



Anime or game adult female character × Ottoman tughra-style calligraphy × character form transfiguration × cobalt blue and gold on paper For each image, randomly select a different anime or game adult female character, extract her clearly recognizable hairstyle, clothing, accessories, and representative motifs, and naturally integrate strands of hair, sleeves, skirt hems, or flowing ribbons into the tughra strokes to form a complete character-themed emblem. Preserve the tughra skeleton: interwoven calligraphic strokes at the bottom, three parallel tall verticals, two tiers of nested large oval loops on the left, and a slender horizontal stroke extending to the right. The character's form and the strokes connect with each other, the overall silhouette is clear, and the figure remains clearly recognizable. Thick cobalt blue strokes are outlined with gold lines, and some areas within the strokes and loops are adorned with fine dense patterns related to the character. The figure and ornaments use a unified Ottoman court miniature painting technique, with fine line outlines and flat color application, forming a clear contrast between thick strokes and fine patterns. The character's signature colors may be incorporated in moderation. Off-white paper ground, with the flat texture of ink, opaque watercolor, and gold. The emblem is fully visible, with large areas of negative space around it, flat and front-facing. For each image, independently draw the character and related ornaments, varying the way the character's form is integrated, the emblem's proportions, and its position in the composition; characters and main combinations do not repeat within the same batch. n=10, continuously generate 10 independent single images, generating 1 image each time, no collage, no grid or split-screen. Vertical 9:16. Bottom-left signature: a solid dark blue dot first, followed by white handwritten text "DeepBlue".
This image was generated with GPT Image 2.5 by OpenAI. The prompt on this page is the exact text used to create it.
The example was generated with GPT Image 2.5 using: 941:1672 · Digital Art · Anime · Fantasy. Reusing these settings gives the closest match.
Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.
Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.