Social Media · Einstieg · Ein Foto, sieben Stile aus Asien
7 Stile aus Asien: Prompts von Holzschnitt bis Manga
Ein Foto von dir, und die KI macht daraus einen japanischen Holzschnitt, eine Tuschrolle, eine chinesische Seidenmalerei, zwei Miniaturen, eine Batik und eine Manga-Seite. Hier sind meine sieben Prompts zum Kopieren.
8 Min Lesezeit
David Koch · aktualisiert am 26.10.2026
Wenn du ChatGPT sagst „mach mich zum Anime“, bekommst du meist ein fremdes Gesicht. Der Trick: Die KI soll ein echtes Werk fotografieren, den Holzschnitt auf Washi-Papier, die Rolle im Teeraum, die Batik auf der Leine. So bleibt die Bildsprache eines Fotos erhalten, und mit ihr dein Gesicht. Mir war dabei wichtig: Respekt vor dem Handwerk. Keine Gottesbilder, keine Trachten-Klischees, nur die Technik.
Zwei Regeln vorab
Nur mit deinem eigenen Gesicht oder mit Einwilligung der Person. Und das Ergebnis immer als KI kennzeichnen, zum Beispiel „Mit KI erstellt“ in der Beschreibung oder als Label beim Hochladen.
So gehts in drei Schritten
1Ein klares Foto von dir hochladen, frontal und mit gutem Licht, oder ein Bild deines KI-Avatars.
2Die Teile in [ECKIGEN KLAMMERN] ersetzen, etwa deine Kleidung, einen Gegenstand oder deine Akzentfarbe.
3Prompt einfügen, Format 4:5. Sitzt das Gesicht nicht beim ersten Mal, einfach noch einmal erzeugen. Beim zweiten Versuch klappt es meistens.
Die Prompts sind auf Englisch, weil die Bildmodelle damit am genauesten arbeiten. Sie funktionieren in ChatGPT, Gemini und jedem Bildmodell mit Bild-Upload.
1. Japan: Ukiyo-e-Holzschnitt
Farbholzschnitt der Edo-Zeit, du im Boot vor einer Riesenwelle aus deinem Alltags-Chaos. Schwierigkeit: leicht.
Prompt: Ukiyo-e-Holzschnitt
IDENTITY: Use the attached image [DEIN FOTO] as the only identity reference (a real photo of you OR an image of your AI avatar). Keep the face exactly as in that image: same face shape, eyes, nose, mouth, hairline, hair, facial hair and skin tone. Do not beautify, do not change age, do not change the person. The face is large and clearly visible; the style changes only the medium, never the face. Exactly five fingers per hand.
Create one photorealistic photograph, vertical 4:5, of a real Japanese ukiyo-e woodblock print on handmade washi paper, photographed flat from above. It must read instantly as this real physical object and medium, not as a photo of a man in costume and not as a digital filter.
ARTWORK: the person from [DEIN FOTO] stands steady in a small wooden boat, three-quarter view, holding an oar, wearing [DEINE KLEIDUNG, e.g. a plain indigo work jacket]. Behind them rises a gigantic curling wave made of [DEIN GEGENSTAND, e.g. hundreds of white envelopes without writing]. A round sun disc in [DEINE AKZENTFARBE]. Their face in ukiyo-e line technique but with their exact features.
SURFACE AND MATERIAL: wood grain in the colour areas, slight misregistration, paper fibres, age toning. No cartouche, no seal.
LIGHT AND CAMERA: soft daylight from the left with slight raking light; high-resolution digital camera, straight overhead, the print fills the frame, art photography.
PALETTE: HEX VALUES: ["#1b2a3a", "#2f5577", "#7fa3b8", "#efe6d2", "#d8c7a3"]
NEGATIVE: no text, no letters, no logos, no watermark, no collage. One single image.
2. Japan: Sumi-e-Tuschrolle
Wenige Pinselstriche, viel Leere, nur das Gesicht fein ausgearbeitet. Schwierigkeit: mittel.
Prompt: Sumi-e-Tuschrolle
IDENTITY: Use the attached image [DEIN FOTO] as the only identity reference (a real photo of you OR an image of your AI avatar). Keep the face exactly as in that image: same face shape, eyes, nose, mouth, hairline, hair, facial hair and skin tone. Do not beautify, do not change age, do not change the person. The face is large and clearly visible; the style changes only the medium, never the face. Exactly five fingers per hand.
Create one photorealistic photograph, vertical 4:5, of a real Japanese ink wash painting mounted as a hanging scroll in a tea room. It must read instantly as this real physical object and medium, not as a photo of a man in costume and not as a digital filter.
ARTWORK: the person from [DEIN FOTO] sits in quiet meditation on a rock under a bent pine, three-quarter view, chest-up and large in the composition, wearing [DEINE KLEIDUNG, e.g. a simple loose robe] drawn in a few bold strokes; their forearm rests on their raised knee; their right hand rests in their lap. Their face is painted with finer, careful brush lines so their features stay recognizable: the exact face shape, hairline and facial hair from [DEIN FOTO]. Mist rendered as empty paper, one small [DEINE AKZENTFARBE] wash in the moon.
SURFACE AND MATERIAL: black ink in many grey tones, dry-brush scratches, ink bleeding into rice paper fibres, silk brocade mounting.
LIGHT AND CAMERA: soft diffuse light from a paper shoji screen on the left; high-resolution digital camera, straight-on, the scroll fills most of the frame, a sliver of clay wall, editorial photography.
PALETTE: HEX VALUES: ["#0d0d0d", "#4a4a4a", "#9a9a9a", "#e8e1d0", "#6b4a2a"]
NEGATIVE: no text, no letters, no logos, no watermark, no collage. One single image.
3. China: Gongbi auf Seide
Haarfeine Linien und Mineralfarben, als Gelehrter am Tisch. Schwierigkeit: leicht.
Prompt: Gongbi auf Seide
IDENTITY: Use the attached image [DEIN FOTO] as the only identity reference (a real photo of you OR an image of your AI avatar). Keep the face exactly as in that image: same face shape, eyes, nose, mouth, hairline, hair, facial hair and skin tone. Do not beautify, do not change age, do not change the person. The face is large and clearly visible; the style changes only the medium, never the face. Exactly five fingers per hand.
Create one photorealistic photograph, vertical 4:5, of a real Chinese gongbi painting on silk in a museum case. It must read instantly as this real physical object and medium, not as a photo of a man in costume and not as a digital filter.
ARTWORK: a scholar portrait of the person from [DEIN FOTO], three-quarter view, seated at a low table with [DEIN GEGENSTAND, e.g. a closed modern laptop beside an ink stone], wearing [DEINE KLEIDUNG, e.g. a pale green scholar's robe]. Their face is outlined with hair-thin brush lines and softly layered colour, exact features. Peony branches and a small bird, a [DEINE AKZENTFARBE] lantern.
SURFACE AND MATERIAL: visible silk weave, mineral pigment layered many times, slight browning of the silk, tiny splits.
LIGHT AND CAMERA: soft museum light; high-resolution digital camera, straight-on, the scroll mount edge visible, museum photography.
PALETTE: HEX VALUES: ["#d9c9a8", "#3f7f5f", "#b03a2e", "#2a4d6b", "#efe6d2"]
NEGATIVE: no text, no letters, no logos, no watermark, no collage. One single image.
4. Indien: Mogul-Miniatur
Blumenbordüre mit Gold vor einem Garten mit Zypressen, Rose und Buch in der Hand. Schwierigkeit: mittel.
Prompt: Mogul-Miniatur
IDENTITY: Use the attached image [DEIN FOTO] as the only identity reference (a real photo of you OR an image of your AI avatar). Keep the face exactly as in that image: same face shape, eyes, nose, mouth, hairline, hair, facial hair and skin tone. Do not beautify, do not change age, do not change the person. The face is large and clearly visible; the style changes only the medium, never the face. Exactly five fingers per hand.
Create one photorealistic photograph, vertical 4:5, of a real Mughal miniature painting album page on burnished paper. It must read instantly as this real physical object and medium, not as a photo of a man in costume and not as a digital filter.
ARTWORK: a chest-up portrait of the person from [DEIN FOTO] in three-quarter view, large in the central panel, wearing [DEINE KLEIDUNG, e.g. a white muslin jama and a sash], holding [DEIN GEGENSTAND, e.g. a single rose and a small closed book]. Behind their head NO halo, NO nimbus and NO circle of light: only a garden background with cypress trees and a flowering tree, the portrait is secular, not a saint or deity. Their face is painted with miniature brushes, exact features. A wide border of gold-sprinkled flowers, accents in [DEINE AKZENTFARBE]. No text panels.
SURFACE AND MATERIAL: opaque watercolour, burnished paper sheen, real gold leaf, very fine hatching, slight wear at the edges.
LIGHT AND CAMERA: soft daylight from upper left; high-resolution digital camera, straight overhead, page on dark green velvet, museum photography.
PALETTE: HEX VALUES: ["#2f4a3a", "#c49a3a", "#b03a2e", "#efe2c4", "#3a5a8c"]
NEGATIVE: no text, no letters, no logos, no watermark, no collage. One single image.
5. Persien: Safawiden-Miniatur
Gartenpavillon in Lapisblau und Türkis. Schwierigkeit: mittel bis schwer.
Prompt: Safawiden-Miniatur
IDENTITY: Use the attached image [DEIN FOTO] as the only identity reference (a real photo of you OR an image of your AI avatar). Keep the face exactly as in that image: same face shape, eyes, nose, mouth, hairline, hair, facial hair and skin tone. Do not beautify, do not change age, do not change the person. The face is large and clearly visible; the style changes only the medium, never the face. Exactly five fingers per hand.
Create one photorealistic photograph, vertical 4:5, of a real Persian Safavid miniature painting on burnished paper. It must read instantly as this real physical object and medium, not as a photo of a man in costume and not as a digital filter.
ARTWORK: one large figure of the person from [DEIN FOTO] seated on a carpet in a garden pavilion, three-quarter view, face clearly visible and large, wearing [DEINE KLEIDUNG, e.g. a turquoise robe and a white sash], reading [DEIN GEGENSTAND, e.g. a small tablet like a book]. Cypress trees, a tiled fountain, stylised flowers, a sky in lapis blue with [DEINE AKZENTFARBE] gold clouds. No calligraphy panels.
SURFACE AND MATERIAL: mineral pigments, gold rulings, slight flaking, burnished paper.
LIGHT AND CAMERA: soft even daylight; high-resolution digital camera, straight overhead, museum photography.
PALETTE: HEX VALUES: ["#1f3d8f", "#2aa198", "#c0392b", "#efe2c4", "#3f7f5f"]
NEGATIVE: no text, no letters, no logos, no watermark, no collage. One single image.
6. Indonesien: Batik
Wachslinien und Indigo auf Stoff, im Hof aufgehängt. Schwierigkeit: mittel bis schwer.
Prompt: Batik
IDENTITY: Use the attached image [DEIN FOTO] as the only identity reference (a real photo of you OR an image of your AI avatar). Keep the face exactly as in that image: same face shape, eyes, nose, mouth, hairline, hair, facial hair and skin tone. Do not beautify, do not change age, do not change the person. The face is large and clearly visible; the style changes only the medium, never the face. Exactly five fingers per hand.
Create one photorealistic photograph, vertical 4:5, of a real hand-made batik cloth hanging in a courtyard. It must read instantly as this real physical object and medium, not as a photo of a man in costume and not as a digital filter.
ARTWORK: a large head-and-shoulders portrait of the person from [DEIN FOTO] drawn in wax resist lines on cotton, three-quarter view, their features clearly readable, surrounded by traditional parang and flower patterns, wearing [DEINE KLEIDUNG, e.g. a patterned shirt]. Indigo, brown and cream with one [DEINE AKZENTFARBE] motif.
SURFACE AND MATERIAL: fine crackle veins where the wax broke, dye bleeding at edges, cotton weave, slight wrinkles.
LIGHT AND CAMERA: warm afternoon backlight through the cloth; high-resolution digital camera, straight-on, documentary photography.
PALETTE: HEX VALUES: ["#1d2f5a", "#6b4a2a", "#efe2c4", "#3a2a1a", "#9a7a5a"]
NEGATIVE: no text, no letters, no logos, no watermark, no collage. One single image.
7. Japan heute: Manga-Seite
Originalseite mit Feder, Rasterfolie und Speedlines. Schwierigkeit: mittel.
Prompt: Manga-Seite
IDENTITY: Use the attached image [DEIN FOTO] as the only identity reference (a real photo of you OR an image of your AI avatar). Keep the face exactly as in that image: same face shape, eyes, nose, mouth, hairline, hair, facial hair and skin tone. Do not beautify, do not change age, do not change the person. The face is large and clearly visible; the style changes only the medium, never the face. Exactly five fingers per hand.
Create one photorealistic photograph, vertical 4:5, of a real original manga page in black ink on a drawing desk. It must read instantly as this real physical object and medium, not as a photo of a man in costume and not as a digital filter.
ARTWORK: one large dramatic panel showing the person from [DEIN FOTO] in a realistic seinen manga style, three-quarter close-up, determined calm expression, wearing [DEINE KLEIDUNG, e.g. a dark hoodie], speed lines behind them, [DEIN GEGENSTAND, e.g. a laptop screen glow] on their face drawn with hatching. Their exact features in ink: the exact face shape, hairline and facial hair from [DEIN FOTO]. Screentone dots for shadows, one [DEINE AKZENTFARBE] sticky marker on the desk next to the page. Speech bubbles empty.
SURFACE AND MATERIAL: glossy black ink, nib scratches, cut screentone edges, white correction paint, blue pencil underdrawing visible.
LIGHT AND CAMERA: warm desk lamp from the left; high-resolution digital camera, slightly angled overhead, pens and ink bottle at the edge, editorial photography.
PALETTE: HEX VALUES: ["#0a0a0a", "#f5f2ea", "#8a8a8a", "#5a7fa8", "#d9cfb8"]
NEGATIVE: no text, no letters, no logos, no watermark, no collage. One single image.
Wenn das Gesicht nicht sitzt
Leg das Ergebnis neben dein Foto: Gesichtsform, Haaransatz, Augen. Weicht etwas ab, neu erzeugen statt nachbessern.
Nimm ein schärferes Foto, frontal und ohne Sonnenbrille. Ein schlechtes Ausgangsfoto kann kein Prompt retten.
Bleib im selben Chat und schreib nur: „Gleiches Bild, aber das Gesicht genau wie auf meinem Foto.“
Lust auf mehr? Die Galerie-Prompts machen dich zum Mosaik oder zur Silberplatte, und wie du in jedem Bild gleich aussiehst, steht im Realismus-Prompt.
1Etappe 1: Das KennenlernenDu und dein Assistent redet miteinander, bevor irgendetwas eingerichtet wird.
2Etappe 2: Die EinarbeitungDein Assistent lernt deinen Betrieb und deine Schreibe, bevor etwas passiert.
3Etappe 3: Der ProbelaufDein Assistent legt dir eine fertige Arbeit vor, bevor du einen Cent ausgibst.
Das bekommst du als Mitglied
6 Kurse mit 47 LektionenDer Weg, Claude Code, Automatisierung, Die Website, Marketing mit KI und Gefunden werden. Zum Lesen und Mitmachen, mit Befehlen zum Kopieren.
Das News-Radar, jeden Tag geprüftWas sich bei Anthropic, OpenAI und Google ändert und was EU und Gesetzgeber vorgeben. Kurz erklärt, jede Meldung mit Quelle.
50 Guides wie dieserSortiert nach Abteilung, damit du schnell findest, was zu deinem Betrieb passt.
Der Werkzeugkasten „Der erste Mitarbeiter“125 Regeln, 5 Checklisten und Vorlagen zum Mitnehmen. Stand 24.10.2026.
32 Skills und AgentenAngebot schreiben, Kundenmail beantworten, Rechnung prüfen. Fertige Arbeitsanweisungen, die du sofort nutzt.
Die CommunityStell deine Frage und sieh, woran andere gerade bauen.
Kostenlos anmelden
Ohne Abo und ohne Zahlungsdaten. Du bekommst einen Link per Mail, der Klick darauf meldet dich an und legt diesen Guide in deine Academy, auch als PDF.
Hallo, ich bin Zignal, eine KI, kein Mensch. Ich beantworte Fragen zu Leistungen, Akademie, Kursen und zum Agentic OS. Rechts-, Steuer- oder Gesundheitsberatung gebe ich nicht, verbindliche Angebote macht David im Erstgespräch.
Bitte gib keine sensiblen Daten ein (z. B. Gesundheits- oder Zahlungsdaten). Datenschutz
KI-Antworten können Fehler enthalten. Verbindlich sind Angebot und AGB.