wowprompt

Dhunuchi smoke portrait in a maroon Baluchari saree

A moody Durga Puja season portrait: seated in a maroon Baluchari silk saree with a smoking clay dhunuchi at her feet, incense haze curling through a single shaft of light. Works with your own photo.

A young woman in a maroon silk saree seated on a low stool, clay incense burner smoking beside her, haze drifting across a textured plaster wall
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

Must hold

One person. One clay dhunuchi with glowing coconut husk and incense smoke. Her face stays sharp and clear of the smoke. Two hands, five fingers each, resting naturally. No words.

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.

The picture

She sits on a low wooden stool, forearms resting on her knees, hands loosely joined, a calm steady gaze into the lens. A clay dhunuchi on the floor beside her sends thick white incense smoke curling up past her shoulder. She wears a maroon Baluchari silk saree with its woven narrative pallu in pale gold over one arm, a maroon blouse, a shankha-and-pola pair on one wrist, gold jhumkas and a small red bindi. Behind her, a warm grey textured plaster wall, the smoke catching light against it.

Technical

A full-frame camera with an 85mm lens at f/1.8, framed from the knees up. A soft key from one side, a thin rim from behind picking out the smoke, falloff into deep shadow. Warm cinematic grade with rich blacks, real skin with texture and pores.

Negative prompt

smoke across the face, fire, flat lighting, crowd, printed saree, airbrushed skin, plastic skin, waxy face, changed face, distorted hands, extra fingers, text, logo, watermark, signature

durga pujadhunuchibaluchari sareesaree portraitmoody portraitstudio portrait

How to run this

Copy the prompt and paste it into GPT Image, then set the aspect ratio to 9:16. 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