wowprompt

Khadi styling thumbnail on the ghats with lamps on the water

A Gandhi Jayanti video thumbnail for a khadi styling video: a young woman in a white handspun khadi set with an indigo block-printed dupatta on the ghats at dusk, lamps floating on the water and open space for a title. Works with your own photo.

A young woman in a white khadi kurta set and indigo dupatta leaning on a ghat railing at dusk, clay lamps on the river behind
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, no text. The right third stays clear dark water and sky for a title added later. Both hands natural. The khadi keeps its handspun slub.

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 stands full length on the left third, leaning on an old iron railing at the river ghats, relaxed, one hand in the pocket of her kurta. She wears a white handspun khadi kurta and straight trousers with an indigo hand-block-printed khadi dupatta, oxidised silver jhumkas and a thin red thread on the wrist. A brass prayer lamp burns on the step beside her. Behind her, stone steps fall to the river where clay diyas float on dark water under a deep blue sky.

Technical

A 135mm lens at f/2, the river and lamps compressed into soft colour. Diya and lamp light as a warm key on the face, the deep blue sky behind. Restrained teal and orange grade, skin kept natural with texture and pores.

Negative prompt

airbrushed skin, plastic skin, waxy face, changed face, distorted hands, extra fingers, Gandhi likeness, crowd, priests, polyester shine, flash, text, logo, watermark, signature

youtube thumbnailgandhi jayantikhadighats at duskdiyastyling videofull length portrait

How to run this

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