245두 사람 한 상 플랫레이

Generate this image now. Return exactly ONE complete image directly. Do not ask questions, browse for photos, return a plan or give a prompt instead of the image.

Output size 1080x1350 pixels, 4:5 portrait, Instagram standard.

[Input: values are the only facts and wording]
MAINS: "【메인 음식】"
SIDES: "【곁들임】"
TABLE: "【식탁 분위기】"
ACCENT: "【포인트 색】"
DETAIL_1: "【첫 음식의 구성】"
DETAIL_2: "【둘째 음식의 구성】"
DISHES: "【두 그릇 모양】"
UTENSILS: "【식기 두 벌】"
LIGHT: "【빛】"

[Fixed card design]
Photograph a two-person table from a truly vertical 90-degree overhead camera. MAINS gives exactly TWO main foods in order; place each on a separate large dish, diagonally balanced, following DISHES if supplied. DETAIL_1 and DETAIL_2 specify the first and second dish respectively; never merge them. SIDES gives the only side foods and drinks and their counts. Count each stated item once, distributed naturally in small dishes, basket or glasses as appropriate. One continuous table space, no grid lines, collage or multiple photos. Main foods together take at least 60% of the area.
Use believable nonrepeating food surfaces and a thin food-appropriate sauce. TABLE controls the real table and cloth. Add exactly two folded napkins and two complete UTENSILS sets, one per diner, at the edges with mild natural asymmetry. ACCENT appears in small napkin or food-related details without dyeing food unnaturally. LIGHT is soft window light from the side with short, directionally consistent contact shadows. Every dish has the same overhead projection: no three-quarter food side views, stretched edge plate or colliding glass. Keep vessels realistic in scale and separate.
Only explicitly supplied foods and SIDES may be shown; do not invent salad toppings, fruit, drink or an extra meal. A supplied DETAIL_1 or DETAIL_2 is an exhaustive ingredient whitelist for its plate, not a suggestion: no grated cheese, parmesan dust, parsley, new seasoning garnish or croutons unless explicitly listed. Do not place a plant, herb sprig or loose ingredient outside the declared dishes. If a detail input is absent choose the ordinary main food with a simple plausible composition. Keep exactly two mains and two place settings even when optional lines are absent. No text, headings, price, labels, person, hands, receipts, brand, watermark or mockup. Richness is a natural shared meal with connected ceramics, cloth and table, not a flat catalogue arrangement. This is a newly imagined meal photograph, not proof of any real restaurant's set contents.

[Button meanings, internal instructions only]
ACCENT: "초록" means green; "벽돌 빨강" means brick red; "짙은 남색" means deep navy; "겨자 노랑" means mustard yellow.
UTENSILS: "포크와 나이프" means fork and knife; "숟가락과 젓가락" means spoon and chopsticks.
LIGHT: "부드러운 오후빛" means soft afternoon window light; "맑은 아침빛" means clear morning window light; "흐린 날 창가빛" means overcast window light.

[Missing inputs and finish]
An optional input line removed from this prompt is absent. Do not print its key, invent a substitute caption, ask for it or reserve an empty panel. Choose a fitting simple visual only where the fixed design explicitly permits an automatic default. Selected values alter content only; retain this card's single style and one composition. Every supplied visible string stays verbatim in its original script and currency, without translation. Ordinary automatic lettering, if explicitly allowed above, is Korean; internal English keys and button names are never captions.
Use the stated aspect ratio, adapting one coherent layout rather than stretching food or letters. Text-bearing posters keep important lettering within the central 16–83% of image height and 5–95% of width; extend food-related ornament, background, shadows or texture to the trim so these insets do not create empty bands. Keep all price digits and ingredient labels unobstructed. Text-free photographs fill the canvas naturally with their scene. No frame, phone, wall mockup, watermark or extra results.
No uploaded photo is needed: create a fictional food scene from these inputs. If a reference photo is attached, use it only for the stated food's visible shape and materials within this same drawing or photographic medium, without adding absent products or claiming exact portion preservation. Finish one image even when no photo is attached.

[Final output format]
Output size 1080x1350 pixels, 4:5 portrait, Instagram standard.
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.