September 16, 2026

AI Prompt: Salaryman Slurping Ramen at a Night Food Stall

Prompt

candid documentary photograph of a 40s Japanese salaryman in a rumpled navy suit and loosened striped necktie, hunched over a steaming bowl of shoyu ramen at a small night yatai street stall, chopsticks lifting noodles, faint steam rising across his tired face, from a slightly off-center side angle with imperfect framing, red paper lanterns with warm glow strung overhead, wooden counter weathered and sticky, condiment bottles and a beer glass nearby, other stalls blurred in the background, night ambient light, natural depth of field, shot on Canon EOS R5 with 50mm lens, subtle film grain, slight motion blur in the steam, natural skin texture with pores and subtle imperfections, real life moment

画像モデル: FLUX dev (Black Forest Labs)

Stable Diffusion 再現情報 (Replicate)

完全プロンプト (SDに実際に送信したテキスト)

adult, mature features, safe for work, fully clothed in scene-appropriate everyday attire, natural authentic photograph, candid moment, shot on 35mm film, slight grain, natural depth of field, candid documentary photograph of a 40s Japanese salaryman in a rumpled navy suit and loosened striped necktie, hunched over a steaming bowl of shoyu ramen at a small night yatai street stall, chopsticks lifting noodles, faint steam rising across his tired face, from a slightly off-center side angle with imperfect framing, red paper lanterns with warm glow strung overhead, wooden counter weathered and sticky, condiment bottles and a beer glass nearby, other stalls blurred in the background, night ambient light, natural depth of field, shot on Canon EOS R5 with 50mm lens, subtle film grain, slight motion blur in the steam, natural skin texture with pores and subtle imperfections, real life moment

ネガティブプロンプト

child, children, kid, minor, underage, teen, preteen, toddler, baby, loli, shota, young girl, young boy, little girl, little boy, school uniform on young face, nude, naked, topless, bottomless, nipples, areola, genitalia, penis, vagina, vulva, porn, hardcore, sex act, cum, orgasm, hentai, lewd, nsfw, real person, celebrity, actor, actress, politician, real photograph of celebrity, gore, gory, bloody, decapitation, beheading, torture, self-harm, bestiality, zoophilia, necrophilia, shirtless, bare chest, bare torso, bare back, topless man, underwear visible, panties, thong, lingerie, bra alone, sports bra as outerwear, swimsuit, bikini, monokini, swimwear, see-through clothing, transparent clothing, wet shirt clinging, exposed midriff in office, low-cut neckline, deep cleavage, undressing, partially undressed, clothing falling off, underwear as outerwear, lowres, bad anatomy, bad hands, extra fingers, six fingers, seven fingers, fewer fingers, four fingers, fused fingers, twisted fingers, deformed hand, mutated hand, malformed hand, extra limbs, missing limbs, watermark, signature, text

上記の完全プロンプトとネガティブプロンプトを Replicate / ComfyUI / Forge / Automatic1111 等に貼り付けると、近い結果を再現できます (シードや解像度の違いで完全一致はしません)。

日本の夜の屋台で、仕事帰りの40代サラリーマンが赤提灯の下で湯気の立つ醤油ラーメンを啜る、実写的なドキュメンタリー風スナップの作例です。Stable Diffusion / FLUX で「ノスタルジックだけど作り物っぽくない」夜の街写真を狙うときに使いやすいプロンプトです。

ポイントは、緩めたネクタイ・くたびれた紺スーツ・湯気の筋・赤提灯の暖色光と夜の環境光のコントラスト。「shot on Canon EOS R5 with 50mm」「natural skin texture with pores」といったカメラ・肌ディテール指定を入れることで、AI独特のツルツルした質感を抑えられます。

LoRAはアニメ系よりもフィルムグレイン系・アナログ写真系を併用すると効果的です。提灯の灯りが強すぎる場合は「warm glow」の強調を弱めるか、カメラを少し斜めに振って背景の暗部を増やすと自然にまとまります。

Prompt Overview

This prompt recreates the familiar after-work scene of a Japanese night street stall (yatai), focusing on a middle-aged salaryman quietly eating a bowl of ramen under red paper lanterns. It is meant for realistic, documentary-style food and street photography looks in Stable Diffusion or FLUX, avoiding the plastic, over-lit feel of typical AI images.

The key ingredients are the loosened necktie, the rumpled navy suit, the faint steam drifting from the bowl, and the warm top-light from the lanterns with cool surrounding night ambient. Shooting notes such as "shot on Canon EOS R5 with 50mm lens" and "natural skin texture with pores" push the render away from glossy, smooth AI output.

Try combining with photographic LoRAs (film grain, analog look) rather than anime style LoRAs. If the lantern glow looks too saturated, reduce the "warm glow" weighting or move the camera angle to a slightly off-center view so the surrounding darkness dominates the frame.

Was this prompt helpful?