Chhath sunset arghya adult portrait
A respectful portrait of an adult woman offering arghya in clear shallow water at sunset. Upload a clear photo, paste this prompt into ChatGPT, Gemini or Grok, change the parts in brackets to suit you, and generate.
- Written for
- ChatGPT, Gemini, Grok
- You'll need
- A clear photo to upload
- Occasion
- Chhath Puja · 13 – 16 Nov · evening arghya 15 Nov
- Status
- Tested 27 Oct 2026 in grok-imagine-image-2.0
- Test settings
- Reference photo: an AI-generated picture of a fictional adult woman (not a real person), made in Grok for this test. Uploaded with the default copy text unchanged. Aspect ratio 2:3 (no 4:5 or 3:4 preset on the edit endpoint). First result used (1 try). Kept at 1152x1728, not upscaled, and converted to WebP.
- Variability
- Faces, poses and small details vary between runs; always compare the result with your own photo.
Prompt
Use the uploaded photo as the reference for the one adult person. Preserve their recognisable face, natural skin tone, age and height as closely as the model permits; match the person to the reference. Scene: a quiet clean ghat at a peaceful riverside with broad clean stone steps during Chhath evening arghya, clear shallow water with safe stone footing and no crowd around the adult woman. Moment or Pose: the adult woman stands in shallow water facing the setting sun at a gentle three-quarter angle, holding a bamboo soop of offerings while a small brass vessel rests securely inside it for a gentle water offering; her face stays clearly visible and unobstructed. Clothing: a plain saffron cotton saree with a red border and a matching blouse, modestly and securely draped, opaque fabric with natural folds and no branding. Light: low golden sunlight from the side with soft reflected fill on her face, retaining her natural skin tone. Camera: 70mm, f/4, eye level from the ghat edge, hands, soop and face readable. Style: respectful devotional portrait photography, calm expression and believable ritual objects. Format: vertical 4:5. Avoid: changed faces, skin lightening, extra fingers, text, logos, watermarks, celebrity likenesses, litter, plastic, pushing crowds, transparent clothing.
Customise
For example: a peaceful riverside with broad clean stone steps.
For example: a plain saffron cotton saree with a red border and a matching blouse.
Fields start with illustrative values; replace them with your own facts. The prompt updates as you type. Copy prompt copies your version.
How to use it
- Open an external image tool listed above. The tested model, if any, is named in Status.
- Upload a clear reference photo of the subject. If it includes identifiable people, get their consent and check each face.
- Customise the fields, copy your version, paste it with the photo and generate.
- Compare the result with the reference. If a face, pose or detail changes, ask for one correction or try again; an exact match is not guaranteed.
How to use this prompt
- This prompt changes your own photo. Choose a clear reference photo, and get permission from people who can be identified.
- Upload the photo in the external AI app you chose. Fill Customise, press Copy prompt and paste the prompt with the photo.
- Compare the new picture with the original. Face, hands, clothes and pose can change. An exact likeness is not guaranteed.
Good to know
- The model may confuse the vessel, soop and water stream; review the offering gesture and face carefully.
- Use reference photos you have the right to use; get consent from identifiable people.
