wowprompt

Durga Puja dhunuchi portrait under a red rim light

A dramatic Durga Puja portrait of a young man in a white garad silk panjabi holding a smoking clay dhunuchi, adjusting his sunglasses, lit by a deep red rim against black. Works with your own photo.

A young man in a white red-bordered panjabi holding a smoking clay dhunuchi and adjusting sunglasses against a black backdrop
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 only, two hands with five fingers each: one holds the dhunuchi, the other adjusts the sunglasses. No text. The face stays lit warm and true, never red.

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

He stands half-turned, chin lifted, adjusting black rectangular sunglasses with one hand and holding a clay dhunuchi at chest height with the other, coconut husk glowing, fragrant smoke curling up across the frame. He wears a white garad silk panjabi with a thin red border at the placket, a red and white cotton gamchha over one shoulder, a red thread on his wrist. Nothing behind him but black and drifting smoke.

Technical

A deep red rim from behind, a soft warm key on the face. 50mm at f/1.4, eye level, waist up. Restrained teal and orange grade, skin natural with visible pores.

Negative prompt

airbrushed skin, plastic skin, waxy face, changed face, red cast on the face, distorted hands, extra fingers, idol, crowd, fire, flat lighting, grey backdrop, text, logo, watermark, signature

durga pujadhunuchipanjabimens portraitred rim lightfestival portraitsunglasses

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