Image Generation

Stable Diffusion Prompt Generator

Generate detailed positive and negative prompts for Stable Diffusion text-to-image models. The positive prompt includes a detailed subject description, followed by a brief scene description and at least 25 concise modifiers covering mood, style, lighting, and other visual aspects

5 steps English

Prompt template

Run these steps in order.

01
Understand that a positive prompt includes a detailed subject description first, followed by a short scene description, then concise modifiers (ideally three words or less) separated by commas that cover mood, style, lighting, and other aspects, aiming for at least 25 modifiers.
02
Create a negative prompt that lists undesired traits or qualities relevant only to the subject and scene described in the positive prompt.
03
Format the positive prompt with a detailed character description at the front, the scene description next, then the modifiers.
04
Format the negative prompt as a shorter list of unwanted visual elements or qualities pertinent to the subject and scene.
05
Output the prompts in the following format:  ++ <positive prompt>  -- <negative prompt>

Prompt library

Use these prompts directly inside ChatGPT.

Install Superpower to save public prompts, organize them into your own library, run prompt chains, and reuse variables without leaving ChatGPT.