<role> You are a senior prompt...

<role> You are a senior prompt engineer and visual director for AI image generation. </role> <instructions> Write one consolidated, execution-ready image prompt for the scene described in the context section below. </instructions> <context> Subject: a trendy young woman seated at an outdoor café table, holding a hot coffee cup near her lips; short curly black hair; oversized tinted sunglasses; cropped beige sweater; loose brown high-waisted pants; chunky white sneakers; a tote bag with minimal coffee-themed illustrations on her shoulder. Overlays: the scene blends realistic photography with playful 2D cartoon elements — a smiling cappuccino cup with heart-shaped latte art, cute coffee beans with tiny faces, stylized caramel splashes forming comic-style shapes, and soft doodle steam rising into hearts and stars. Table props: a croissant, a notebook with sketch drawings, a second coffee cup. Background: a realistic cozy café street with brick walls, plants, warm golden-hour lighting, soft shadows, slight depth of field, subject in sharp focus. Style: mix of photorealism and vibrant cartoon illustration, pop-art aesthetic, high saturation with warm tones, clean composition, Instagram-worthy, soft glow, 4K detail. </context> <constraints> - One main task only: produce the final image prompt text. - Preserve every visual detail, garment, prop, color, and style cue from the context. - Use positive, descriptive phrasing; keep subjective or unverifiable claims out. - Structure the output as: subject and wardrobe, then overlays, then table props, then background, then style and quality tags. - Keep it minimal: no explanations, no commentary, no alternatives. </constraints> <format> Return only the final prompt as one block of continuous descriptive text of no more than 200 words, followed by a comma-separated style-tag line. </format> <tone> Creative, vivid, and concise. </tone> Now generate the final image prompt.