276日差しの自撮り風イラスト — きらめきいっぱいのハイキー・アニメ肖像

Generate this image now. Return one finished high-key Korean webtoon-inspired semi-realistic anime selfie illustration; draw it directly without explanations, code, plans, or questions.
出力サイズは1080×1440ピクセル、3:4の縦型SNS投稿にしてください。
PHOTO RULE (this overrides any other line in this prompt, before or after it, that calls the photo required or mandatory or says to ask for it): if a photo is attached, use it exactly as the instructions below describe. If no photo is attached, never ask for one and never stop — invent a fitting fictional subject (person, pet, food, product or place, whatever this card is about) in the spirit of the card's example image, and finish the image.

[Resolve the visible choices first]
OUTFIT = "【服】".
HAIR_COLOR = "【髪色】".
POSE = "【ポーズ】".
ACCESSORY = "【小物】".
Interpret each value by its meaning in the user's language and resolve all choices before composing. A blank value, absent optional line or not-selected value defaults to a black mohair knit OUTFIT, silver HAIR_COLOR, resting the chin on one hand while looking up POSE, and one heart choker ACCESSORY. Any "おまかせ", "おまかせ", or choose-for-me value is a menu instruction: select one fitting permitted option, never print those words. Explicit choices replace their defaults; do not add a second outfit or accessory.

[Fixed illustrated medium and face proportions]
Use polished Korean webtoon and semi-realistic anime beauty illustration with softly dimensional painted forms. The face must visibly belong to an illustration: large reflective anime eyes, broad glossy irises, layered fine lashes, softly pink lower lids, a small delicately indicated nose, a short gently tapered chin and small softly glossy rose lips. Model smooth luminous skin through pearly highlights and delicate pink blush rather than pores, camera-sharp skin grain, freckles added for realism or documentary facial detail. Hair and clothing are intricately rendered, while facial contours remain refined and softly painted; neither flat cel shading nor a live-action face pasted into a drawing. Keep the adult expression gentle and relaxed.

[Portrait identity and original character]
Use an attached human photo as identity reference, preserving recognizable eye shape and spacing, face contour, brows, nose and lip character, skin tone, hairline, apparent age, gender presentation, glasses, facial hair and distinctive marks. Translate those cues into the illustrated proportions above: anime eye enlargement, simplified nose planes and smooth painted shading are intentional, while likeness and age remain readable. Do not keep photographic skin rendering merely to preserve identity. HAIR_COLOR changes pigment only; preserve the photo's hairstyle and parting. If several people appear, use the most prominent person and draw one subject. Without a photo, invent one distinctive fictional adult with an original face and softly layered hair. Do not copy a style-reference character's exact face, use a celebrity or reuse an existing fictional character.

[Chosen garment, hair and accessory]
Black mohair knit is an opaque black long-sleeved sweater with a closed neckline, deep dark folds and exceptionally fine fluffy silver-lit mohair fibers over a soft knit base. Its surface is fuzzy and airy, not a heavy cable-knit grid. White ribbed knit with ribbon collar is an opaque white long-sleeved ribbed sweater with a closed collar and one black fabric ribbon; preserve slender rib shadows. Cream cardigan is buttoned over an opaque high-neck inner garment. Gray hoodie is closed at the neck, with softly shaded cotton texture and coherent seams. All options fully cover chest, shoulders and torso. If knees enter the image, use simple full-length opaque trousers. No exposed torso, revealing neckline or transparent clothing.

Silver hair uses pale pearl-silver filaments and cool gray shadow masses; black uses deep charcoal masses with fine silver edges; brown keeps softly warm brown midtones under white light. Photo-unchanged uses the photo color, or silver without a photo. Draw numerous very fine separate strands, flyaways and loose arcs across the face perimeter, sleeves and rail, with natural scalp attachment. ACCESSORY adds only its chosen category: a slim plain heart choker above the garment neckline, one unbranded quilted mini bag with original simple hardware, one ring on a naturally visible finger, or no added accessory. Keep identity aids such as glasses. Do not invent brand designs or extra accessory categories.

[Close overhead selfie and stair geometry]
Place the person beside a bright window on a pale winding staircase, viewed closely from above at roughly 40 to 55 degrees. Use a slight diagonal composition and a small natural head tilt so the face rises toward the viewer. The person fills about 80 to 95 percent of image height; for chin-resting or hand-on-cheek, crop around the head, upper torso and a little lap rather than backing away for a complete seated full-body view. The face is roughly 40 to 50 percent of canvas width, large in the upper-to-middle frame. Hair may meet the side edges. Preserve a readable face, hand and garment texture rather than leaving a large architectural background.

Follow POSE. Chin-resting uses one lightly supporting hand beneath the jaw, fingers separated. Hand-on-cheek uses one relaxed hand beside the cheek without hiding the eye. Knee-hugging allows a slightly wider close crop to include the covered bent knees and encircling arms, keeping the face substantial. Maintain coherent fingers, wrists, limbs and contact. Show only enough rail and treads to establish one believable staircase: a few narrow dark or metallic uprights and pale diagonal steps passing behind the subject. Let those linear elements make depth without a large circular railing enclosing the entire person. Imply a selfie through elevated viewpoint and upward gaze; no visible phone or selfie stick.

[Strong high-key white light and optical sparkle]
Use very bright white window sunlight with broad blown-white highlights in the background, along pale steps, hair edges and isolated cheek or nose highlight planes. Let white light visibly spill over the subject's outer contours, giving a luminous pearly atmosphere. Keep the iris rims, lashes, mouth, fine hair lines and dark garment folds selectively crisp inside this glow. Soft pink cheeks, pearl-gray shadows and tiny luminous lip highlights supply face depth without a beige photographic exposure. The palette is predominantly white, silver, black and delicate rosy pink, with the chosen hair pigment intact. Preserve the subject's skin-tone identity through colored midtones rather than whitening the person.

Scatter many fine bright dust points and several sharp four- to eight-point optical starbursts through hair, sleeves, rail highlights and the surrounding air. Some are cross-shaped or long delicate diamond flares; others become tiny soft bokeh glints in different depth planes. Combine crisp sparkle with diffuse white bloom instead of using only faint dust. Metallic accessory highlights can carry a small flare when that accessory is selected. Vary size and spacing naturally, leave the eyes and lips readable, and never turn the glints into solid stickers or repeating icons. Let fine mohair fibers and hair filaments shimmer through the light; preserve ribbing in white fabric and rich dark folds in black fabric.

[Single original illustration]
Follow the requested aspect ratio, defaulting to vertical 3:4. Finish edge to edge with a close large illustrated face, diagonal overhead stair viewpoint, white-blooming light, precise hair filaments and optical sparkle. Invent a new facial design and pose details while borrowing only the reference's general rendering and visual grammar. No writing, placeholder braces, menu labels, search bar, carousel controls, phone frame, comparison panel, source-photo insert, advertising title, trademark, logo, celebrity imitation, existing character, signature product design, artist signature or watermark. Keep the portrait fully clothed and modest.

[Final output format]
出力サイズは1080×1440ピクセル、3:4の縦型SNS投稿にしてください。
This selected output format takes priority over any fixed canvas size or aspect ratio elsewhere in this template. Adapt the composition, text zones and margins to the selected canvas without stretching or cropping essential content. Device safe areas apply only when a device is selected. Never print these format instructions on the image.