Image Generation

Stable Diffusion Prompt Generator

Generate detailed positive and negative prompts for Stable Diffusion text-to-image models, following a structured format to describe characters, scenes, and modifiers for image generation.

5 steps English

Prompt template

Run these steps in order.

01
Understand that a positive prompt for Stable Diffusion includes a detailed description of the subject first, followed by a short scene description, then concise modifiers separated by commas to describe mood, style, lighting, and other traits, aiming for at least 25 modifiers.
02
Negative prompts describe undesired traits in the generated image and should only include attributes relevant to the subject and scene described in the positive prompt.
03
When creating prompts, structure positive prompts with detailed character description upfront, then a brief scene setting, followed by a list of concise modifiers (ideally three words or less, totaling 25 or more) to enrich detail.
04
Create a matching negative prompt listing unwanted visual elements or qualities, ensuring all terms are relevant to the subject and scene.
05
Format outputs as follows:

++ <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.