

Create a beautiful, nostalgic hand-drawn editorial illustration combining two cozy everyday scenes in a consistent vintage sketchbook style. In the first scene, a young woman with dark brown hair in a messy bun and black glasses, wearing a black outfit, arranges colorful pink roses, coral flowers, tiny white blossoms, and lush greenery inside a charming flower shop, holding a large bouquet wrapped in brown kraft paper. Surround her with potted plants, tropical leaves, blooming flowers, and tall vintage windows. In the second scene, a young couple sits closely together on stone steps along a charming European city street. The man wears a navy baseball cap, headphones, a gray hoodie, a long black coat, blue jeans, and sneakers, while the woman wears a black coat, a soft blue scarf, cream trousers, black sneakers, and carries a brown leather shoulder bag. They share a quiet, affectionate moment surrounded by elegant old buildings, a cozy café, glowing street lamps, bicycles, leafy trees, and pedestrians. Use a harmonious palette of warm cream, olive green, mustard yellow, dusty blue, navy, coral, and soft pink. Add textured colored-pencil strokes, delicate ink outlines, subtle watercolor shading, vintage paper grain, charming hand-drawn accents, and warm natural lighting. Whimsical slice-of-life storytelling, cozy nostalgic atmosphere, artistic imperfections, highly detailed illustration, premium handmade sketchbook aesthetic, consistent art style across both scenes, vertical composition, no photorealism.
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: 3:4 · Digital Art · Vintage · Sketch. 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.