wowprompt

1990s film still in a velvet bandhgala down a hotel corridor

A frame that looks lifted from a 1990s wedding film: a midnight-blue velvet bandhgala, a candid laugh and a marble hotel corridor glowing with brass sconces. Works with your own photo.

A young man in a midnight-blue velvet bandhgala laughing mid-step in a marble hotel corridor lit by warm brass wall lamps
The output this prompt produced, unedited.
Works with or without your photo.

Optional. Attach a clear, front-facing photo to keep your own face. Without one, the prompt creates an original person.

The prompt

Subject

A young man laughs mid-step down a grand hotel corridor in a velvet bandhgala, caught like a still from a 1990s wedding film.

Identity

With a photo attached: the person in the photo is the subject. Keep their face exactly as it is, with bone structure, eye shape and spacing, nose, lips, jawline, hairline, skin tone and apparent age all unchanged. Only the clothing, pose, setting and light come from this prompt.

Pose

Turning back toward someone off frame, head tipped in a candid laugh, one hand fixing a cufflink.

Wardrobe

A midnight-blue velvet bandhgala with antique brass buttons, a white silk pocket square, ivory churidar, black mojaris and a gold signet ring.

Setting

A long hotel corridor of cream marble, brass-framed doors and a patterned runner carpet, a bouquet of tuberoses on a side table.

Light

Warm brass wall sconces down both sides, a soft key on the face, polished reflections in the marble.

Camera

A 35mm lens at f/2, framed from the knees up, the corridor receding behind.

Finish

A warm cinematic grade with rich blacks, the slight softness and fine grain of 1990s film stock, real skin with texture and pores.

Negative prompt

modern phone, LED strips, contemporary slim suit, digital sharpness, flat lighting, airbrushed skin, plastic skin, waxy face, changed face, distorted hands, extra fingers, text, logo, watermark, signature

1990sbandhgalafilm stillretro portraitmens ethnic wearhotel corridor

How to run this

Copy the prompt and paste it into GPT Image, then set the aspect ratio to 4:5. Upload your reference photo before pasting, not after: a model that has already started without it will invent a face instead of keeping yours.

The prompt is written in Markdown with each part under its own heading, which is what the copy action hands over. Change one section at a time, keeping the rest intact, so you can tell which change did the work.

Related prompts

All image