Witch in Candlelit Library — AI Portrait Prompt Example
✨ このプロンプトを自分の好みでカスタマイズして生成
下のフォームから日本語で指示するだけ。最初の数回は完全無料でお試しいただけます。

上の画像をベースに、あなた専用の画像をAIが生成します。下のチップから選ぶか、自由に文章を入力して試せます ↓
Prompt
documentary photograph of a young witch in her late 20s with pale skin and long dark hair, sitting at an oak table in a medieval castle library, wearing a deep forest-green velvet robe with silver embroidery, reading an ancient grimoire with yellowed pages, candlelight casting warm amber shadows on her face and the book, dust motes floating in the dim light, shelves of leather-bound books in background, stone walls with faded tapestries, natural ambient light from a small stained-glass window, shot on Fujifilm X-T5 with 35mm lens, subtle film grain, soft depth of field, imperfect framing, asymmetric composition, no visible face, from behind, side profile view, books and candle in foreground, natural skin texture with pores and subtle imperfections
Stable Diffusion 再現情報 (Replicate)
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, documentary photograph of a young witch in her late 20s with pale skin and long dark hair, sitting at an oak table in a medieval castle library, wearing a deep forest-green velvet robe with silver embroidery, reading an ancient grimoire with yellowed pages, candlelight casting warm amber shadows on her face and the book, dust motes floating in the dim light, shelves of leather-bound books in background, stone walls with faded tapestries, natural ambient light from a small stained-glass window, shot on Fujifilm X-T5 with 35mm lens, subtle film grain, soft depth of field, imperfect framing, asymmetric composition, no visible face, from behind, side profile view, books and candle in foreground, natural skin texture with pores and subtle imperfections
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魔女という静謐で映画的なファンタジーポートレートを生成するために設計されています。キャンドルとステンドグラスによる自然光、ベルベットや革の本、石壁などの豊かなテクスチャ、そして内省的なムードが強調されています。「ドキュメンタリー写真」「フィルムカメラ」の指定により、ありがちなAIのツルっとした質感を抑え、背中越しの横顔という構図が神秘性とリアリティを加えています。
雰囲気をさらに高めるには、中世のインテリアや大気照明用のLoRAの使用をおすすめします。より幻想的な見た目を求めるなら、「妖精の光」や「ウィル・オー・ザ・ウィスプ」を追加しても良いでしょう。プロンプトは意図的に完全な対称性や無機質な照明を避けており、歴史ファンタジーの中の一瞬を切り取ったような、自然な印象の画像が得られます。
Prompt Overview
This prompt is designed to generate a serene, cinematic fantasy portrait of a witch reading a magic book in an old castle library. It emphasizes candlelight and natural light from stained glass, rich textures such as velvet, leather-bound books, and stone walls, along with an introspective mood. By specifying "documentary photography" and "film camera," it reduces the typical AI-smooth texture, and the composition of a side profile from behind adds mystery and realism.
To further enhance the atmosphere, we recommend using LoRAs for medieval interiors and atmospheric lighting. For a more fantastical look, you can add "fairy lights" or "will-o'-the-wisp." The prompt intentionally avoids perfect symmetry and sterile lighting, resulting in a natural-looking image that feels like a captured moment in historical fantasy.
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