Comic of your kitchen experiment
A funny four-panel comic of you attempting a new recipe and finally serving it with pride. Upload a clear photo, paste this prompt into ChatGPT, Gemini or Grok, change the parts in brackets to suit you, and generate.
Part of the Comic panel story trend
- Written for
- ChatGPT, Gemini, Grok
- You'll need
- A clear photo to upload
- Status
- Tested 20 Oct 2026 in Gemini web app, Auto mode (model identifier not shown)
- Test settings
- Reference photo: an AI-generated picture of a fictional woman (not a real person), made in the same Gemini chat just before the test. The default copy text was then sent unchanged. Try 1 wrote an extra 'COUGH' word, so try 2 is used; only the speech bubble has words. Gemini's output size is 928x1152; only converted to WebP, not upscaled.
- Variability
- Faces, poses and small details vary between runs; always compare the result with your own photo.
Use the uploaded photo as the reference for the person. Preserve their recognisable face, natural skin tone, hairline and body proportions as closely as the model permits; check the result against the reference. Scene: a four-panel comic: 1) tying an apron, ready to cook aloo paratha, 2) flour everywhere, 3) a puff of smoke from the pan, 4) proudly holding the finished plate. Pose: panel 1 confident, panel 2 surprised, panel 3 coughing, panel 4 beaming with a speech bubble saying Chef's special!. Clothing: the outfit from the photo with an apron. Light: warm kitchen colours in flat comic style. Style: playful comic art with bold outlines and halftone dots, the same face in every panel; no panel numbers and no text other than the speech bubble. Format: vertical 4:5, 2x2 grid Avoid: a different face in any panel, skin lightening, food brand labels, extra text, extra fingers, logos, watermarks.
Customise
For example: aloo paratha.
For example: Chef's special!.
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
- Faces can drift between panels; if one panel doesn't look like you, ask to redraw only that panel.
- Use reference photos you have the right to use; get consent from identifiable people.




