wowprompt

Chhath dawn arghya on the Yamuna under a Delhi metro bridge in mist

A Chhath Puja dawn arghya on the Yamuna in Delhi: a young woman stands waist-deep beneath a long concrete metro bridge in winter mist and lifts a bamboo soop of thekua and fruit to the pale rising sun, the dawn cool grey-blue. Works with your own photo.

A young woman in a pink saree standing waist-deep in a misty river under a concrete bridge, lifting a bamboo tray of fruit and sweets to a pale sun
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

Base

Chhath usha arghya on the Yamuna, Delhi, under a concrete metro bridge in winter mist.

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, and keep their own body: build, height and proportions, shoulders, arms, hands and legs, with the same skin tone on face, neck, arms and hands. Use the photo only for who the person is. Ignore its pose, expression, clothing, hairstyle, background, framing and light, and rebuild all of them exactly as described below, even when the photo shows them standing straight or dressed differently.

Add: pose

She stands waist-deep facing the sun at frame right, a quarter turn to the camera, eyes half closed. Her left hand grips the soop's front rim at forehead height; her right supports it beneath.

Add: wardrobe

A deep pink cotton saree with a green border, pallu wrapped across the front, long-line full-sleeve green blouse; sindoor.

Add: set

The soop holds thekua, bananas and a coconut; bridge pillars fade into mist.

Lock

The sun a small pale disc.

Camera

70mm at f/2.8, water level.

Grade

Cool grey-blue, real skin with pores, fine grain.

Negative prompt

airbrushed skin, plastic skin, waxy face, changed face, distorted hands, extra fingers, orange cast, orange sky, warm wash, metro train logo, readable signs, crowds in focus, watermark

chhath pujausha arghyachhath in delhiyamuna ghatchhath dawnbamboo soopfestival portrait

How to run this

Copy the prompt and paste it into GPT Image, then set the aspect ratio to 2:3. 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