique hotel bedroom at night. iPhone snapshot + vintage CCD direct-flash aesthetic, like a casual photo taken straight from a private camera roll. A clearly adult Korean woman, age 23–27, with a refined small oval face and naturally cool fair skin, preserving realistic fine skin texture, visible pores, and subtle variations in skin tone. Long black hair worn loose and slightly messy, with fine stray strands falling naturally along both sides of her face. Elongated cat-like eyes with subtly lifted outer corners, cool pink nude makeup, a faint blush, and glossy nude-pink lips. Her overall vibe is lazy, aloof, slightly rebellious, with a Korean bad-girl edge. She is always wearing thin-frame oval black glasses, slightly lowered on the bridge of her nose. She raises her eyes and looks directly at the camera over the top edge of the lenses, with a cool, sleepy, nonchalant gaze and naturally relaxed, slightly parted lips. She wears a fitted black spaghetti-strap tank top with dark charcoal-black low-rise denim shorts, paired with a delicate silver necklace. The outfit is simple and fitted, revealing a slender neck and shoulders, naturally defined collarbones, a visible waistline, and long, evenly proportioned legs. Her body proportions are mature, healthy, natural, and realistic. She sits on the edge of a messy white hotel bed, with her legs naturally apart and extending toward the foreground. Her upper body leans noticeably forward toward the camera, shoulders slightly drawn inward, arms hanging naturally downward, with both hands positioned near the space between her knees. Her head is tilted slightly as she looks upward toward the camera, creating an intimate candid perspective as if the photographer were standing directly in front of her and casually shooting from a slightly elevated angle. Close-range high-angle shot, 35mm-equivalent perspective. Her knees and legs occupy the foreground while her face remains the visual center of the frame. Use natural perspective distortion, with closer elements appearing larger and distant elements smaller, to create realistic depth. Avoid a polished studio pose; preserve slight asymmetry, relaxed posture, and believable body weight and tension. The background features a slightly messy white hotel bed with naturally scattered white pillows and wrinkled sheets, dark gray walls, and a dark wooden headboard. The room is dimly lit, with no other people present. Vintage CCD compact-camera direct flash. Harsh frontal on-camera flash illuminates her face, shoulders, and legs, producing realistic flash reflections on her cool fair skin with slightly blown highlights, while the background remains noticeably underexposed. Cool gray, desaturated color palette, subtle digital noise, fine grain, soft focus, slight defocus, and faint handheld motion blur, preserving the imperfect texture of a cheap vintage digital camera. Korean Instagram hot girl, Y2K digital camera, private bedroom photobook, candid snapshot, intimate camera-roll aesthetic, cool desaturated tones, direct flash, realistic skin texture, messy black hair, oval thin-frame glasses, high-angle close shot, leaning forward on bed, photorealistic, imperfect handheld framing, subtle film grain, authentic early-2000s digital-camera feeling. No text, no watermark, no UI elements, no extra people, no duplicated limbs, no extra fingers, no malformed hands, no distorted anatomy, no exaggerated body proportions, no plastic skin, no anime, no illustration.

No tags
经典超跑复古汽车工程图海报
ChatGPT

Poster vẽ kỹ thuật xe cổ điển siêu xe cổ điển

Create a collectible vintage automotive engineering poster featuring four legendary classic supercars: Ferrari F40 (1989), Lamborghini Countach 5000 QV (1985), Porsche 959 (1986), and McLaren F1 (1994). Use an aged cream paper background with subtle fibers, faded ink, pencil-and-ink technical illustrations and authentic 1980s–90s factory-document aesthetics. Give each car a prominent realistic 3/4 hero view, surrounded by front, side, rear and top technical drawings with dimensions. Include concise specification panels explaining each car’s engine, horsepower, torque, drivetrain, suspension, brakes, aerodynamics, weight, acceleration and top speed. Add detailed mechanical illustrations of the engines, chassis and drivetrain, plus small studies of headlights, wheels, brakes, intakes, spoilers and interiors. Use numbered callouts, arrows, measurement lines, engineering annotations and period-style typography. Make the information feel like an authentic factory engineering sheet rather than a modern infographic. Highly detailed, realistic automotive rendering blended with hand-drawn technical artwork, sophisticated archival print texture, 16:9 landscape, ultra-high resolution.

No tags
都市科技感现代温室高光CCD生活人像
ChatGPT

Chân dung cuộc sống ccd nhà kính hiện đại công nghệ cao có độ bóng cao

Photography Style: Daylight clear high-key CCD lifestyle style Portrait Direction: Urban tech lifestyle portrait Scene Direction: Modern smart agriculture greenhouse outer corridor / transparent glass structure / white frame / neat tomato and lettuce planting area Clothing Direction: Bright grape purple slim-fit U-neck knit top + creamy white ultra-short shorts Temperament Tags: Fresh, intellectual, bright, natural, light tech feel Facial Direction: Clear intellectual natural face Body Direction: Light and slender Line Emphasis: Medium to strong Lens Direction: Half-body to thigh Posture and Action: Standing by the greenhouse glass door, one hand holding a small fruit/vegetable basket, the other hand lightly touching the door frame, front-facing with a slight angle looking at the camera Lighting Atmosphere: Daytime bright natural light + glass and white frames forming clear diffuse reflection Filter Effect: Bright clear purple-green CCD colors + clean white highlights + clear midtones + light grain Aspect Ratio: 9:16 Supplementary Requirements: No rural filters, no Mori style; greenhouse structure must be modern, rational, and neat, the character still maintains a fashionable urban lifestyle feel

No tags
原生艺术上下双拼构图插画
ChatGPT

Nghệ thuật bản địa minh họa thành phần đôi trên và dưới

Create a vertical illustration with a "top-bottom split composition," where the vertical layout of the canvas is divided into top and bottom areas with a strict 1:1 ratio. It should be a single complete work, not a collage of two independent images. Top Half: Use the user-uploaded original image as the primary source, automatically identifying the main characters, cats, dogs, or other common pets in the original image and presenting them as the sole core subject. Focus on extracting identifiable information of the subject itself, including the person's face shape, facial features, hairstyle, hair color, skin tone, age, clothing, accessories, posture, and temperament, or the pet's fur color, patterns, body shape, ear shape, eye characteristics, and expression. The top half should center on "original subject display," maintaining a visual state that is as realistic, natural, and clear as possible. Appropriate cropping and composition optimization can be done according to the needs of the split screen, but do not change the identity of the subject. If the original image contains buildings, indoor spaces, street scenes, or other complex environmental elements, these contents should only be treated as auxiliary background weakening and not as key extraction objects; there is no need to specifically preserve the architectural style. The overall requirement for the top half is that the subject is clear, complete, and not cut off, the image is clean, the visual center is stable, and the main task is to clearly show "who the original subject uploaded by the user is." Bottom Half: Perform a stylized translation of the same subject from the top half in the bottom half. It must still be the same person or animal, maintaining core recognizability and not becoming an unrelated new character. Create a complete illustration in the visual language of "Raw Art / Art Brut." Core stylistic features: unrefined academic lines, rough forms, direct symbols, and irregular color blocks. General principle: allow for exaggeration, distortion, and irregular brushstrokes, creating visual impact with strong lines, ink marks, and emotional tension. The composition uses a single clear subject or a clear scene, the visual center is stable, the subject is complete and not cut off, and the background is moderately simplified while retaining a sense of breathability; lines, color blocks, light and shadow, materials, and paper texture must serve the same style and not mix in unrelated painting styles. The image should be natural, have a handmade feel and recognizable stylistic features, avoiding common AI issues like excessive smoothness, meaningless piles of detail, and random decoration. Unless the theme specifically requires it, do not generate text, logos, watermarks, borders, or UI, and do not make multi-image collages. Overall Supplementary Requirements: The top and bottom parts must clearly correspond to the same subject, forming a top-bottom contrast relationship of "original subject / stylized subject." The bottom half should reflect a raw, direct, and unrefined sense of crude art, but must not lose the recognizability of the subject. Maintain a handmade, simple, primitive, and impactful visual language overall, and do not make it into a polished commercial illustration. Do not generate additional explanatory text, titles, logos, watermarks, UI, or borders.

No tags
街拍照片转杂志感时尚插画对比图
ChatGPT

So sánh các bức ảnh đường phố được chuyển thể thành hình minh họa thời trang theo phong cách tạp chí

Use the uploaded real street style photo as the source. Create one vertical 9:16 comparison image: Top 50%: original photo Bottom 50%: AI-filtered editorial fashion illustration Keep the person clearly recognizable. Preserve the original hairstyle, body proportions, pose, movement, outfit colors, clothing silhouettes, shoes, bags, accessories, and the overall mood of the photo. Do not simply apply a cartoon effect or trace the photograph. Redraw the person as a polished editorial fashion illustration with slightly refined, naturally elongated proportions, clean hand-drawn linework, matte color fills, subtle tonal variation, and soft handcrafted texture. The outfit is the priority. Carefully preserve important fashion details such as: clothing shape and layering, shoulder line, waistline, skirt or trouser length, pockets, collars, cuffs, footwear, bags, glasses, jewelry, and other recognizable accessories. Simplify the facial features into a tasteful fashion illustration style while keeping the original expression and personality. Avoid oversized anime eyes, chibi proportions, doll-like faces, or overly cute expressions. Transform the surrounding environment into the same illustration language instead of removing it. Keep the most important architecture, storefronts, windows, streets, trees, shadows, and environmental color blocks so the filtered image still feels like the same place and the same moment. Simplify unnecessary background details while preserving the original composition, camera angle, lighting direction, and spatial relationships. Use clean continuous outlines, soft matte colors, subtle paper texture, restrained hand-painted details, and a modern Japanese editorial fashion illustration feel. The result should feel stylish, natural, contemporary, and collectible, like an illustrated OOTD page from a fashion or lifestyle magazine. Avoid photorealistic rendering, glossy 3D, heavy watercolor bleeding, thick oil-paint texture, excessive linework, generic cartoon styling, or changing the outfit into a different design. Keep the top and bottom images closely matched in crop, subject scale, pose, and composition. The two sections must each occupy exactly 50% of the final image. Do not add any text, titles, labels, logos, brand names, watermarks, borders, Before/After labels, or decorative typography.

#时尚#插画#街拍+2
户外木质阳台柔韧姿势比基尼女性
ChatGPT

Cô gái mặc bikini tạo dáng uyển chuyển trên ban công gỗ ngoài trời

Ultra-realistic photographic photo, 8K resolution, masterpiece. Sunny outdoors, daytime, a young woman standing on a wooden balcony. Dynamic and bold pose, back bent significantly backwards, an extremely flexible pose to highlight the chest and abdomen. Shot from diagonally below at an extreme low angle. She is wearing a black bikini, face looking up at the sky, long brown hair flowing towards the back due to gravity and wind. One arm gracefully held high above the head, the other hand gripping the balcony railing to support the body. A tight waist showing a beautiful curve, emphasized abdominal muscle lines. Backlighting creates a beautiful halo effect, intense shadows cast through the leaves, background is blue sky and vibrant green trees. Portrait photo, sharp focus, realistic skin texture, anatomically correct skeleton, cinematic lighting, full of cinematic feel.

No tags
漫展红裙中国风少女全身人像摄影
ChatGPT

Nhiếp ảnh chân dung toàn thân cô gái phong cách trung hoa trong bộ váy đỏ tại triển lãm truyện tranh

## [Subject Description] A photorealistic full-body portrait of a **young adult East Asian woman** with a naturally feminine, slender-curvy physique, long legs, and realistic Hourglass figure. She has fair warm-toned skin, a softly oval face, delicate refined features, dark almond-shaped eyes, natural straight eyebrows, a small straight nose, softly rosy lips, and a calm, slightly reserved expression. She is looking down at a smartphone held in both hands. Her hair is **very long, straight, and glossy black**, parted slightly off-center, with long face-framing strands falling naturally around her cheeks and extending well down her back. She wears large ornate **gold drop earrings**. Her outfit is an elaborate **Chinese-inspired fantasy/cosplay costume**: a deep red satin cropped top with a plunging neckline, pale pink trim, soft white faux-fur edging, decorative gold epaulettes on the shoulders, and wide translucent pink sleeves patterned with overlapping dark-outlined petal/scallop shapes. A round gold ornament decorates the waist. She wears a long deep-red high-waisted skirt with intricate traditional floral and swirling patterns in pale green, pink, cream, and gold. The skirt has a high side slit revealing one leg. A long **lavender-purple sash** is wrapped and tied around her waist, with its ends hanging down over the skirt. Dark purple fabric is visible beneath the skirt opening. She wears glossy **deep-red pointed-toe stiletto pumps**. Her pose is elegant and slightly playful: her back and shoulder lean naturally against a wall, one leg straight on the floor while the other is bent backward at the knee with the pointed heel lightly touching the wall. She holds her smartphone naturally at chest level. She possesses the best head-to-body ratio, a perfect, curvaceous, S-shaped female figure,Hourglass figure,long legs with perfect leg lines, and a slender waist, perfect foots,perfect foot lines ## [Scene / Background] An indoor **large-scale anime, comic, or cosplay convention exhibition hall**. The woman stands beside a light gray tiled wall. The spacious hall extends into the background with polished reflective flooring, structural columns, overhead industrial ceiling elements, exhibition displays, and large colorful anime character posters. Several convention attendees and cosplayers appear in the background, naturally blurred and out of focus, creating an authentic crowded event atmosphere. Keep the woman as the clear visual subject while retaining recognizable convention context. ## [Lighting / Ambience] Bright indoor exhibition-hall lighting from multiple recessed and overhead ceiling fixtures. Soft, even illumination on the woman with gentle shadows and natural skin rendering. Cool-neutral ambient light mixes with slightly warm highlights from the hall lighting. The polished floor produces subtle realistic reflections. Background lighting falls naturally into soft bokeh. ## [Composition / View] showing the entire woman from head to both shoes without cropping any limbs or accessories. Eye-level to slightly low camera perspective, approximately 50mm portrait-lens look. The woman occupies the left and central portion of the frame while the convention hall recedes toward the right. Natural perspective, realistic depth of field, sharp focus on the woman, softly blurred background, clear separation between foreground subject and convention crowd. Preserve the complete pose, including the bent leg, both feet, shoes, long skirt, sash, and hair. ## [Style Reference] High-end **photorealistic cosplay photography**, realistic East Asian facial features, natural adult appearance, authentic skin texture, physically accurate anatomy and proportions, realistic hair strands, satin and translucent fabric textures, detailed embroidery and costume construction. Elegant fashion-editorial quality combined with an authentic anime convention environment. No illustration, no cartoon rendering, no exaggerated anatomy, no artificial beauty-filter appearance. ## [Image Quality Parameters] Ultra-detailed photorealism, high-resolution photography, crisp facial and costume details, realistic skin pores and texture, natural hair detail, accurate hands and fingers, realistic fabric folds and material reflections, physically plausible lighting, subtle depth of field, cinematic background bokeh, polished floor reflections, balanced exposure, high dynamic range, professional cosplay editorial photography, clean image rendering, natural color grading, sharp subject focus, no fisheye distortion, no excessive blur, no cropped limbs,No cropped limbs or truncated feet.

No tags
超写实日式和室双人旗袍黑丝写真
ChatGPT

Phòng nhật bản đôi sườn xám siêu thực theo phong cách nhật bản ảnh lụa đen

Hyper-realistic Japanese-style washitsu double portrait, vertical aspect ratio approximately 3:4, two clearly adult East Asian women, 20+, sitting side-by-side on traditional tatami room floor, camera placed extremely low directly in front of their feet, using a 20–24mm ultra-wide-angle lens for a close-up low-angle upward shot. The feet of the two people are closest to the lens, and the soles of the feet wrapped in thin black stockings are significantly enlarged, occupying the lower half of the frame; the faces are located in the upper-middle part of the frame, forming a strong near-large far-small perspective. Both individuals have small-to-medium frames, slender waists, naturally full thighs, and realistic body proportions. They are sitting naturally against a Japanese-style wall with their legs extended toward the camera and knees bent: the legs of the person on the left are basically parallel and pointing forward, with both soles directly facing the camera; the legs of the person on the right are crossed, with one sole in the foreground center and the other slightly raised to the right. The soles are completely covered by stockings, and the outlines of toes, ball of the foot, arch, and heel can be clearly identified through the thin stockings; the stockings become more transparent after being stretched on the soles, with fine fabric texture visible at the tips. Appearance details: the person on the left has long straight jet-black hair combed back to reveal ears and forehead, wearing small gold earrings. The person on the right has hair in a simple low bun with a few stray strands on the sides of the face. Both look directly at the camera with quiet, cold expressions and exquisite yet natural makeup: slender eyeliner, light brown eyeshadow, and low-saturation bean paste lip color. Clothing consists of two different colored modern slim-fit cheongsams / modified Chinese-style sleeveless dresses. On the left: a warm ginger / amber yellow cheongsam with a stand collar, sleeveless, tight-fitting cut, fabric with red-orange floral and small traditional patterns, a small teardrop opening at the center of the neckline, and the skirt hem naturally split on the side, revealing thighs in a sitting position. On the right: a grey-blue / slate grey floral cheongsam, also high-collared and sleeveless, covered with pink, dark red, and cream-white flowers and green leaf patterns; the fabric is matte and soft, fitting the waist and hips, with the skirt naturally spread out with the sitting posture. Both wear smoke-black ultra-thin translucent pantyhose / sheer pantyhose, about 10–15D, in tones of black-grey or dark coffee-grey, which clearly reveal natural skin tone. The stockings completely cover from the thighs to the toes, with a delicate silken luster on the surface that produces faint highlights under the flash. No fishnets, thick black socks, or bare feet. Hand placement is natural: the person on the left has hands near the chest/abdomen or between the knees; the person on the right has one hand lightly on the chest and the other propped on the side of the body, maintaining a casual group photo state. Setting is a traditional Japanese tatami washitsu. The floor is laid with light beige straw-woven tatami with dark green woven edges. Background includes white lime walls, dark brown wooden beams, wooden lattice sliding doors, and translucent washi paper windows. On the upper left wall hangs a white wood-framed calligraphy piece with black ink characters. In the foreground on the upper right, there is a thick low dark brown wooden table, the corner of which is very close to the lens, creating obvious perspective enlargement. On the table is a transparent glass teapot filled with light golden-yellow tea, next to a white teacup. The wooden table partially blocks the upper right of the frame, increasing the sense of real space. Lighting uses front-facing portable digital camera hard flash combined with dim indoor warm light. The flash directly illuminates the faces, cheongsams, and stockinged soles; skin tones are warm white; the soles are very clear and bright due to being closest to the flash, with obvious stocking textures, toe outlines, and arch layers. The background wooden structures and deep parts of the room remain dark. Overall texture is 2000s–2010s Asian photo / CCD digital camera indoor direct flash style: strong ultra-wide-angle perspective, slight vignetting, small amount of grain, slightly soft edges, limited dynamic range, realistic skin texture, no modern HDR or commercial studio photography. Key Focus: Two adult East Asian women + Japanese tatami room + ultra-low camera position close-up low-angle shot + two people sitting on the ground with legs extended + multiple thin black stockinged soles directly facing the camera and significantly enlarged by wide angle + clear toe and arch outlines + ginger yellow floral cheongsam + grey-blue floral cheongsam + smoke-black sheer pantyhose + glass teapot + dark low wooden table + wooden beams and calligraphy + front direct flash + CCD photo texture. Avoid: Minors, bare feet, white socks, fishnets, thick black stockings, high heels, standing posture, kneeling posture, normal eye-level camera angle, modern Western-style bedroom, people too far away, soles too small, shoes blocking feet, anime faces, CG feel, plastic skin, extra toes, extra legs/feet, watermarks, and garbled text.

No tags
真实动物情境拟人化警示图
ChatGPT

Hình ảnh cảnh báo nhân loại về tình huống có thật của động vật

Animal: [Specific Animal] Event: [Specific Event] Place this animal into this specific event, using Realistic Animal Photography × Situational Anthropomorphism × Reaction Meme × Mild Warning Visuals. Retain the physical structure, fur, claws, face, and species characteristics of the real animal, do not transform it into a humanoid form. Automatically design the most appropriate scene, actions, expressions, eye contact, character relationships, and props based on the event. If the event includes a clear profession, social identity, or role identity, the animal can be dressed in clothing, hats, badges, equipment, and accessories matching that identity, but the body still maintains its real animal form. Prioritize representing a single, realistic, absurd, and easy-to-understand moment in the frame. If the event involves danger, violations, or obvious consequences, prioritize expressing the warning through the visual itself, such as electric arcs, sparks, heat, damage, slipping, leaking, startled reactions, pathetic consequences, etc.; do not stack them into a safety education infographic. Keep the layout simple: a single complete frame, no columns, no storyboards, no multi-panel comics. At most, add one eye-catching short title and one short roast, dialogue, or warning phrase. Overall, make it funny first, then make people realize the consequences. Shorter version: [Specific Animal] is experiencing [Specific Event]. Realistic Animal Photography × Situational Anthropomorphism × Reaction Meme. Retain real animal structure; if there is a clear profession or social identity, they can wear corresponding uniforms, hats, badges, and equipment, but do not transform into a humanoid. Automatically design scenes, actions, expressions, eyes, and props based on the event. If there are dangers or consequences, visualize them directly through the image; do not make it into a long knowledge-popularization image. A single complete frame, at most one large title + one short dialogue or warning.

No tags
独立杂志感拼接纸艺海报
ChatGPT

Poster nghệ thuật ghép giấy theo phong cách tạp chí độc lập

Create one independent editorial-style poster for each uploaded photo. Do not make a collage. Process and output each photo separately. Use a strict 3:4 vertical composition, divided horizontally into two exactly equal sections, each occupying 50% of the canvas. TOP HALF — ORIGINAL PHOTOGRAPH Preserve the original photo. Keep the main subject unchanged while retaining its realistic texture, natural lighting, and original color atmosphere. Apply only subtle editorial-grade color correction to create the refined feel of an art magazine, independent publication, or exhibition photography. To fit the composition, you may gently extend the sky, ground, or surrounding environmental background, but do not stretch, distort, or alter the main subject. BOTTOM HALF — LAYERED PAPER CUT / PAPER ART REINTERPRETATION Reinterpret the most recognizable subject, silhouette, pose, and spatial relationships from the photo as a minimalist layered paper-cut / paper-art composition. Use one primary subject as the visual anchor. Do not mechanically reproduce every detail. Instead, reconstruct the key silhouette, proportions, and structure through folding, cutting, layering, and overlapping. Transform only a few supporting environmental elements into foreground, midground, and background paper layers. Use scale contrast, negative space, clean alignment, and front-to-back layering to make the subject immediately recognizable while maintaining a restrained editorial composition. COLOR & MATERIAL Extract the most distinctive and recognizable colors from the original photo, then reduce them into a limited and harmonious paper-art palette. Use warm ivory or light-colored paper as the base, supported by a small amount of stronger accent colors, darker structural tones, soft transitional layer colors, and very limited highlights. The material should resemble high-quality matte cardstock, with subtle visible paper fibers, clean cut edges, and soft contact shadows under natural diffused lighting. Emphasize the tactile quality of real handcrafted paper art. Avoid glossy plastic-like 3D effects, cheap craft-paper aesthetics, neon colors, and overly saturated or complex gradients. EDITORIAL TYPOGRAPHY SYSTEM Add a refined editorial typography system. Based on the identity, location, action, material, emotion, or symbolic meaning of the subject, create one short main title. Add 2–4 groups of smaller supporting text. These may include object names, location information, numbers, sequence markers, coordinate-like numbers, direction words, status words, material descriptions, classification labels, or a very short poetic phrase. Do not use any year or date. The main title should convey emotion and identity, while the smaller text should add rhythm, structure, and refinement. TYPOGRAPHY INTEGRATION Integrate the typography naturally into the composition so that it interacts with the paper-cut forms. Arrange text along paper-layer edges, subject contours, geometric axes, or areas of negative space. Use horizontal or vertical typesetting, rotated text, generous letter spacing, edge alignment, corner placement, cross-section layouts, embedded typography, or partially overlapped text. The main title may have a subtle paper-cut or folded-paper quality, while the supporting text should remain thin, modern, restrained, and precise. The final result should feel elegant, tactile, balanced, art-directed, and distinctly editorial.

No tags
唐代闺阁梳妆红粉汉服美人
ChatGPT

Người đẹp trong trang phục hán phục đỏ hồng trong phòng khách nhà đường

Tang-dynasty private boudoir snapshot, clearly adult East Asian woman sitting at a vanity, looking into a bronze mirror while adjusting her hair, her back visible outside the mirror and her face reflected softly inside it, full body shot, ornate Tang hairstyle, flowing pink and red hanfu, candlelit inner chamber, carved wooden dressing table, comb, rouge box, gauze curtains, embroidered cushions, soft-light CCD, blown highlights, strong bloom, heavy blur, slight out-of-focus, hazy glow, low contrast, low saturation, film grain, slight digital noise, intimate candid feeling, ultra realistic, no text, watermark, modern objects --9:16

No tags
现代简约社论风格美食海报设计
ChatGPT

Thiết kế poster thực phẩm phong cách biên tập tối giản hiện đại

Brand: [BRAND NAME] Food / Drink: [PRODUCT] Headline: [2–4 WORD HEADLINE] Accent Color: [COLOR] Visual Interaction: [food replaces a letter / passes through type / refracts letters / becomes a divider / reveals hidden text] Supporting Info: [PRICE / HOURS / INGREDIENTS / ADDRESS] Aspect Ratio: 9:16 Create a premium editorial food poster for a modern café, bakery, or restaurant brand. Use a warm cream or ivory background, generous negative space, oversized typography, photorealistic food photography, and a clean European editorial layout. The key idea is that the food must actively interact with the typography rather than simply sit beside it. Use the selected visual interaction to create one clear visual hook. For example, a coffee cup can replace a letter, a croissant can overlap the headline, transparent glass can physically refract letters behind it, melted cheese can become part of the layout, or a missing food slice can reveal hidden text underneath. Keep the main headline large and instantly readable at thumbnail size. Combine a bold Grotesk Sans Serif with a refined Editorial Serif, using no more than 2–3 type styles. Build clear hierarchy with: large headline, medium product name, small brand information, price, ingredients, opening hours, or address. Use only cream, black, natural food colors, and one accent color. Food should look highly realistic with natural texture, believable shadows, accurate materials, and appetizing detail. Avoid CGI, plastic surfaces, excessive gloss, fake textures, or over-stylized commercial food photography. Keep the composition clean, asymmetric, refined, and brand-ready. Every text element should feel intentional and meaningful, with no Lorem Ipsum or random filler copy. The final result should feel like a real independent café campaign designed by a strong editorial design studio, with one instantly understandable food-and-typography interaction as the visual hook.

No tags
女性日常生活九宫格视觉叙事参考人像
ChatGPT

Chân dung tường thuật trực quan lưới chín ô vuông về cuộc sống hàng ngày của phụ nữ

Referencing the facial features and characteristics of the character in the reference image, generate an image aspect ratio of 3:4 vertical, divide the image into 3x3 9 segments, condense a woman's day of life into 9 images, all not looking directly at the camera, each scene is as follows ① Waking up, the appearance of sitting up from the bed, sleepy expression, messy pajamas ② Washbasin, composition from behind, face reflected through the mirror, currently brushing teeth, sleepy expression, messy pajamas ③ Preparing casual clothes, holding clothes in front of a full-length mirror, face reflected in the full-length mirror, the clothes reflected in the full-length mirror are the same as the clothes held in hand, wearing Peach John (Peach John) ④ Walking in a residential area wearing the casual clothes from ③ ⑤ Relaxing in a coffee shop wearing the clothing from ④ ⑥ Returning home wearing the clothing from ⑤, the appearance of taking off shoes at the entrance ⑦ Same clothing as ③, bathroom, composition from the side, preparing for a bath, throwing worn clothes into a laundry basket ⑧ Bathroom, soaking in the bathtub, front-facing slightly from above wide-angle composition, clear hot water ⑨ Pink rabbit pajamas different from ①, relaxing on the sofa

No tags
25岁日本女性在卧室寻找手机充电线
ChatGPT

Cô gái nhật 25 tuổi tìm cáp sạc điện thoại trong phòng ngủ

25 years old, Japanese, fair skin, slim figure, brown bun hair, loose oversized black sleeveless top, loungewear, desperately searching for a charging cable by the bed, kneeling on the floor, phone battery at 1%, anxious natural expression, slightly messy bedroom, warm indoor lighting, daily life full of atmosphere, photorealistic, 9:16

No tags
保持原始构图的精准人脸替换提示词
ChatGPT

Từ nhắc nhở thay thế khuôn mặt chính xác duy trì bố cục ban đầu

Use the uploaded TARGET IMAGE as the exact master image and the uploaded REFERENCE IMAGE only for the girl’s facial identity. Replace the face/identity of the girl in the TARGET IMAGE with the face from the REFERENCE IMAGE. Apply the same reference girl’s facial features consistently to the main central girl and to ALL four smaller framed photos around her. IMPORTANT: - Change ONLY the facial identity. - Keep the original TARGET IMAGE’s hairstyle, hair length, hair color, hair placement, earrings, sunglasses, clothing, red dress, body shape, hands, poses, bag, shoes, lighting, shadows, camera angle, perspective, background, flowers, photo frames, paper textures, decorations, handwritten text, hearts, and entire composition EXACTLY unchanged. - The sunglasses in the original target image must remain exactly where they are; do NOT remove, replace, or change them. - Do not copy the reference girl’s hairstyle, clothes, body, pose, background, or accessories. - Preserve every detail of the TARGET IMAGE except the face identity. - The reference girl must look naturally integrated into every appearance of the girl in the collage. - Maintain the original expressions, head angles, gaze directions, and poses from the TARGET IMAGE. - Match the reference face naturally to each different angle and expression without changing the original pose. - Keep the image realistic, seamless, high-resolution, and photorealistic. - Do not add or remove any objects or text. FINAL RULE: TARGET IMAGE = everything. REFERENCE IMAGE = facial identity only. Change ONLY the girl’s face identity. Everything else must remain SIM-TO-SIM with the TARGET IMAGE.

No tags
玫瑰香槟粉新中式茶室人像
ChatGPT

Hồng sâm panh hồng chân dung phòng trà kiểu trung quốc mới

Rose champagne pink CCD soft flash, a young adult East Asian female, oriental classical oval face, wearing a light rose gold slim-fit frog-button short top and a dark tea brown high-waist slit long skirt. She stands by a long table in a modern New Chinese tea room pouring tea, gently turning sideways to look at the camera. 9:16 near full body, using the short top and high-waist structure to highlight the bust, slim waist, and leg length.

No tags
高空酒廊紫色亮片兔女郎直闪抓拍
ChatGPT

Cô gái thỏ đính sequin màu tím trong phòng khách trên cao được chụp trong nháy mắt trực tiếp

Ultra-realistic night party group photography, horizontal aspect ratio 3:2, seven clearly adult East Asian women, age 20+, wearing uniform purple sequin bunny girl stage costumes, huddled tightly together for a group photo in a high-rise hotel lounge / night view restaurant. The photographer is very close, using approximately 28–35mm equivalent lens + direct front flash, figures almost fill the entire frame, crowded composition, strong sense of authentic party snapshot. All seven people wearing deep purple sequin bunny girl bodysuits, fabric covered in tiny sequins, producing purple-blue highlights under the flash; paired with black fine fishnet tights, white stand collars, black bowties, white cuffs, purple sequin bunny ear headbands, and white fluffy bunny tails on the lower back. Costumes are uniform but with slight variations in detail for each person, maintaining full normal coverage. Figures are all naturally slim to slight hourglass shapes, narrow shoulders, cinched waists, rounded hips, thighs with realistic soft volume, no athletic muscles or exaggerated proportions. Hairstyles are mainly black, dark brown, light brown, and golden brown medium-long hair, including let-down hair, low ponytails, light curls, and wispy bangs. Makeup is Japanese-style nightclub party style: distinct eyeliner, eyelashes, light brown eyeshadow, nude pink or mauve lips. Composition focus is seven people layered and squeezed together: On the left, one person is sideways with her back to the camera, looking back at the lens, white bunny tail clearly visible; next to her, one person is front-facing but slightly turned, holding a champagne glass; in the center-back, two or three people are very close, one person with a hand touching bunny ears or hair; in the front-center of the frame, one person is clearly leaning forward, body facing forward, head looking back at the lens, becoming the foreground core; on the right, two people are semi-sideways near the table, the rightmost person has light brown-blonde hair holding a slender champagne glass. Everyone is looking directly or semi-directly at the camera, expressions are cool, smiling, or slightly party-vibe, not uniform expressions. Champagne glasses, transparent glass cups, wine bottles, ice buckets, and warm candle light reflections are visible on the table and in front of the figures. Background is a dark brown wood high-rise lounge, outside the floor-to-ceiling windows is a sea of city night lights and skyscraper lights, windows reflect indoor warm light, overall background is relatively dark. Lighting uses strong camera direct flash + dim warm ambient light: faces, shoulders, sequin costumes, and fishnet tights are directly illuminated by the flash, skin tones are warm white; purple sequins generate many fine highlights; background darkens rapidly, city night view forms scattered bokeh. Allow for small amount of high ISO noise, slight motion blur, and edge softening. Overall presents a 2000s–2010s Japanese nightclub / high-rise lounge party CCD digital camera snapshot texture: high contrast, direct flash, high saturation purple, deep shadows, slight grain, limited dynamic range, realistic skin texture, no commercial studio feel. Key Focus: Seven adult East Asian women + purple sequin bunny girl suits + purple bunny ears + white bunny tails + black fine fishnet stockings + white collars and cuffs + multiple people tightly huddled + central figure leaning forward looking back + multiple people holding champagne glasses + high-rise night view lounge + floor-to-ceiling window city lights + direct front flash + 2000s digital party snapshot. Avoid: Fewer than seven people, single person overly prominent, white or black bunny girl suits, ordinary dresses, messy sock/shoe colors, daytime, outdoors, photography studio, figures standing dispersed in a row, over-smoothed skin, anime faces, CG feel, extra figures, extra limbs, watermarks and garbled text.

#兔女郎#夜店风#直闪+2
户外泼水节舞台女性主持特写
ChatGPT

Cận cảnh nữ mc trên sân khấu lễ hội songkran ngoài trời

A 9:16 vertical photograph freezes the explosive atmosphere of a huge open-air water festival after dark. Dense mist hangs beneath the lighting rigs while water rains across the stage and audience, leaving every exposed surface glossy and reflective. An adult East Asian woman dominates the right half of the frame as the main-stage MC, photographed during an intense vocal moment. Her torso faces diagonally across the stage toward the left while her hips settle into a broad, balanced stance. Her right hand holds a microphone directly beside her mouth. Her left arm rises high above her head with a loose bend at the elbow, palm open toward the crowd, creating a strong diagonal that echoes the beams cutting through the spray. Her head tilts slightly toward her raised arm, eyes wide and directed into the distance, mouth open mid-shout with a bright, exhilarated expression. A completely unbuttoned lightweight white long-sleeved shirt hangs loosely from her shoulders, its embroidered eyelet collar and sleeve details visible wherever the light strikes. The sleeves are pushed and bunched around her forearms. Saturated fabric produces irregular folds, darker damp areas, subtle translucency, and believable tension around her moving arms. Underneath, she wears a light-colored semi-sheer lace bralette with intricate floral construction and a deep plunging neckline. Her low-rise dark charcoal denim micro-shorts feature metallic silver eyelets across the waistband, with droplets gathering along the denim fibers and metal hardware. A thick textured dark strap encircles her upper right thigh. The camera sits near stage-floor height several meters away, looking upward through a 35mm-equivalent lens. Her legs create a strong foreground anchor while her upper body rises against the illuminated festival haze. The vertical composition leaves generous space above her raised hand for crossing beams, suspended droplets, and distant rigging. Her placement toward the right opens the left side of the image to reveal the immense scale of the crowd, with hundreds of indistinct figures compressed into a restless field of silhouettes and scattered highlights. The shallow-to-moderate depth of field keeps her face, torso, and clothing crisply resolved while the audience progressively melts into luminous atmospheric blur. A concentrated violet key light strikes one side of her face and torso while an intense electric-blue source washes across the opposite side. Occasional magenta reflections appear within the wet shadows. Powerful white stage beams pierce diagonally through the mist overhead, exposing countless suspended droplets as tiny bright points. A water cannon erupts behind her at an oblique angle, its spray transformed into a glowing blue-purple cloud that partially obscures the lighting truss. The soaked black stage beneath her produces fragmented mirror-like reflections around her legs and footwear, disturbed by shallow puddles and splashing water. Her skin carries realistic moisture, visible pores, tiny specular highlights, and uneven droplets across her shoulders, abdomen, arms, and legs. Damp hair separates into individual strands, with several pieces adhering naturally near her cheek and neck while loose sections react to the humid airflow. The image carries the tactile imperfections of high-energy live-event photography: slight atmospheric bloom around powerful lights, fine sensor grain, localized motion blur in flying droplets and distant hands, deep shadow pockets, clipped highlights from stage fixtures, and complex mixed-color illumination. The result feels crowded, wet, visceral, and physically close to the performance. No decorative text, quotes, slogans, captions, plastic skin, beauty-filter smoothing, or deformed anatomy. Aspect ratio 9:16.

No tags
床上嬉戏打闹的男女朋友
ChatGPT

Chàng trai và cô gái vui vẻ trên giường

Boyfriend and girlfriend, two people. The two will play and romp on the bed. Falling down due to excessive play. Clothing is random, casual wear right after a bath, messy clothes, messy hair, camera angle is random as front or true side or back or directly above, Negative prompt: bottoms, coats

No tags
1 / 687