Waiting for the moon on a cloudy Karwa Chauth
A moody photo of you on a haveli balcony watching the clouds, waiting for the moon to appear. 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
- Karwa Chauth · 29 Oct
- Status
- Tested 6 Oct 2026 in ChatGPT built-in image generation (underlying model identifier not exposed)
- Test settings
- Exact website default prompt; one generated output; synthetic reference photograph supplied; WebP export quality 88, original dimensions retained.
- Variability
- Single run reviewed visually; repeatability not tested. AI output, hands, expressions, lighting and likeness may vary.
Prompt
Use the uploaded photo as the reference for the woman. Preserve their recognisable face, natural skin tone, hairline and build as closely as the model permits; check the result against the reference. Scene: a carved stone balcony of an old haveli in Jodhpur on Karwa Chauth night, thick grey clouds with just a bright edge of the moon peeking through, the thali with sieve and diya on the ledge. Moment or Pose: she leans on the balcony, looking up at the clouds with a patient, hopeful half-smile, one hand holding the sieve against her chest; face clearly visible. Clothing: a maroon bandhej saree with a gold border and bangles. Light: warm diya light from below, silvery glow from the clouds, light breeze moving the dupatta. Camera: 50mm, f/2, slightly low angle to include the sky. Style: moody cinematic portrait, deep blues with warm reds, natural skin. Format: vertical 4:5. Avoid: changed face, a fully clear sky, two moons, plastic skin, text, watermarks.
Customise
For example: Jaipur.
For example: a maroon bandhej saree with a gold border and bangles.
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 moon may come out fully visible despite the clouds; regenerate for the peeking look.
- Use reference photos you have the right to use; get consent from identifiable people.
