

{ "prompt": { "aspect_ratio": "9:16", "style": "vintage European café oil painting, expressive brushwork, mid-century editorial artwork", "subject": { "character": "stylish young European woman with shoulder-length wavy auburn hair", "expression": "calm, confident, slightly playful gaze toward the viewer", "pose": "seated sideways at a small café table, one arm resting on the chair back while the other lightly holds a coffee cup", "details": "subtle makeup, berry-red lipstick, small gold earrings" }, "outfit": { "top": "deep coral-red short-sleeve blouse with a relaxed neckline", "style": "chic 1960s-inspired European fashion" }, "composition": { "framing": "medium-wide portrait", "camera_angle": "slightly elevated three-quarter angle", "subject_position": "slightly left of center", "foreground": "round café table with coffee, small glass and scattered objects" }, "background": { "setting": "charming old European café interior", "design": "large abstract geometric wall shapes mixed with subtle architectural details", "colors": ["teal", "coral", "cream", "burnt orange"] }, "props": [ "ceramic espresso cup", "small glass bottle", "vintage café chair", "folded napkin" ], "color_palette": "teal, coral red, cream, burnt orange and warm brown", "texture": "thick imperfect oil brushstrokes, visible canvas grain, slightly weathered painted surface", "lighting": "warm afternoon window light with soft natural shadows", "mood": "stylish, relaxed, nostalgic European café atmosphere", "negative_prompt": "exact recreation of reference, same pose, same character, same outfit, same composition, photorealistic, 3D render, CGI, text, logo, watermark" } }
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: 899:1600 · Oil Painting · Vintage · Portrait. 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.