wowprompt

Portrait still animated into Dev Deepawali on the Varanasi ghats

Turns one portrait still into an eight second vertical clip of a young man sitting on the Varanasi ghat steps on Dev Deepawali at blue hour, with rows of tiny diyas on every step and boats of lamps on the river. Cool blue sky and water, the lamps only as points. Works with your own photo.

A young man in an off-white kurta sitting on Varanasi ghat steps lined with tiny diyas at blue hour, the river full of floating lamps behind him
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, the same face and body in every frame.
  • Small natural motion: no walking, no turning away from the camera, no change of clothes.
  • The lamps stay tiny points; the sky and water stay cool blue, never orange.
  • No text, signs or logos anywhere.

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 in every frame, 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.

The scene

He sits three steps up from the water on the stone ghat, torso angled slightly left of the camera, knees bent, feet flat on the step below. His left forearm rests on his left knee, the hand loose; his right hand sets a small clay diya on the step beside him and stays there. He wears an off-white handloom cotton kurta with a band collar, sleeves pushed to the forearm, and a thin grey wool shawl over one shoulder. Over eight seconds the flames flicker, his shawl edge lifts in the breeze, he blinks, looks out at the river, then turns his head back toward the lens with a calm half smile. A wooden boat drifts left to right behind him, and thousands of diyas line every step and float on the Ganga.

Technical

An 85mm lens at f/1.8, slight push-in, blue hour light from the open sky above the river, the diyas only as small warm points that do not light his face. True cool colour, real skin with pores, fine grain. Sound: river lapping, a distant conch, low chanting from far down the ghats.

Negative prompt

airbrushed skin, plastic skin, waxy face, changed face, morphing face, face drifting between frames, distorted hands, extra fingers, orange cast, warm wash, golden grade, sunset glow, crowds in sharp focus, fireworks, camera shake, subtitles, text, logo, watermark

Thumbnail prompt

For the cover image of this video. Paste it into an image model such as GPT Image.

Frame

A tall cover frame at blue hour on the Varanasi ghats. A young man in an off-white kurta and grey shawl sits on the lower right third of the stone steps, looking at the lens with a calm half smile, one hand beside a small clay diya. Rows of tiny diyas run along every step and float on the dark blue river behind him. The look of an 85mm lens at f/1.8, true cool colour, real skin. The upper left sky is clear for the words.

Identity

With a photo attached: keep the face from the photo exactly as it is. Without a photo: an original young man from Varanasi of about twenty-five with deep wheatish skin, a light beard and a small scar through his left eyebrow. Do not base the face on a real person.

Text

  • "DEV DEEPAWALI"
  • "VARANASI"

Heavy white sans-serif capitals with a soft dark shadow, stacked in the upper left sky, clear of his face. Nothing else is written anywhere. Spell each line exactly.

image to videodev deepawali videovaranasi ghat videophoto to videodiya ghatsfestival reelvertical video

How to run this

Copy the prompt and paste it into Veo, 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 video