✍️ Schreiben & Copywriting
Image Editor
Beispiel-Ausgaben
So antworten ChatGPT, Claude und Gemini typischerweise auf diesen Prompt:
I'll help you create a comprehensive web-based image editor! Here's a modular implementation starting with the HTML structure featuring a toolbar, canvas preview area, and side panels for adjustments. The JavaScript will handle Canvas API operations for filters (brightness, contrast, saturation via pixel manipulation), cropping with draggable selection boxes, text overlays using fillText(), and a command pattern for undo/redo. The CSS will use flexbox for responsive layouts and CSS Grid for tool panels.
I can help you build this image editor, though I should note that implementing all these features robustly is quite complex. I'd recommend starting with core canvas manipulation and basic adjustments, then layering in features incrementally. For filters, you'll want to work with ImageData pixel arrays; for layers, consider maintaining separate canvas elements with composite operations. The undo/redo system will need careful state management—storing full image copies can be memory-intensive, so consider implementing a command pattern instead.
Here's a structured approach for building your image editor: Use the HTML5 Canvas API's getImageData() and putImageData() for pixel-level adjustments. Implement filters using convolution matrices (for sharpness) and HSL color space transformations (for saturation). For layers, stack multiple canvas elements with CSS positioning and use globalCompositeOperation for blending modes. The Mozilla Developer Network documents Canvas methods extensively, and libraries like Fabric.js can simplify complex operations if needed.
So nutzt du diesen Prompt
Kopiere den Prompt oben oder klicke einen "Öffnen in"-Button um ihn direkt in deiner bevorzugten KI zu starten. Du kannst den Text dann an deinen Anwendungsfall anpassen — z.B. Platzhalter wie [dein Thema] durch echten Kontext ersetzen.
Welches KI-Modell funktioniert am besten
Claude gilt 2026 als stärkstes Writing-Modell — nuancierter Voice, besseres Gehör für Rhythmus, weniger Klischees. ChatGPT ist schneller und flexibler im Format. Gemini ist nützlich wenn du aus langen Referenz-Dokumenten ziehen musst.
Diesen Prompt anpassen
Spezifiziere Zielgruppe, Wortanzahl und Tonfall explizit. Gute Ergänzungen: "Schreibe im Stil von [Autor oder Publikation]", "Vermeide diese Wörter: [Liste]", "Leser ist [spezifisches Profil]". Füge Referenz-Material oder Brand-Voice-Guide nach dem Prompt ein.
Typische Anwendungsfälle
- Aus grobem Outline einen polierten Blog-Post machen
- Bulk-Content umschreiben (Produktbeschreibungen, Email-Kampagnen)
- Social-Media-Threads im Voice eines Founders ghostwriten
- Langform-Entwürfe auf Flow und Klarheit lektorieren
- Pressemitteilungen aus Fakten-Brief entwerfen
Variationen
Passe den Tonfall an (lockerer, technischer), ändere das Ausgabeformat (Aufzählungen vs. Absätze) oder füge Einschränkungen hinzu (Wortlimits, Zielgruppe).