
Haldi ceremony in open daylight
GPT Image
Works with your photo
Four sections, each with its own categories. Every prompt states the model it was tested on, the aspect ratio it expects, and whether it can keep your own face when you attach a photo.
Prompts for still images, each one shown with the output it produced and the model it was tested on.
31 categoriesPrompts for video models, with the clip each one produced and the settings it needs.
12 categoriesPrompts for work: search, advertising, writing, analysis and code, each written to return something usable rather than a draft.
16 categoriesPrompts for the things that come up every week: replies, messages, notes and planning.
14 categories
GPT Image
Works with your photo

GPT Image
Works with your photo

GPT Image
Works with your photo

Gemini
Works with your photo

GPT Image

GPT Image
Works with your photo
GPT Image
Works with your photo
GPT Image
Works with your photo
GPT Image

GPT Image
Works with your photo
GPT Image
Works with your photo
GPT Image
Works with your photo
The prompt itself, the image it produced, the model it was run on, the ratio it was run at, and its negative block where it has one. Where a prompt can keep your own face from a photo, that is stated as a field rather than buried in the text, so you know before you copy it.
The same prompt run on two models does not give the same picture. Naming the model is the difference between a prompt you can reproduce and one that happened to work once for whoever wrote it.