GPT Image 2 prompts

Browse GPT Image 2 prompts for fashion portraits and graphic compositions. Compare how each prompt describes its subject and the way the image is arranged.

探索提示词

9,970 条提示词

Social Media Post - Amalfi Coast Luxury Travel Editorial — output

Social Media Post - Amalfi Coast Luxury Travel Editorial

Nagarjuna CreatesGPT Image 2
Create one ultra-realistic cinematic luxury travel editorial portrait in vertical 4:5. A naturally beautiful elegant woman relaxes on a {argument name="location" default="private cliffside terrace overlooking the Amalfi Coast"}, wearing a {argument name="dress" default="flowing sage-green satin gown"} with delicate gold jewelry, holding a {argument name="drink" default="crystal glass"} while watching the sunset over the Mediterranean. Surround her with authentic Italian details: bougainvillea, hand-painted ceramic pottery, lemons, candles, olives, fruit, elegant aperitivo dishes, patterned cushions and a beautiful tiled table. In the background: dramatic cliffs, pastel hillside villas, glowing terraces, a historic domed church, small boats on turquoise water and the sun reflecting across the sea. Use warm golden-hour light, cinematic rim lighting, natural reflections, atmospheric haze, layered depth and rich Mediterranean color. Style: Vogue + Condé Nast Traveler luxury editorial, ultra realistic, cinematic, 85mm lens, shallow depth of field, natural skin texture, detailed fabric, HDR, rich color grading, 8K. Mood: elegant, luxurious, romantic, peaceful, timeless, wanderlust, exclusive. No text, logo, watermark, border or AI artifacts.
Profile / Avatar - Minimalist Hip-Hop Woman Illustration — output

Profile / Avatar - Minimalist Hip-Hop Woman Illustration

Hania AiGPT Image 2
Beautiful {argument name="subject" default="hip-hop woman"} wearing a {argument name="headwear" default="baseball cap"}, blurred effect, painterly brush strokes, minimalist illustration. The background is pure {argument name="background color" default="ruby red"}. Dynamic character angle with motion blur. The character is dominated by black and red tones, wearing black clothing contrasted with dramatic red lighting and shadows, emphasizing a mysterious and powerful presence. Surrealist aesthetics, sophisticated atmosphere, rich depth, visually striking contrast and conflict organically blended together, reflections, artistic expression, and a luxurious high-end feel.
Profile / Avatar - Candid East Asian Woman Street Portrait — output

Profile / Avatar - Candid East Asian Woman Street Portrait

EeshaGPT Image 2
Ultra-realistic candid portrait of a {argument name="subject" default="young East Asian woman"} outdoors in bright natural daylight, captured from a slightly low angle. She has straight, shoulder-length dark black hair with soft wispy bangs framing her forehead, natural facial features, warm clear skin with realistic pores and subtle imperfections, and a bright genuine smile showing her teeth. She is wearing a {argument name="clothing" default="simple oversized plain white crew-neck T-shirt"}. Her head is slightly tilted back, shoulders relaxed, and she is looking toward the camera with a joyful, spontaneous expression. Natural loose strands of hair move softly around her face. Background: {argument name="background" default="modern city skyscrapers and urban architecture"}, heavily blurred with shallow depth of field, creating a clean contemporary city atmosphere. Strong but soft midday sunlight illuminates her face naturally, with realistic highlights and gentle shadows. Photography style: authentic candid street photography, photorealistic skin texture, natural color grading, realistic hair strands, subtle lens imperfections, 50mm lens look, shallow depth of field, soft cinematic bokeh, high dynamic range, crisp facial detail, natural exposure, no artificial beauty filter, no plastic skin, no excessive retouching. Composition: vertical portrait, approximately 4:5 aspect ratio, close-up to medium shot, subject centered slightly to the right, face prominently framed, realistic smartphone/camera photography aesthetic.
Comic / Storyboard - Dark Surrealist Library Archive — output

Comic / Storyboard - Dark Surrealist Library Archive

PSSGPT Image 2
Create an original psychological dark-surrealist scene in a colossal underground archive. Endless shelves of sealed black books rise like skyscrapers and vanish into fog. In the central aisle, a solitary human figure in bone-white clothing kneels before one open book on the floor. No words are visible. From the blank pages rises a delicate life-size figure made entirely of dense black smoke, standing face-to-face with the kneeling person. The smoke figure has no eyes or mouth; instead, its chest contains a small locked crimson door. Thin threads connect that door to the kneeling person’s hands, suggesting a secret self finally acknowledged.

Vertical 9:16 framing, towering shelves create a narrow symmetrical canyon, high-angle shaft of cold silver light, the two figures positioned small in the lower center, immense oppressive scale above them. Black paper, aged stone, floating ash, volumetric fog, subtle polished-floor reflections, premium photorealistic dark concept art, refined editorial composition, quiet dread and introspection rather than horror spectacle.

Color palette: obsidian black, graphite, bone white, cold silver, a single muted crimson accent at the tiny door.

Constraints: entirely original metaphor; blank book pages with absolutely no writing; no recognizable person; no text, symbols, logos, signatures, borders, or watermark.

Avoid: visible letters or runes, portrait close-up, split face, black substance on skin, glowing eyes, gore, skulls, conventional ghosts, fantasy wizard styling, imitation of any named artist.
E-commerce Main Image - Luxury Skincare Campaign Poster — output

E-commerce Main Image - Luxury Skincare Campaign Poster

Playyy AIGPT Image 2
Create a premium skincare poster for a fictional brand. Feature a glass serum bottle on a glossy cream surface with golden lighting, water droplets, soft reflections, botanical shadows, elegant typography, and a high-end beauty campaign feel. Create a refreshing soda poster for a fictional drink brand. Feature a colorful can with ice, bubbles, condensation, citrus slices, splash effects, bold typography, vibrant colors, and crisp commercial product lighting. Create a futuristic product launch poster for a fictional AI device. Feature a sleek minimal device floating in the center with glowing light, glass reflections, subtle motion blur, modern typography, and a clean high-end tech campaign style.
Social Media Post - Whispers of Spring Cherry Blossom — output

Social Media Post - Whispers of Spring Cherry Blossom

Compound Learning - Tech | ScienceGPT Image 2
{
  "title": "WHISPERS OF SPRING",

  "scene": "A peaceful pathway beneath blooming cherry blossom trees during a warm spring afternoon. Pink blossoms fill the canopy overhead while delicate petals drift gracefully through the air. Soft sunlight filters through the branches, creating a dreamy and enchanting atmosphere.",

  "subject": "A young woman walks away from the camera before gently turning her head over her shoulder with a soft, mysterious smile. She wears a flowing natural linen dress that moves gracefully with the breeze, highlighting her delicate facial features and effortless elegance.",

  "detail": "Wind carries countless pink cherry blossom petals across the frame while warm sunlight creates glowing highlights throughout the scene. Every strand of hair moves naturally in the breeze, with ultra realistic skin texture, lifelike fabric folds, soft floral surroundings, and subtle atmospheric haze enhancing the cinematic realism.",

  "atmosphere": "Elegant, peaceful, romantic, dreamy, timeless, cinematic, graceful, and enchanting.",

  "lighting": "Warm spring sunlight filtering through cherry blossom branches, soft natural illumination, glowing highlights, volumetric light rays, gentle ambient shadows, and subtle atmospheric haze.",

  "composition": "Cinematic editorial portrait captured with an 85mm lens, featuring the subject in a three-quarter over-the-shoulder pose. Shallow depth of field, creamy bokeh, balanced framing with flowering trees, soft leading lines, and immersive visual storytelling.",

  "style": "Photorealistic, masterpiece, editorial fashion photography, analog film aesthetic, dreamy pastel color palette, ultra realistic skin texture, highly detailed, shallow depth of field, creamy bokeh, atmospheric haze, HDR, cinematic realism, 8K."
}
Profile / Avatar - Golden Hour Rose Bouquet Portrait — output

Profile / Avatar - Golden Hour Rose Bouquet Portrait

AIwithMinalGPT Image 2
Ultra-realistic cinematic vertical portrait of a beautiful young woman standing gracefully outdoors in warm golden-hour sunlight, holding a large bouquet of fresh deep-red roses close to her chest. She has long, naturally flowing black hair cascading over her shoulders and down her back, with soft windblown strands framing her face. Her features are delicate and elegant, with expressive dark-brown eyes, naturally defined eyebrows, long eyelashes, luminous smooth skin, subtle warm blush, and soft red lips with a gentle confident smile.

She is wearing an elegant deep-burgundy long-sleeved dress with a refined, slightly sheer texture and sophisticated silhouette. She wears delicate pearl drop earrings that catch the sunlight beautifully. The bouquet consists of multiple realistic crimson-red roses with lush green leaves and natural stems.

A large soft peach-orange helium balloon floats beside her in the upper-right background, attached with thin delicate strings, adding a romantic dreamy atmosphere. Warm sunlight creates a beautiful golden rim light around her hair and shoulders, with subtle glowing highlights and natural lens flare. The background features elegant dark architectural details softly blurred into creamy bokeh.

Professional fashion photography, romantic cinematic atmosphere, photorealistic skin texture, natural facial details, realistic hair strands, highly detailed roses and fabric, shallow depth of field, creamy bokeh, HDR, soft cinematic color grading, 85mm portrait lens, f/1.8, natural golden-hour lighting, sharp focus on the face, sophisticated editorial aesthetic, ultra-detailed, 8K quality, vertical composition, 9:16 aspect ratio.
Infographic / Edu Visual - Consistent Identity Hairstyle Lookbook — output

Infographic / Edu Visual - Consistent Identity Hairstyle Lookbook

CiriGPT Image 2
Create a 12-panel grid (3 columns × 4 rows, numbered 1 to 12) showing the SAME person from the reference photo with 12 different hairstyles. This is a hairstyle lookbook. Final image aspect ratio: 4:5 (vertical/portrait). THE ONLY THING THAT CHANGES BETWEEN PANELS IS THE HAIR ON THE HEAD (shape, style and length only). Everything else stays exactly as in the reference photo. Identity Anchor (Critical) The face must be IDENTICAL to the reference photo in every single panel. Preserve exactly: facial bone structure, jawline, cheekbones, nose shape, lips, eye shape and spacing, eyebrows, skin tone, skin texture (pores, natural imperfections), and overall facial proportions. This is the same real person in all 12 frames. Do NOT beautify, slim, or alter the face. Same age, same expression as in the reference. Mandatory Rules (Do Not Violate) - NO SUNGLASSES. Eyes must be fully visible in all 12 panels. - NO ENVIRONMENTAL BACKGROUNDS. Every panel must have a plain, uniform, solid light grey studio backdrop with zero objects, zero textures, zero gradients. Just flat neutral grey. - Hair COLOR stays exactly as it appears in the reference photo in all 12 panels. Only the shape, length and style changes, never the color. Keep Identical in Every Panel (Do Not Change) - MAKEUP AND SKIN: If the person in the reference photo wears makeup, replicate it identically in every panel. Same lip color, same eye makeup, same brow grooming. If they wear no makeup, keep all panels makeup-free. Do NOT add, remove, or alter makeup between panels. - Clothing: the same clothing visible in the reference photo, replicated exactly. - Accessories: preserve ALL visible accessories from the reference photo (earrings, necklaces, rings, bracelets, piercings, watch, glasses, etc.). Do not omit, resize, recolor, or restyle any accessory. If the person wears prescription glasses (not sunglasses), keep them in every panel. - Background: plain solid light grey studio backdrop in every panel. No room, no furniture, no environment. The 12 Hairstyles 1. Pixie cut: very short, textured, slightly tousled on top with tapered sides and nape 2. Classic bob: chin-length, straight, blunt ends, clean middle part 3. Long layered waves: past the shoulders, soft voluminous waves with face-framing layers 4. Sleek low bun: hair pulled back smoothly into a tight low bun at the nape, no flyaways 5. Curtain bangs with medium-length hair: soft parted fringe framing the face, hair falling just past the shoulders 6. High ponytail: hair pulled up into a sleek high ponytail, smooth crown, length falling behind 7. French bob: short bob ending at the jawline with a soft blunt micro-fringe across the forehead 8. Long straight hair with middle part: very long, sleek, pin-straight, falling well past the shoulders 9. Shaggy wolf cut: medium length, heavy layers, choppy fringe, textured and voluminous with a slightly wild look 10. Elegant updo: hair swept up into a polished chignon with soft face-framing tendrils 11. Short curly crop: short voluminous curls all over, natural texture, tapered at the sides 12. Side-swept Hollywood waves: long glamorous deep side part, sculpted vintage waves cascading over one shoulder Photographic Specs Shot on a Canon EOS R5 with an 85mm f/1.4 lens, studio portrait lighting (soft key light, subtle fill), shallow depth of field with sharp focus on the face. PLAIN SOLID LIGHT GREY STUDIO BACKGROUND in every panel. Natural skin rendering with visible pores and realistic hair strands (no plastic or CGI look). Consistent lighting, color grading and exposure across all 12 panels. Photorealistic, high detail, hyperrealistic, 8K. No illustration, no painterly effect, no over-smoothing. NO SUNGLASSES. Each panel clearly numbered 1 to 12 in the top-left corner. Overall output aspect ratio 4:5.
Profile / Avatar - Woman with Plush Rabbit Close-up — output

Profile / Avatar - Woman with Plush Rabbit Close-up

EeshaGPT Image 2
Ultra-realistic cinematic extreme close-up of the {argument name="subject" default="adult woman"} from the reference, strict identity lock with exact facial features and proportions. She lies on a bed hugging a large {argument name="object" default="white plush rabbit"} against her cheek. 70–80% side profile, face slightly turned toward camera, one eye meeting the lens, calm intimate expression. Loose natural hair with a few strands across her face, minimal makeup, realistic pores and skin texture. Warm sunlight stripe across her face with soft ambient fill. Dense realistic rabbit fur, shallow depth of field, corrected portrait perspective, cinematic lighting, subtle film grain, natural colors, 8K detail. No beautification, identity drift, distorted profile, plastic skin, tangled hair, extra fingers, CGI look, text or watermark.
Comic / Storyboard - Surreal Faceless Figures Portrait — output

Comic / Storyboard - Surreal Faceless Figures Portrait

AijazGPT Image 2
A cinematic, photorealistic portrait of a mysterious young man use image for face reference standing perfectly centered in a surreal crowd of identical faceless figures dressed entirely in white. The man has short, neatly styled black hair, sharp masculine facial features, light stubble and a trimmed beard, intense dark eyes, and a calm, emotionless expression. He wears an {argument name="subject clothing" default="impeccably tailored all-black suit"} with a {argument name="shirt color" default="wine colour dress shirt"}, creating a dramatic contrast against the surrounding white figures.

The crowd consists of numerous human-like figures wearing {argument name="crowd clothing" default="seamless white full-body garments"} that completely cover their heads and faces, creating an eerie, anonymous atmosphere. Several white figures stand close to the camera in the foreground, heavily blurred and partially obscuring the frame, while others fade into the background.

Symmetrical composition, centered subject, eye-level camera, shallow depth of field, strong foreground bokeh, soft diffused studio lighting, muted monochromatic black-and-white palette, subtle atmospheric haze, minimalist surrealism, psychological thriller aesthetic, mysterious and unsettling mood, high-end fashion editorial photography, realistic skin texture, cinematic lighting, extremely detailed, natural proportions, 85mm portrait lens, f/2 aperture, soft background blur, vertical composition, ultra photorealistic, 8K detail.

No text, no watermark, no logo, no extra limbs, no distorted faces, no cartoon or illustration style.
Product Marketing - Experimental Editorial Portrait Poster — output

Product Marketing - Experimental Editorial Portrait Poster

Saul GoodmanGPT Image 2
Create a medium-sized 9:16 experimental editorial portrait poster using the following customizable inputs:

Subject: {argument name="subject" default="Adult Male or Female Portrait"}
Interference: {argument name="interference effect" default="Color Split / Narrow Light Beam / Horizontal Cut / Motion Veil"}
Title: {argument name="title" default="Title"}
Palette: [Main Neutral Tones + One Accent Color]
Mood: [Sharp / Cinematic / Restrained / Experimental]

Create a striking close-up or waist-up portrait with the subject occupying a strong portion of the frame. Preserve realistic facial features, natural skin texture, authentic hair, realistic proportions, clear emotion, and a strong silhouette. The portrait must work visually as a fashion photograph before the graphic intervention is applied.

Use only one primary interference method:

Color Split: Uneven translucent bands selectively shift, reveal, separate, or distort portions of the portrait.

Narrow Light Beam: A single controlled beam cuts across the face or body and continues naturally into the surrounding space.

Horizontal Cut: Bold horizontal bands interrupt selected areas of the portrait and interact with oversized typography.

Motion Veil: Keep the main portrait sharp while selected areas create subtle horizontal photographic motion trails.

Make typography an integral part of the composition. Use one dominant headline, allowing letters to crop beyond the frame, overlap the subject, disappear behind the body, or interact with the interference.

Keep supporting text minimal: one small series label and one short phrase.

Use mostly black, white, grey, charcoal, or deep neutral tones, plus one accent color. Keep skin tones natural and avoid excessive warmth or yellow grading.

Add only a few subtle graphic details such as fine lines, circles, or open corner marks when necessary.

The final composition should feel like a premium fashion editorial, contemporary photography poster, or experimental art-direction piece—clean, intentional, sophisticated, and visually balanced.
E-commerce Main Image - Luxury Perfume Commercial Photography — output

E-commerce Main Image - Luxury Perfume Commercial Photography

𝐔𝐑𝐖𝐀 𓂃♡GPT Image 2
Ultra-realistic professional commercial product photography of a {argument name="product" default="premium glass perfume bottle"} placed on a {argument name="surface" default="polished black marble table"} inside a luxurious modern hotel lobby. The perfume bottle has a sophisticated transparent glass design, elegant metallic cap, realistic liquid visible inside, subtle condensation droplets, and clean premium packaging. In the background, a large floor-to-ceiling window overlooks a {argument name="view" default="beautiful modern city skyline"} during golden hour, with warm sunlight naturally entering the room. The bottle is positioned perfectly in the center of the composition with realistic studio-quality reflections on the glass and marble surface. A few delicate white flowers and minimal luxury accessories are arranged naturally around the product without distracting from it. Soft warm sunlight creates realistic highlights along the edges of the bottle while subtle professional fill lighting keeps the product perfectly exposed. Natural shadows, realistic glass refraction, accurate reflections, physically accurate materials, authentic photography imperfections, shallow depth of field, realistic background bokeh, premium beauty campaign aesthetic, high-end commercial photography, shot on a professional full-frame camera with an 85mm lens, natural cinematic color grading, extremely detailed, photorealistic, 8K resolution, sharp product focus, realistic proportions, vertical 9:16 composition, no fantasy elements, no surreal effects, no floating objects, no distorted packaging, no extra text, no watermark.
Comic / Storyboard - Police Robot Dinosaur Battle Scene — output

Comic / Storyboard - Police Robot Dinosaur Battle Scene

カーブミラーGPT Image 2
"{argument name="squad name" default="Metropolitan Police Department Heavy Equipment Countermeasures Division Robot Squad"}" {argument name="situation" default="Fighting with a research-developed dinosaur-type robot"}
Profile / Avatar - Chinese Dreamcore Portrait Photography — output

Profile / Avatar - Chinese Dreamcore Portrait Photography

未明SuHuanGPT Image 2
{argument name="aspect ratio" default="9:16 vertical"}, {argument name="texture" default="realistic real-person photography texture"} × {argument name="scene" default="traditional Chinese dressing"} × {argument name="atmosphere" default="chilly dreamcore atmosphere"}
Game Asset - Vermilion Sword Character Concept Art — output

Game Asset - Vermilion Sword Character Concept Art

AIライフハックGPT Image 2
# CUSTOM_VERMILION_SWORD_ANCHOR ## [Input Item] Protagonist: [Female / Male] (Selection required) ## [Purpose] Without using reference images, generate a new single anchor image to serve as the protagonist for this video project. This image will be used as the sole design standard for character, costume, and sword for subsequent 'Design-focused Three-view' and 'Simple Three-view' sheets. Prioritize a character design that is not only visually appealing as a finished illustration but also has clear facial features, hair, body type, proportions, clothing, sword, and color placement, making it easy to expand into front, side, and back views later. ## [Aspect Ratio] **Fixed 1:1 square.** Fit the protagonist from the top of the head to the tips of the toes, including the entire sword, within the square without strain. Ensure a stable full-body composition where the character is not too small and is not cut off at the edges of the screen. ## [Person] A young adult male/female swordsman in their early 20s. Slender and supple, with naturally long legs and a physique capable of handling a sword. Do not make them excessively muscular. Sharp and attractive high-quality 2D anime face design. Hair should be medium length as a base, with clear shapes for bangs, sides, and the back of the head, creating a silhouette easily recognizable in a video. ## [Costume] Not traditional Japanese clothing, but a **sophisticated modern swordsman style incorporating Japanese elements**. Based on the premise of video action and three-view expansion, do not over-complicate with decorations or overlapping layers of fabric. Create a clear costume where the front, side, and back structures can be naturally developed. The primary color of the costume is **Vermilion**. The vermilion should cover enough area to identify the person at a glance. Inner-wear, pants, belt, and shoes should be primarily black to dark gray. Do not make the entire body a simple solid vermilion. Do not use multiple colors. ## [Sword] Only one sword. Maintain a natural sword shape, with the blade in a neutral metallic color and the hilt primarily black to dark gray. **Do not use a scabbard. Do not have them hold a scabbard. Do not show a scabbard on screen.** Do not make the blade itself red. While vermilion effects will generate from the tip in the main video, do not display flashy slashing effects in this anchor image. **The blade should not be drawn as a symmetrical single metal plate, but should have a clearly distinct asymmetrical structure between the edge and the spine. The edge side should have a wide, bright silver-white 'kirihamane' (cutting surface) that is continuous from the guard to the tip. The opposite spine should be thin and drawn as a dark gray metallic surface. Only the side with the wide silver-white surface is the 'edge', and the thin dark side is the 'spine'.** **The cutting surface should run continuously on the same side for the entire length of the blade and not switch to the opposite side midway. Do not create a wide silver-white surface on the spine side. Maintain a natural curve like a Japanese sword, where the wide cutting surface functions as the actual striking edge. Do not use a 'mine-uchi' (striking with the back) composition that makes the spine side look like the striking surface.** ## [Composition] Full-body image of one protagonist. Based on a natural 3/4 standing pose, where the face, both hands, both legs, shoes, entire costume, and entire sword can be confirmed. Not in the middle of a sword action, but in a quiet stance ready to start moving. Avoid extreme perspective, jumping, crouching, or poses with large body twists. Prioritize the accurate readability of character proportions and costume structure. ## [Art Style] High-quality 2D anime style. Sharp lines, organized cell shading, and a clear silhouette. Design it so it can naturally expand into the black-and-white + vermilion graphic expression used in the video. Do not make it photorealistic, 3D, or CGI. ## [Background] Simple background based on white to very light gray. Very light paper or ink nuances are acceptable but must not interfere with the design confirmation. Do not include cityscapes, buildings, crowds, text, or logos. ## [Completion Conditions] Single protagonist / 1:1 square / Full body clearly visible / Attractive and reproducible face, hair, and body / Natural hands and legs / Clear shape and color placement of vermilion costume / Full shape of one sword confirmed / **No scabbard present** / **Wide silver-white cutting surface continuous from guard to tip on the edge side** / **Spine side is thin and dark metal without a cutting surface** / **Cutting surface is continuous on the same side for the full length** / **Wide cutting surface functions as the striking edge and does not look like back-striking** / Design naturally expandable to front, side, and back / Can be used as the sole character standard for subsequent three-views. ## [Prohibitions] Multiple people, excessive decoration, multi-coloring, photorealism, 3D, CGI, extra weapons, **scabbard, symmetrical blade where edge and spine cannot be distinguished, missing cutting surface, cutting surface switching sides midway, wide cutting surface on the spine, reversal of edge and spine, mine-uchi composition,** extra limbs, distorted hands, broken sword, extreme action poses, background information overload, text, logos, watermarks, being cut off at screen edges. # CUSTOM_VERMILION_SWORD_THREE_VIEW ## [Input Item] Sheet Type: [Design-focused / Simple] (Selection required) ## [Fixed Display for Design-focused] Use only if 'Design-focused' is selected. Title line 1: `VERMILION` / Title line 2: `SWORD`. Swatches: Vermilion / Black / Dark Gray / Off-white. Auxiliary text: None. For 'Simple', do not display title, swatches, or auxiliary text. ## [Purpose] Using **only the one adopted anchor image** attached with this instruction as the sole character, costume, and sword design reference, create one three-view sheet of the same person. ## [Aspect Ratio] **Fixed 16:9.** Use a horizontal 16:9 canvas for both Design-focused and Simple types. Do not change to 1:1, 4:3, 3:2, 2:3, 9:16, or any other ratio. ## [Person Reference] Using the adopted anchor image as the sole standard, maintain facial features, age, hairstyle, hair color, hair length, body type, height, proportions, costume design, color placement of vermilion and black tones, shoes, sword, hilt, and high-quality 2D anime expression. FRONT/SIDE/BACK are not three different people, but the **same person viewed from different directions**. Naturally supplement the side and back views that are not directly visible in the anchor image based on the existing design; do not add new decorations, patterns, equipment, colors, or costume structures just because they aren't visible. ## [Three-view] FRONT is direct front, SIDE is **complete side profile**, and BACK is a clear rear view. **SIDE must always face right.** The face, nose tip, chin, gaze, chest direction, abdominal direction, and toes must **all face toward the right of the screen**. Do not point the face or nose toward the left. Do not make the SIDE a left-facing profile. Do not degrade the SIDE into a 3/4 direction. In the SIDE view, the **right shoulder, right arm, and right hand must be the foreground side closest to the camera**, with the left shoulder, left arm, and left hand in the background. Ensure the sword held in the right hand can be clearly confirmed without being hidden by the body. Do not use a composition where the left hand is primarily visible in the SIDE view. Display the full body from head to toe in all three views, maintaining the same height, proportions, body type, leg length, and costume structure. Use a natural upright posture as the base; do not cross legs or twist the body significantly. Ensure hand positions and shapes are naturally visible; in the SIDE view, do not expose the background hand to the point of breaking the side profile. Do not hide costume structure with poses. ## [Costume] Expand the costume from the anchor image into three directions. Maintain the positional relationship between the vermilion parts and black/dark gray parts; do not change color distribution per view. Rear structures not visible from the front should be minimal supplements that do not contradict the front/side structures. Do not simplify, glamorize, or redesign the costume. ## [Sword] Use **only one** sword identical to the anchor image. **Do not use a scabbard; all three views must be in a drawn state. In FRONT/SIDE/BACK, the sword must be held in the right hand; do not switch it to the left hand.** Do not change the blade, hilt, length, or curve between views; it must be the same sword seen from three directions. Maintain a natural curve; **the outside/convex side of the curve is the edge, and the inside/concave side is the spine.** Show the bright cutting surface continuous from guard to tip on the edge side, and draw the spine as a thin back. The cutting surface must pass through the same edge side in all views. **In the SIDE view, the priority is that the foreground right hand holds the sword, and the sequence of Right Hand -> Hilt -> Guard -> Blade -> Edge side can be clearly confirmed without being hidden by the body.** The sword may be held naturally diagonally downward, but at an angle that does not interfere with the right-hand grip and edge confirmation. Do not use a mine-uchi composition. Organize the sword so it does not interfere with character confirmation; do not fuse it with the body or costume. Do not perform independent sword displays, weapon displays, or scabbard displays. ## [Art Style] Maintain the same high-quality 2D anime expression as the anchor image. Do not change character design, lines, cell shading, or color expression to another style. Do not make it live-action, photorealistic, 3D, or CGI. ## [Sheet Type] ### [Design-focused] **Establish a fixed information area on the far left of the 16:9 horizontal canvas, and divide the right side into three vertical character panels: FRONT/SIDE/BACK.** Place the two-line title `VERMILION` / `SWORD` and the four-color swatches in the left info area. Character panels should be in order of FRONT, SIDE, BACK from left to right, with `FRONT` / `SIDE` / `BACK` labels placed small at the top. Panels should have uniform width, height, boundaries, and margins, with consistent character scale and head/foot positions. Fine outer frames, subtle grid lines, small dots, or very light ink/editorial accents may be used as long as they don't hide the character, right hand, sword, or costume. **The central SIDE panel must be a complete side profile facing right**, ensuring the right shoulder, arm, hand, and sword are visible to the camera. Do not make it a left-facing SIDE. **Maintain the structure of Left Info Area + 3 Vertical Panels every time; do not change to free layout. Do not add independent sword or scabbard displays.** ### [Simple] Within the 16:9 horizontal canvas, **evenly arrange three character figures in a horizontal row: Left = Front, Center = Complete Right-facing Side Profile, Right = Complete Rear.** The center SIDE must be a **complete side profile with the face, nose, chin, gaze, chest, and toes all facing the right of the screen**. The right shoulder, arm, hand, and sword are in the foreground, with the left side in the background. Do not face left. Do not use 3/4 view. The background should be white or a near-white neutral gray; consist only of the three characters and a plain background. **Do not include any text, letters, numbers, titles, view names, labels, annotations, swatches, frames, decorative lines, icons, extra graphics, independent sword displays, or scabbard displays.** ## [Completion Conditions] Same person as the anchor / Fixed 16:9 / FRONT, SIDE, BACK correctly established / **SIDE is a complete side profile** / **SIDE must face right** / **SIDE has face, nose, chin, gaze, chest, toes all facing right** / **SIDE has right shoulder, arm, hand in foreground** / **SIDE has left side in background** / **Right-hand sword grip in SIDE view clearly confirmed without body obstruction** / Consistent facial identity in FRONT/SIDE / BACK view matches head shape and hair / Consistent hair, body type, proportions / Costume design and vermilion placement match / No scabbard and drawn sword in all 3 views / Right-hand sword grip in all 3 views / Sword length, curve, hilt, edge, and spine match / Cutting surface is continuous from guard to tip on the same edge / No reversal of edge/spine (no mine-uchi) / Full body not cut off / Natural hands, legs, shoes / Design-focused structure (Left info + 3 panels) established / Simple type has no elements other than 3 figures and plain background / Do not mix sheet types. ## [Prohibitions] Character change, face change, hairstyle change, body type change, proportion change, costume redesign, changing vermilion placement, multi-coloring, extra equipment, extra swords, **scabbard, switching sword to left hand, facing SIDE to the left, pointing nose/face left in SIDE view, pointing chest/toes anywhere but right in SIDE view, hiding the right hand behind the body in SIDE view, making the left hand primary in SIDE view, breaking the SIDE into 3/4 view, reversal of edge and spine, blade switching cutting sides midway, mine-uchi orientation,** extra limbs, distorted hands, broken sword, adding decorations not in anchor, ratios other than 16:9, changing fixed layout of Design-focused type, adding text/decor to Simple type, mixing Design-focused and Simple types, photorealism, 3D, CGI.
Profile / Avatar - Custom Meme Sticker Pack Generator — output

Profile / Avatar - Custom Meme Sticker Pack Generator

HoodyGPT Image 2
Create a {argument name="subject" default="Meme sticker pack"} based on the images attached, remixing with {argument name="emojis" default="😎😛💕🚀🥳"}. Use exaggerated internet-reaction expressions, including crying, confusion, shock, smugness, side-eye, and deadpan disbelief, with awkward poses, low-fi cutout textures, and absurd humor. Create a single square(1:1) transparent sticker sheet with nine distinct stickers arranged in a 3×3 grid, each showing a different expression, pose, or reaction. Separate the stickers with wide, fully transparent gaps. No background, shadows, or overlapping elements.
Profile / Avatar - Gothic High-Fashion Extreme Close-up — output

Profile / Avatar - Gothic High-Fashion Extreme Close-up

CHAseGPT Image 2
[Person] Image 1 [Signature] In the bottom right corner, a small {argument name="logo" default="Meta-operated Threads logo"} is placed, and above it, the name "{argument name="signature" default="CHAse"}" is written in small white cursive script like a signature.

[Person's Pose and Expression]

Pose and Composition: A frontal extreme close-up / bust shot that densely captures the person's face and both hands.

Posture: Both hands are naturally crossed and raised in front of the chest and face, seductively covering the lower face and nose to highlight long nails and rings. Strands of hair falling over the face add a dreamlike scale.

Expression: An intense and fatal gaze staring directly into the camera lens through the fingers. It creates a mysterious and alluring aura.

[Clothing and Props]

Clothing: Wearing a {argument name="clothing style" default="dark-toned metallic tweed/embroidered fabric jacket intricately woven with red and gold pearl threads"}. Delicate embroidery on the sleeves and collar adds a three-dimensional effect.

Props:

Ornate Long Stiletto Nail Art: Long, sharp gothic/ornate long-tip nails featuring sophisticated gold foil and oriental patterns on a deep black base serve as a visual focal point.

Metallic Ring: A wide hammered-texture gold ring worn on a finger supports a heavy luxury aesthetic.

[Hairstyle and Makeup Details]

Hair: Long straight hair in jet black / dark brown tones flowing naturally with a part. Thin, free-spirited stray strands across the eyes and cheeks maximize the fatal aesthetic.

Makeup: Sharp cat-eye black eyeliner with long-drawn tails matched with deep smoky shaded eye makeup. Lips hidden by hands have a moist, deep red tone under the light.

[Lighting and Direction]

Light Source: Contrast created between an intense Crimson Red Gel Light bursting from the left side (person's right) and a cold deep green/emerald ambient light filling the background on the right.

Effect: Intense red highlights and shadows are formed on the person's right cheek, knuckles, nails, and jacket, creating dramatic cinematic suspense through complementary color contrast (Red vs Green).

[Texture and Color Mood]

Color: A 'Dark Crimson Noir' color mood harmonizing intense Crimson Red lighting, cold Deep Emerald Green background, and heavy Gold and Black on the nails and jacket.

Texture Details:

Nail and Ring Texture: The smooth, glossy gel coating on the long nails vs. the bumpy hammered metallic texture of the gold ring.

Jacket Embroidery Texture: The three-dimensional and detailed weaving of the metallic gold thread filling the jacket fabric.

Light Penetration Texture: Smooth specular highlights created as the intense red gel light permeates skin irregularities and knuckles.

[Film and Lens Depth, Angle]

Composition and Angle: A horizontal frontal close-up angle closely aligned with the person's eye level.

Features: Sharp focus is set like a blade on the fingers, stiletto nail art, and clear eyeliner through a shallow depth of field (DoF), while the dark green background is softly out-of-focused.

[Background and Studio Layout]

Space: A minimal studio horizon set with deep darkness and deep green ambient tones.

Detail: The background is kept dark and neat to immerse the gaze entirely in the subject's face, ornate hand gestures, and complementary lighting contrast.
Social Media Post - 4-Panel Ethnic Fashion Collage Portrait — output

Social Media Post - 4-Panel Ethnic Fashion Collage Portrait

AvelyrahGPT Image 2
Ultra-realistic 4-panel collage portrait of the same young woman in a cozy home setting, wearing a short aesthetic {argument name="outfit color" default="deep red"} kurti exactly like reference style, soft cotton texture, minimal embroidery, loose long bell sleeves, flattering fit, trendy casual ethnic look. She is wearing {argument name="jewelry" default="stylish silver earrings and matching aesthetic bangles"}, natural makeup, smooth glowing skin, realistic facial features preserved, long black silky hair. Full baggy light blue jeans visible with natural denim folds.
Profile / Avatar - Futuristic Teal-Haired Warrior Portrait — output

Profile / Avatar - Futuristic Teal-Haired Warrior Portrait

LANDCÄSTER.EXEGPT Image 2
Vertical close-up portrait of a fierce futuristic female warrior with extremely long flowing teal hair tied high, decorated with oversized red paper lantern ornaments, engraved silver bells, beads, cords, and tassels. She wears a fitted black-and-teal cropped combat outfit and a richly embroidered floral face mask in deep red, jade green, and gold. Bold red ceremonial face paint frames her intense pale eyes, with a large black calligraphic symbol painted on her forehead. Intricate tattoos cover her exposed midriff. Wind sweeps strands of hair dramatically across the foreground. Soft pale-cyan sky background, warm sunlight from the side, gentle bloom, shallow depth of field, dreamy lens softness, subtle chromatic aberration, sculpted 3D/anime realism, elegant fantasy character design, polished editorial composition, teal-red-orange palette, centered chest-up framing, mysterious and defiant mood.
Social Media Post - Tropical Vacation Editorial Photography — output

Social Media Post - Tropical Vacation Editorial Photography

𝑨𝒇𝒓𝒊𝒏GPT Image 2
Create a vibrant, cinematic, photorealistic image inspired by the provided reference image. Use the reference only for the overall character, mood, composition, and fashion aesthetic — create a fresh original scene.

A beautiful young woman with long, naturally wavy dark-brown hair, warm expressive eyes, glowing natural skin, and a bright genuine smile. She has a relaxed, carefree personality and looks naturally happy. Her hair flows dramatically in the warm ocean breeze.

She wears a loose, flowing {argument name="dress color" default="coral-red/orange"} oversized dress with {argument name="pattern" default="large cream botanical and floral patterns"}, lightweight fabric, wide sleeves, and a relaxed vacation silhouette. The dress moves naturally with the wind, creating elegant flowing shapes.

Place her in a {argument name="setting" default="stunning tropical coastal environment with turquoise ocean water, soft waves, golden sandy beach, lush green tropical plants, distant mountains, palm trees, and colorful flowers"}. Use rich, vibrant colors with a warm cinematic golden-hour atmosphere.

Photography style: ultra-realistic editorial travel photography, cinematic composition, natural skin texture, realistic facial details, subtle film grain, soft depth of field, beautiful bokeh, volumetric sunlight, warm highlights, rich color grading, high dynamic range, realistic fabric texture, natural hair movement.

Composition: full-body portrait, slightly dynamic walking pose, body turned naturally toward the camera, looking directly into the lens with a joyful smile. Capture a candid vacation moment rather than a posed studio portrait.

Make the image feel colorful, dreamy, youthful, spontaneous, luxurious, and cinematic while remaining photorealistic.

Avoid: distorted anatomy, extra fingers, extra limbs, duplicated body parts, malformed hands, unnatural face, plastic skin, excessive makeup, stiff posing, warped clothing patterns, floating objects, artificial-looking hair, oversaturated skin, blurry face, low detail, text, watermark, logo.

Vertical portrait composition, 9:16 aspect ratio, extremely detailed, photorealistic, cinematic, vibrant tropical color palette.
Comic / Storyboard - Spectral Courier Gothic Alley — output

Comic / Storyboard - Spectral Courier Gothic Alley

BediGPT Image 2
Under a fractured gas lamp, she waits in a rain-slicked alley, her {argument name="clothing detail" default="black lace veil"} dripping with mist. A {argument name="jewelry piece" default="silver locket"} pulses against her collarbone, signaling the courier is near. Her gloved hand rests on a hidden blade shaped like a {argument name="blade shape" default="church key"}. She does not shift, breathe, or blink. A stray cat hisses and retreats. The scent of wet roses and gunpowder curls around her. Her shadow pools like oil on wet cobblestones
Product Marketing - Pastel Flower Petal Dress — output

Product Marketing - Pastel Flower Petal Dress

Prompt アトリエ|AI画像プロンプトGPT Image 2
Subject:
{argument name="main theme" default="Afternoon wrapped in flower clothing"}

Main Subject:
In the center of the frame, a woman in a dress made only of pink, white, and pale purple small flowers sits sideways on a floor covered in petals. Behind her, a giant wall of the same-colored flowers extends vertically, and she holds a flower twig next to her face with her right hand.

Person/Expression:
The woman turns her face to the front, looks at the camera, and smiles modestly. A round-cheeked oval face with a small chin, horizontally long bright eyes, thin loose eyebrows, a small nose tip, and pale coral lips. {argument name="hair style" default="Dark brown hair"} is in a high braided updo, with thin bangs, curled wisps on both sides, and small flowers in the hair. Pale pink eyes and cheeks, smooth bright skin.

Clothing/Pose:
A sleeveless floral dress densely packed with small roses, star-shaped flowers, and clustered pale purple flowers. It features a deep V-neck, shoulder straps covered in flowers, a waist that follows the body, and a long floral train flowing from the left hem to the floor. Resting her left hand on the floor for support, bending both legs toward the right of the screen, and holding a flower branch to her face with her right hand.

Background/Light:
A flower wall of pink, white, and pale purple from the center to the right, a pale beige wall and floor space on the left, and a large amount of small flowers and petals in the foreground. {argument name="light softness" default="Soft direct light"} from the upper left illuminates the flowers and skin, scattering small flower shadows on the wall.

Composition/Camera:
3:4 vertical orientation, slightly high camera angle capturing from the head to above the knees. The person is large in the center, and the long flower train spreads to the lower left foreground. Focus on the person and the foreground flowers, slightly blurring the background flower wall.

Texture/Style:
A photorealistic concept photo that finely depicts realistic petals and skin. Summarizes pink, white, and pale purple in a soft pastel tone.

Negative:
Do not make the dress made only of flowers out of fabric; do not omit the long floral train
Profile / Avatar - South Asian Portrait with Majestic Peacock — output

Profile / Avatar - South Asian Portrait with Majestic Peacock

JuliaGPT Image 2
A realistic, high-detail medium shot of a young South Asian woman sitting next to a majestic blue Indian peacock outdoors. The woman has long, dark brown hair with soft highlights, wearing a {argument name="outfit color" default="white"} traditional designer Anarkali suit with {argument name="embroidery" default="blue floral"} floral embroidery and a sheer white dupatta. She is smiling gently at the camera. Next to her, a vibrant peacock stands tall with bright blue neck feathers and a lush green-and-gold crest. Background features a serene garden setting with lush green trees, soft natural daylight, shallow depth of field, 8k resolution, shot on a professional 85mm portrait lens.
按模型、风格或主题浏览

寻找下一个方向

ASTORIE CANVAS

让灵感,继续生长。

在同一个创作空间,连接提示词、参考素材和生成结果。

打开创作画布 ↗