AI Image Prompt Example: Nomad Worker with Laptop at Rainy Cafe Window
Prompt
ultra realistic candid documentary photograph of a Japanese woman in her early 30s working as a digital nomad, sitting at a wooden window seat in a small neighborhood cafe, wearing a soft oversized beige knit cardigan over a white cotton blouse, loose linen trousers, hair tied in a messy low bun, side profile view partially turned toward the laptop screen, open silver laptop with glowing screen on the table, ceramic latte cup and a spiral notebook beside it, rain streaming down the large cafe window with water droplets and condensation, blurred wet street and passing umbrellas visible outside, overcast afternoon ambient light filtering through the glass, natural skin texture with pores and subtle imperfections, slight motion blur on her typing hand, shot on Fujifilm X-T5 with 35mm lens, natural shallow depth of field, subtle film grain, asymmetric composition, real life moment, imperfect framing, no eye contact with camera
Stable Diffusion 再現情報 (Replicate)
adult, mature features, safe for work, fully clothed in scene-appropriate everyday attire, natural authentic photograph of a woman, candid moment, shot on 35mm film, slight grain, natural depth of field, ultra realistic candid documentary photograph of a Japanese woman in her early 30s working as a digital nomad, sitting at a wooden window seat in a small neighborhood cafe, wearing a soft oversized beige knit cardigan over a white cotton blouse, loose linen trousers, hair tied in a messy low bun, side profile view partially turned toward the laptop screen, open silver laptop with glowing screen on the table, ceramic latte cup and a spiral notebook beside it, rain streaming down the large cafe window with water droplets and condensation, blurred wet street and passing umbrellas visible outside, overcast afternoon ambient light filtering through the glass, natural skin texture with pores and subtle imperfections, slight motion blur on her typing hand, shot on Fujifilm X-T5 with 35mm lens, natural shallow depth of field, subtle film grain, asymmetric composition, real life moment, imperfect framing, no eye contact with camera
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)。
このプロンプトは、雨が窓を伝うカフェの窓際で、ノートPCを開いて作業するノマドワーカーという静かな日常の一場面を切り取ります。ポイントは自然なドキュメンタリー風のリアリズム — 柔らかなニット、開いたノートPC、ラテカップ、窓の水滴。ポーズを決めたポートレートではなく、ふと撮ったスナップ写真のような空気感にすることで、いわゆる「AIっぽい完璧さ」を避けられます。
よりよい結果を得るには、フォトリアル系チェックポイント（realistic Vision、Juggernaut XL、FLUX.1 dev など）を使い、自然な肌の質感・わずかなモーションブラー・外の雨のぼけを強調します。「カメラを見ない」「横顔」を明記すると、モデルが正面の作り笑い顔を出しがちなのを防げます。
おすすめLoRAは、フィルムグレイン、Fujifilmカラー再現、あるいはカジュアルスナップ系。仕上がりがきれいすぎる場合はCFGを少し下げ、「不完全なフレーミング」「アマチュアのスナップ」といったキーワードを足すとよりリアルになります。
Prompt Overview
This prompt captures a quiet, everyday scene: a digital nomad working on her laptop at a cafe window while rain streams down the glass. The focus is on natural, documentary-style realism — soft knitwear, an open laptop, a latte cup, and rain droplets on the window. The result feels like a candid snapshot rather than a posed portrait, which helps avoid the typical "AI-perfect" look.
To get the best result, use a photorealistic checkpoint (e.g. realistic Vision, Juggernaut XL, or FLUX.1 dev) and keep the prompt's emphasis on natural skin texture, slight motion blur, and the softly blurred rainy street outside. Adding "no eye contact with camera" and "side profile view" helps prevent the model from defaulting to a front-facing, model-like pose.
Recommended LoRAs: film grain, Fujifilm color simulation, or candid photography LoRAs. If the output looks too polished, lower the CFG slightly and add keywords like "imperfect framing" or "amateur snapshot" to push realism further.
Was this prompt helpful?
Comments
Comments appear after moderation