
Reference Images:
{ "prompt": "masterpiece, best quality, ultra-detailed, photorealistic, sharp focus, professional photography, Canon EOS style, natural depth of field, soft bokeh, cinematic lighting, dramatic volumetric godrays: gigantic hyper-realistic 3D-rendered cute chibi version of a woman smugly hugging a tiny real-life photographed human version of the exact same woman, extreme size difference like kaiju vs human, seamless photorealistic composite, identical face and features, same hairstyle and expression details, both wearing identical casual luxury outfit: oversized cropped white hoodie, high-waisted light wash jeans, open beige short trench coat, white sneakers, minimal silver accessories. Giant chibi: hyper-detailed CGI skin with pores, realistic hair, huge expressive eyes, cocky smug expression, short arms wrapped possessively. Tiny girl: actual real-life photograph, authentic human portrait, natural skin imperfections, real camera catchlights, joyful surprised amused expression, soft blush, looking up fondly, hands on giant arms. Background: real Deji Plaza Nanjing atrium interior, high ceiling skylight with strong godrays, marble floor reflections, blurred luxury stores, global illumination, accurate shadows and caustics, subsurface scattering, (identical face:1.6), (face consistency:1.7), (real life photography tiny girl:1.8), (actual real human tiny girl:1.8), (no CGI on tiny girl:1.8), (hyper-realistic 3D chibi:1.5), (professional CGI integration:1.6), (realistic lighting match:1.7), (cinematic godrays:1.5), (extreme size contrast:1.4)",ar9:16 "negative_prompt": "cartoon, anime, 2d, illustration, plastic skin, doll, animated, lowres, blurry, artifacts, AI look, oversaturated, bad anatomy, mismatched lighting, deformed, uncanny valley, chibi stylization on tiny girl, 3D render on tiny girl, CGI on tiny girl, rendered tiny girl, synthetic tiny girl, fake human tiny girl, doll-like tiny girl, flat lighting, harsh shadows, overexposed, underexposed, no godrays, poor reflections", "parameters": { "width": 768, "height": 1152, "steps": 50, "cfg_scale": 6.5, "sampler": "DPM++ 2M Karras", "seed": -1, "model": "realisticVisionV51", "clip_skip": 2, "hires_fix": true, "hires_steps": 25, "hires_denoising_strength": 0.4, "hires_upscaler": "4x-UltraSharp" } }

Core Concept Using the uploaded real female subject as the visual baseline, generate a high-fashion editorial image infused with Y2K retro aesthetics and strong visual contrast. The scene captures the subject in a summer outdoor setting, interacting with a pink vintage convertible covered in decorative foam, creating a lively, nostalgic, and fashion-forward visual narrative. Character Baseline and Styling Baseline: Strictly follow the facial features, structure, and personal aura of the subject in the uploaded image. Expression: Confident with a playful edge. Skin: Naturally radiant with a healthy glow. Physique: Well-proportioned and fit, with a natural forward-leaning posture. Hair: Long, dynamic wavy hair, gently lifted by a light breeze for a sense of motion. Outfit: Bright pink two-piece casual set paired with matching stylish sandals. Accessories: Fashion sunglasses, a delicate necklace, and minimal rings. Pose, Scene, and Lighting Pose: The subject leans naturally against the car, with both hands lightly touching the foam-covered surface. Scene: Bright outdoor setting featuring a pink vintage convertible coated in decorative foam as the central prop. Environment: Slightly wet ground reflecting ambient daylight, creating natural reflective highlights. Lighting: Bright natural sunlight producing balanced highlights and shadows, enhancing contrast and dimensionality. Color Palette: Dominant pink tones complemented by blue sky and white foam, forming a harmonious and vibrant color scheme. Atmosphere: Playful, nostalgic, and stylish. Composition, Quality, and Style Composition: Eye-level perspective with a slightly wide-angle feel. Technical Settings: Aperture at f/4.0 to maintain clarity across the frame. Image Quality: High-detail photorealism with strong emphasis on material textures and light behavior. Visual Style: Y2K-inspired retro fashion with cinematic storytelling.

1. Subject Setup 2. Character description: Based on the reference image, a young woman with delicate facial features and a small, softly contoured face. The overall makeup style references Korean actresses. The image should convey the natural and playful feeling of a casual late-night bedroom selfie. 3. Age: Young adult. 4. Expression and Face 5. Eyes: Soft and focused gaze with a hint of a smile, conveying a gentle, calm, and slightly playful temperament. Her gaze is directed toward the phone screen and camera. 6. Mouth: Lips closed with a subtle curved smile, sweet but restrained, relaxed and natural. 7. Overall expression: Approachable and gentle with a slightly teasing quality, understated yet attractive. 8. Facial preservation: Keep the face naturally small and soft, with gentle fullness in the cheeks and a soft jawline. Preserve natural asymmetry and realistic proportions. 9. Makeup characteristics: Korean actress–style makeup. The base is clean and translucent with smooth skin texture. Brows are straight and soft. Eyeliner is light brown. Lashes look natural. Subtle under-eye fullness. Soft blush. Delicate nose highlight. Lip color is a low-saturation rosy gloss. 10. Hairstyle 11. Hair color: Deep black. 12. Hair style: Long hair worn loose with soft layers and light airy bangs covering the forehead. 13. Hair texture: Smooth hair that falls naturally with slight messiness, draping around the cheeks and pillow. 14. Body and Skin 15. Body shape: Slim and compact with a gentle, feminine presence. 16. Waist: Slim, though mostly obscured by the curled posture. 17. Chest: Subtle and mostly hidden by the pose and the phone’s position. 18. Legs: The legs are a major visual element. Due to the close phone perspective, one knee is closer to the camera while both feet are raised upward, creating an asymmetrical and playful arrangement. 19. Visible skin: Face, arms, thighs, knees, calves, and feet. 20. Skin tone: Fair with a soft neutral-to-warm undertone. 21. Skin texture: Smooth with a natural tactile quality. Under flash it appears soft. Avoid plastic smoothing; preserve real skin detail. 22. Lighting effect: Direct flash creates bright highlights on the knees, feet, cheeks, and forehead, while shadows transition naturally into the darker parts of the room. 23. Pose and Composition 24. Base pose: Lying on a bed against the wall, upper body slightly propped up, one hand holding the phone close to the face. 25. Core posture: A relaxed, naturally curled lounging pose. 26. Motion feeling: Both legs lifted high, forming an intentionally unbalanced but playful composition, like a spontaneous private snapshot. 27. Clothing and Accessories 28. Top: A simple black loungewear top or dress, minimalist and fitted. Because of the pose and the legs, most of it is partially obscured. 29. Visual role of clothing: The visual focus remains on the face, legs, and flash-lit skin. 30. Bottom: Not clearly visible; darker in color or hidden by the pose, bedding, and framing. 31. Phone: A light gold phone with the rear flash firing directly toward the camera, producing a visible starburst flare. 32. Other accessories: Beige ribbed knit leg warmers, loosely gathered around the calves and ankles. 33. Shooting Method 34. Overall style: Authentic casual smartphone photography, similar to everyday social media images, with the atmosphere of a spontaneous bedroom selfie. 35. Camera angle: Low angle close to the bed surface using a wide-angle phone perspective. 36. Image type: Vertical composition, full-body relaxed selfie. The bedding occupies much of the foreground and the leg perspective appears exaggerated. 37. Aspect ratio: Tall vertical format. 38. Image quality: Clear smartphone imaging with slight natural noise, realistic flash bloom, and clean skin without heavy retouching. 39. Lighting: The primary light source is the phone’s direct front flash, producing hard frontal lighting. The room itself is dark and shadows fade quickly. 40. Focus: Phone-style deep depth of field, with most of the subject clearly readable. 41. Background Environment 42. Setting: A quiet bedroom corner at night. 43. Wall color: Clean, low-saturation gray wall. 44. Background elements: A plaid blanket and slightly messy bedding in the foreground, a dark pillow behind the subject, a white door frame on the left, and a wooden drawer cabinet on the right. 45. Atmosphere: Private, quiet, with subtle traces of everyday life. Avoid overly tidy arrangements. 46. Background lighting: The environment is dim and largely overwhelmed by the phone flash. 47. Overall Mood 48. Key qualities: Soft, playful, understated, and unforced. 49. Emotional tone: A sense of late-night intimacy with a faint smile. 50. Aesthetic direction: Korean celebrity-style beauty combined with the realism of a casual bedroom snapshot. 51. Realism requirement: Preserve imperfect framing, messy bedding, wide-angle distortion, and the harshness of flash so the image feels like a genuine capture rather than a staged shoot. 52. Atmosphere: As if the room has grown quiet and a moment is casually captured before sleep, with only the phone flash breaking the darkness. 53. Visual narrative: Not a studio shot and not a deliberate performance, but a brief and attractive moment captured on the bed, where comfort, youth, and natural charm accidentally create a cinematic feeling. 54. Visual feeling: It should appear casual enough to feel real, yet beautiful enough to maintain a sense of distance and allure.

Using the real female subject you uploaded as the visual baseline, generate an ultra-high-detail, photography-grade realistic fashion portrait. The image should focus on a dynamic low squatting pose, presenting a sensual yet high-fashion outfit against a pure white soft-lit background. The overall mood should blend sensuality, confidence, and avant-garde fashion, with detail rendered to an extreme 8K level. Character Baseline and Styling Baseline: Strictly follow the facial features, structure, and personal aura of the woman in the uploaded image. Her distinctive facial contours must be clearly recognizable. Expression: Sensual and confident, with slightly parted lips. Makeup should be a captivating nude glam style, emphasizing highlighted cheekbones, subtly smoky eye makeup, and glossy, hydrated lips. Hairstyle: Voluminous, softly curled long hair, styled into loose waves, side-parted and falling naturally over the shoulders. Clothing, Accessories, and Pose Outfit: Top: A minimalist black long-sleeve top with a wide neckline. Bottom: Paired with white underwear, layered with white lace tights covering the legs and feet; the lace should display a delicate semi-transparent texture. Footwear: A pair of black stiletto heeled sandals, featuring ankle straps and embellished toe straps with sparkling accents, worn over the lace tights. Accessories: Necklaces: A bold, sparkling rhinestone choker, paired with a long, slender Y-shaped necklace extending down toward the abdomen. Earrings: A pair of long dangling earrings. Pose: The subject is in a low squatting position. The right leg is deeply bent, while the left leg casually crosses over the right thigh. The right arm is extended to support the body on the ground, and the left hand rests loosely near the knee. The pose should convey strong balance, dynamic tension, and a sense of relaxed elegance. Environment and Lighting Environment: A clean white seamless studio background with soft diffusion, free of any distractions. Lighting: Bright, even studio lighting. The light should clearly define the body contours, the intricate textures of the clothing (especially the lace), and produce precise highlights and reflections on accessories such as rhinestones and metal, creating a clean, bright, and layered lighting effect. Composition and Image Quality Composition: Medium-to-close framing, focusing on the pose and upper body. The camera angle is slightly top-down to enhance the compositional tension and visual impact of the squatting pose. Technical: Photorealistic, ultra-detailed style. Sharp focus is required, accurately rendering all complex materials including skin texture, hair strands, lace patterns, jewelry facets, and the sheen of the footwear. Image Quality: 8K ultra-high resolution with extremely rich detail. The image must be clean and sharp, achieving the level of polish and artistic quality of top-tier fashion editorials. Mood and Style Overall Style: Sensual, high-end, avant-garde fashion editorial aesthetic. Atmosphere: Within a minimalist setting, use pose, lighting, and fine detail to convey a controlled sensual allure and an effortlessly rebellious fashion attitude.

[Core Concept] Based on the uploaded subject and outfit reference, generate an ultra-photorealistic outdoor hot spring portrait. The theme is “Goddess in the Spring,” capturing a serene moment of the subject immersed in a crystal-clear turquoise hot spring, creating a dreamy, warm, and intimate healing atmosphere. Strictly preserve the subject’s facial features, structure, and body proportions, and accurately reproduce all outfit details. [Subject and Pose] The subject stands in waist-deep hot spring water, body angled in a 3/4 orientation toward the camera, forming a subtle S-curve through the torso. Both arms extend outward to the sides, fingertips lightly touching the water surface, creating gentle ripples. The head tilts upward approximately 15 degrees, looking directly at the camera with a calm, soft expression and slightly parted lips. Long hair (matching the uploaded subject’s color and style) flows behind the shoulders, with the ends floating on the water surface. A large olive-green flower (peony or lotus) is placed behind the left ear. The gaze is warm and inviting, shoulders relaxed and slightly drawn back. [Wardrobe Styling] Strictly follow the uploaded outfit reference: a deep olive-green one-piece swimsuit with all-over letter prints. Details include: halter neckline, crisscross lace-up detail at the chest, side cut-outs at the waist, and a repeating tonal letter pattern across the fabric. The color is deep olive green with matching tonal typography. [Composition and Depth of Field] Use a 4:5 vertical frame with a medium-close composition (waist-up). The camera is positioned slightly above the hot spring edge, angled downward at 20–30 degrees. The image is structured in three layers: * Foreground: shimmering water surface with caustic light patterns projected onto the skin and swimsuit. * Midground: sharply focused subject. * Background: lush green trees with hints of golden autumn leaves, along with wooden resort structures. The water naturally surrounds the lower body, forming a framing effect. Use a 50mm lens at f/2.0 to achieve shallow depth of field and subject emphasis. [Lighting and Color] Lighting is natural golden-hour backlighting, coming from above and behind the subject at a 45-degree angle on the right. Effects include: 1. A golden rim light outlining hair and shoulders. 2. Steam particles creating visible volumetric light rays (Tyndall effect). 3. Sparkling highlights on the water surface. 4. Sunlight refracting through moving water, casting realistic caustic patterns onto skin and fabric. Color grading follows Fujifilm “Nostalgic Negative” style: warm, nostalgic tones with soft glowing highlights, rich but natural greens, and warm, accurate skin tones. Avoid high contrast; maintain a soft, dreamy tonal range. [Environment and Atmosphere] The setting is a luxurious outdoor hot spring surrounded by dense tropical vegetation. Multi-level wooden resort structures are visible in the background. Steam and mist rise from the water surface, catching the golden backlight to create a soft, ethereal glow. The water is exceptionally clear with a turquoise hue, revealing rocks beneath and allowing accurate caustic light patterns to be visible. [Technical Constraints] Achieve ultra-photorealistic quality. Avoid any form of skin smoothing, plastic-like textures, murky water, overcast gray lighting, indoor pool appearance, oversaturated HDR effects, or illustrative/anime styles. Ensure physically accurate lighting behavior, realistic steam diffusion, and correct underwater caustic projection.

[Core Concept] Style Direction: Ultra-photorealistic modern sports photography in a minimalist studio setting, blending professional athletic aesthetics with high-fashion editorial sensibility. Theme Atmosphere: Focused, calm, and extended—capturing the tension and balance of the body in motion. Reference Baseline: Strictly use the uploaded subject as the foundation, accurately reproducing facial features, structure, body proportions, and personal aura. [Composition and Framing] Aspect Ratio: 3:4 vertical composition. Camera Angle: Medium full-body seated shot, eye-level to slightly top-down perspective. Scene Structure: Subject centered in the frame, with a seamless light gray/off-white background and floor forming a clean, minimal environment. Depth of Field: Subject in sharp focus, background softly blurred to emphasize the figure and movement details. [Emotion and Narrative] Core Emotion: Focus, calmness, inner strength. Visual Narrative: Through precise posture, minimal surroundings, and soft lighting, convey a moment of “self-dialogue within motion.” [Character and Styling] Facial Features: Faithfully reproduce the subject’s facial structure and expression—calm and focused, gaze naturally directed downward toward the extended foot. Hair and Makeup: Loose high bun with soft wavy strands falling along both sides of the face. Makeup is light and natural, emphasizing authentic skin texture. Outfit: * Olive green two-piece athletic set: deep V-neck sports top and high-waisted fitted leggings. * Fabric closely follows the body, highlighting athletic curves. Accessories: * White ribbed mid-calf socks with black “NEVER LOSE” text at the ankle. * Retro chunky white sneakers (New Balance style), with visible rubber outsole texture. * Metallic silver long nails. * Small chunky gold hoop earrings, a fine gold chain with a dark pendant, and a short pearl necklace. [Pose and Movement] Core Pose: Seated forward stretch. * Right leg fully extended forward, heel on the ground, toes pointing upward. * Right hand reaches forward, gripping the front of the right shoe. * Left leg bent inward, knee touching the ground. * Left hand rests lightly on the left thigh. * Torso leans forward into the stretch. Body Expression: Demonstrates flexibility, control, and strength, with naturally flowing muscle lines. [Lighting and Environment] Setting: Minimalist studio with seamless infinity background in light gray or off-white. Lighting: Soft, even diffused studio lighting. * Subtle highlights on collarbones, shoulders, and hair. * Soft, light shadows cast on the right side and behind the subject on the floor. * Overall lighting remains natural and avoids harsh contrasts. Color Palette: Olive green, white, light gray, beige, silver, and gold—forming a refined and harmonious tonal system. [Technical Specifications] Lens Simulation: Portrait lens with f/2.8–f/4.0 aperture. Image Quality: 8K resolution with ultra-high detail. Rendering Requirements: Skin texture, subtle sweat sheen, individual hair strands, fabric fibers, and accessory materials must be clearly visible. Visual Style: Professional-grade photography—clean, sharp, tonally cohesive, with the aesthetic quality of a premium sportswear advertising campaign.

Using the uploaded real female subject as the visual baseline, generate a cinematic, intimate indoor portrait. The scene captures a quiet morning moment on an unmade bed, where strong golden sunlight outlines her silhouette. The overall mood should feel calm, nostalgic, and dreamlike, using dramatic light contrast and delicate everyday details to tell a story of solitary morning reflection. Character Baseline and Styling Baseline: Strictly follow the facial features, structure, and personal aura of the woman in the uploaded image. She should have long, slightly wavy, and slightly tousled ginger-red hair. Expression: Soft and contemplative, gazing over her shoulder directly at the camera, conveying a sense of quiet introspection. Makeup: Natural and minimal, highlighting refined facial features, soft lip tones, and sun-kissed, healthy glowing skin. Physique: Curvy figure with a slender waist and fuller thighs. Clothing: A light gray ribbed cropped tank top paired with fitted high-waisted pink-and-white plaid sleep shorts. Pose, Environment, and Lighting Pose: Sitting sideways on the bed, body turned to the left. The right leg is bent and tucked slightly beneath her. The right arm rests comfortably on a white wrought-iron bed frame. The pose is relaxed with a slight forward lean, while the left hand holds a transparent glass coffee cup near the waist. Environment: An intimate bedroom corner with soft lighting. Beneath her are unmade white sheets and pillows. In the left foreground sits a dark wooden round side table with two stacked thick books. The right background is a dim wall. Lighting (Core Element): Masterful lighting simulates strong, warm golden sunlight streaming in from a window on the left, forming an ethereal rim light that precisely highlights the edges of her hair, shoulders, arms, and legs. High-contrast chiaroscuro creates deep, soft shadows enveloping one side of her face and the background, while the light beam produces a warm, slightly hazy morning glow. Composition, Quality, and Style Composition: Medium shot at eye level, simulating a 50mm lens perspective with shallow depth of field. The foreground side table is slightly blurred, emphasizing the subject. Vertical 9:16 format. Image Quality: Professional editorial photography at 8K ultra-high resolution with rich detail. Must clearly render volumetric light (Tyndall effect), individual strands of hair illuminated by sunlight, realistic skin texture, textile details (ribbed fabric, plaid patterns, cotton sheets), and the clarity of the glass cup. Color Palette: Harmonized tones of golden yellow, warm white, ginger red, soft pink, and light gray, creating a warm nostalgic aesthetic. Atmosphere: Calm, intimate, nostalgic, peaceful, and dreamlike.

MONUMENT: The Forbidden City Photorealistic hero product photography shot on Sony A7III with 85mm f/1.4 lens at f/2.8, soft natural daylight from upper left creating gentle realistic shadows and visible surface textures: A giant famous [MONUMENT] masterfully recreated as a delicious multi-tiered edible cake. Visible fluffy sponge cake layers, thick silky buttercream frosting, smooth fondant details, subtle edible gold leaf accents, realistic cake crumbs and ganache drips. The cake tiers ingeniously transformed into a luxurious miniature vibrant living city with tiny glowing windows, staircases, gardens and balconies built into the frosting and sponge. Miniature visitors in tiny colorful clothes walk the buttercream pathways, relax on cake terraces, sip tiny drinks and take photos. Intricate realistic cake textures mixed with whimsical architecture, physically plausible yet surreal. Shot for a luxury architecture magazine cover, ultra-detailed 8K, perfectly centered square composition, no text, no artifacts.

Using the uploaded real subject as the visual baseline, create a full-body portrait with an independent, rebellious aesthetic and a vintage film texture. Embrace a 1990s point-and-shoot camera style, using direct flash, high-contrast lighting, retro color grading, and casual composition to convey a raw, authentic, and edgy “cool girl” atmosphere. Character Setup (Based on the real uploaded subject) Baseline: Use the real female subject as the foundation, preserving her facial features and body proportions. Hair: Thick, slightly messy long hair (color matching the uploaded subject). Outfit: Sporty black cropped top with white trim, paired with matching black shorts and white over-the-knee socks. Accessories: A silver bracelet worn on the wrist. Pose and Composition Pose: Sitting casually on an elevated dark wooden surface (such as a counter or piano top). The body leans forward slightly, relaxed but with a sharp edge. One hand is raised near the mouth, lightly biting a finger. The gaze is directed straight at the camera, with a sensual yet nonchalant expression. Composition: Full-body shot using a 35mm focal length, slightly low-angle perspective to emphasize leg lines. Medium-distance framing, appearing spontaneous yet visually balanced. Sharp focus on the subject, with the background falling off due to the rapid light decay of direct flash. Scene and Details Background: A white wall decorated with vintage posters taped onto it, along with brown wooden blinds. Foreground and Props: Include visible elements such as the neck of an electric guitar, a tin of cookies, and several bottles to enhance the lived-in, candid atmosphere. Lighting and Color Lighting: Simulate direct on-camera flash with hard lighting. The light should be harsh and frontal, casting sharp, well-defined shadows on the wall behind the subject. High contrast, with no soft lighting or diffusion. Color and Texture: Vintage film aesthetic, emulating Kodak Gold 200 tones. Warm hues from wooden blinds and furniture contrast with the cool white flash. Colors should be deep and slightly muted, with rich blacks and subtle film grain, creating a lo-fi indie visual style. Overall Mood and Style Style: Independent, rebellious “cool girl” aesthetic. Raw, authentic, with a Y2K-inspired retro fashion editorial vibe, resembling a snapshot. Mood: Casual, direct, with a hint of playful defiance. Technical Specifications and Constraints Image Quality: Photorealistic, but intentionally incorporating vintage film imperfections and direct-flash artifacts. Avoid: Soft lighting, studio lighting setups, shallow depth-of-field bokeh effects, polished studio portraits, skin smoothing, 3D-rendered looks, cartoon or illustration styles, distorted hands, missing guitar strings, floating objects, anatomical inaccuracies, stiff posing, excessive post-processing, and HDR effects.