GifproGifpro

Witch Reading a Spellbook in a Castle Library - AI Image Prompt Examples

Witch Reading a Spellbook in a Castle Library - AI Image Prompt Examples
P

Prompt

candid documentary photograph of a mature female witch in her 40s with silver-streaked dark hair in a loose bun, wearing a deep forest green velvet robe with silver embroidery and a leather belt with small pouches, sitting at a heavy oak table in an ancient castle library, reading a large leather-bound spellbook with yellowed pages, surrounded by towering bookshelves filled with antique books, warm flickering candlelight from brass candlesticks, dust particles in the air, stone walls with shadows, natural skin texture with fine wrinkles around the eyes, shot on Canon EOS R5 with 35mm f/1.4 lens, natural depth of field, subtle film grain, imperfect framing, asymmetric composition, side profile view, facing sideways, three-quarter angle, concentrated expression, slightly furrowed brows, hand touching old paper, medieval fantasy atmosphere, no modern elements
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, fantasy art, mythical creature, ethereal atmosphere, detailed lighting, candid documentary photograph of a mature female witch in her 40s with silver-streaked dark hair in a loose bun, wearing a deep forest green velvet robe with silver embroidery and a leather belt with small pouches, sitting at a heavy oak table in an ancient castle library, reading a large leather-bound spellbook with yellowed pages, surrounded by towering bookshelves filled with antique books, warm flickering candlelight from brass candlesticks, dust particles in the air, stone walls with shadows, natural skin texture with fine wrinkles around the eyes, shot on Canon EOS R5 with 35mm f/1.4 lens, natural depth of field, subtle film grain, imperfect framing, asymmetric composition, side profile view, facing sideways, three-quarter angle, concentrated expression, slightly furrowed brows, hand touching old paper, medieval fantasy atmosphere, no modern elements
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、古城の図書室で魔法書を読む成熟した魔女を描く、中世ファンタジーの雰囲気を重視した作例です。蝋燭の暖かな灯りと古書・石壁の質感表現がポイントで、自然な肌のきめや実用的な服装のディテール、ドキュメンタリー風の撮影スタイルを組み合わせることで、AI生成特有の過度に磨かれたファンタジーイラスト的な仕上がりを避けています。

より良い結果を得るには、中世・ルネサンス絵画の美学に特化したLoRAを使用すると、蝋燭の灯りの表現や布地の質感が向上します。顔を横に向けた構図と本に集中する表情が思索的なムードを生み出し、物語の挿絵や装丁デザインなどへの応用に適しています。

Prompt Overview

This prompt focuses on creating an atmospheric medieval fantasy scene centered on a mature witch character, emphasizing the warm candlelight against ancient books and stone textures. The realistic rendering of skin texture, practical clothing details, and documentary-style shooting technique help the image avoid the typical over-polished AI fantasy look.

For best results, consider using a LoRA trained on medieval or renaissance oil paintings to enhance the candlelight atmosphere and fabric rendering, while keeping the prompt's emphasis on natural imperfections and asymmetrical composition. The side profile view with the subject's attention on the book creates a contemplative mood suitable for storytelling or book cover applications.

Was this prompt helpful?

Comments

Comments appear after moderation

この記事が役に立ったら投げ銭で応援

Apple Pay / Google Pay / カード (Visa/Mastercard/JCB/Amex) / Link / Alipay / WeChat Pay 対応 · Stripeで安全に決済

開発者が選ぶ最強ツール集

運営者が毎日使っているツール・ガジェット 6選

見る
Homeヘルプ