August 31, 2026

Witch Reading Spellbook in Castle Library AI Image Prompt

Prompt

candid documentary photograph of a mature witch in her 40s sitting at an ancient oak desk in a castle library, wearing a deep forest green velvet robe with embroidered silver trim and a simple leather belt, reading a large weathered spellbook bound in worn leather, her hands gently touching the yellowed parchment pages, thin wax candles casting warm flickering light across the room, towering bookshelves filled with ancient tomes fading into shadow, a small brass telescope on the desk, dust motes floating in candlelight, natural skin texture with visible pores and fine lines, side profile view of her face, soft ambient candlelight, subtle film grain, shot on 35mm film, natural depth of field, imperfect framing, shelves of old books in soft focus background, a raven perched on a wooden book stand watching her

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, wearing mythical or fantasy attire suited to the scene, anatomically coherent single-creature design, detailed hands with five fingers, natural authentic photograph, candid moment, shot on 35mm film, slight grain, natural depth of field, candid documentary photograph of a mature witch in her 40s sitting at an ancient oak desk in a castle library, wearing a deep forest green velvet robe with embroidered silver trim and a simple leather belt, reading a large weathered spellbook bound in worn leather, her hands gently touching the yellowed parchment pages, thin wax candles casting warm flickering light across the room, towering bookshelves filled with ancient tomes fading into shadow, a small brass telescope on the desk, dust motes floating in candlelight, natural skin texture with visible pores and fine lines, side profile view of her face, soft ambient candlelight, subtle film grain, shot on 35mm film, natural depth of field, imperfect framing, shelves of old books in soft focus background, a raven perched on a wooden book stand watching her

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, modern bikini, modern swimsuit, modern lingerie, panties, thong, sports bra, shirtless modern man, office worker shirtless, human legs on mermaid, legs and fish tail together, two tails, dragon tail on mermaid, lizard tail on mermaid, reptile tail on mermaid, scales on human legs, torso to tail seam mid-thigh, mermaid with knees, mermaid with feet, 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、夜の古い図書室の静かな雰囲気に焦点を当てています。温かいろうそくの光、そびえ立つ本棚、魔女の集中した姿勢が組み合わさることで、親密な読書と神秘性が感じられるシーンを創り出します。細部まで描写されたベルベットのローブや、望遠鏡・カラスといった小道具によって、この画像は具体的で生活感のあるファンタジーの世界に根ざしたものになっています。

スタイル面では、自然主義的でドキュメンタリー風の美学を採用しています。成熟した被写体を指定し、「率直なドキュメンタリー写真」「横顔」といった用語を使い、自然な肌の質感やフィルムグレインなどのディテールを含めることで、磨き上げられたイラストというよりは、映画のセットで切り取られた一瞬のように感じられる画像を生成するようモデルに促しています。これにより、AIファンタジーアートにありがちな、過度に滑らかで一般的な見た目を避けることができます。

この被写体でより良い結果を得るには、歴史ファンタジーのキャラクターやルネサンス期の肖像画で学習されたLoRAが効果的です。『Mature Female』や『Witch』のLoRA強度を0.6〜0.8に調整すると、被写体の一貫性を保つのに役立ち、『Candlelight』や『Chiaroscuro』のLoRAを追加することで、劇的な照明をさらに強調できます。机の上の小道具を変えて、よりミニマルな構図にするために望遠鏡を外したり、別のストーリー性を出すために湯気の立つカップを加えたりといった実験をお勧めします。

Prompt Overview

The imagery in this prompt focuses on the atmosphere of a quiet, ancient library at night. The combination of warm candlelight, towering bookshelves, and the witch's focused pose creates a sense of intimate study and mystery. The careful description of the figure's clothing—a detailed velvet robe—and the setting, including the telescope and raven, helps to ground the image in a specific, lived-in fantasy world.

Style-wise, we lean into a naturalistic, documentary aesthetic. By specifying a mature subject, using terms like 'candid documentary photograph' and 'side profile view', and including details such as natural skin texture and film grain, we encourage the model to generate something that feels more like a captured moment from a film set than a polished illustration. This helps avoid the overly-smooth, generic look common in AI fantasy art.

For best results with the subject, a LoRA trained on historical fantasy characters or Renaissance-era portraiture could be effective. Adjusting the 'Mature Female' or 'Witch' LoRA strength between 0.6 and 0.8 should help maintain a cohesive subject, while a 'Candlelight' or 'Chiaroscuro' LoRA can further emphasize the dramatic lighting. We suggest experimenting with the desk props, such as removing the telescope for a more minimalist composition or adding a steaming cup for a different storytelling cue.

Was this prompt helpful?