Why does the output change by model?

Each model reads prompts differently. Midjourney uses --ar and --no flags and weights commas; Stable Diffusion uses a separate negative prompt; DALL·E prefers a single natural-language sentence. The builder formats your inputs to each model's conventions.

Where does the negative prompt go?

For Stable Diffusion and SDXL it is emitted as a separate "Negative prompt:" line, which is how those models consume it. For Midjourney it is converted to --no flags. DALL·E ignores negative prompts, so it is folded into descriptive phrasing instead.

How specific should the subject be?

Very. "A red fox" is weak; "a red fox curled asleep on moss, frost on its fur" gives the model something concrete to render. Specificity in the subject and style fields does more than any other setting.

Is anything uploaded?

No. The builder runs locally and only outputs text. Nothing is sent to any image model or stored.

What is the Image Generation Prompt Builder?

Guides you through subject, style, lighting, composition, camera specs, and negative prompt fields to construct a well-structured image generation prompt formatted for DALL·E, Midjourney, or Stable Diffusion. It runs free in your browser on Gera Tools, with nothing uploaded.

Image Generation Prompt Builder

Name: Image Generation Prompt Builder
Creator: Gera Tools
License: https://creativecommons.org/licenses/by/4.0/

Image generation prompt builder

A great diffusion image starts with a structured prompt, and the structure differs by model. Midjourney rewards comma-weighted phrases and flags; Stable Diffusion wants a separate negative prompt; DALL·E reads a single clear sentence. This builder lets you fill in the parts of a strong prompt — subject, style, lighting, composition, camera — and then formats the result correctly for the model you are targeting.

How it works

You describe the subject (the most important field), choose a style, and layer in lighting, composition, and optional camera/lens specs for photographic realism. A negative prompt field lets you list what to avoid. When you pick a target model, the builder assembles everything in that model’s syntax: Midjourney gets --ar and --no flags, Stable Diffusion gets a separate negative prompt line, and DALL·E gets a natural-language sentence with the avoidances phrased positively.

How each field affects the output

Subject is where most of the image’s content comes from. The more concrete and specific it is, the more predictable the result. “A person” leaves enormous room for interpretation; “a middle-aged woman in a green wool coat, reading on a park bench, autumn leaves on the ground beside her” gives the model almost everything it needs. Specificity in the subject is the single highest-leverage change you can make to a prompt.

Style shifts the entire aesthetic — from photorealistic to oil painting to flat vector illustration. Different styles interact differently with the other fields: lighting keywords matter a great deal for photorealistic and cinematic styles, but much less for flat illustration or watercolor styles where lighting is implied by the art form itself.

Lighting shapes mood more than almost any other field in photorealistic images. “Soft diffused light” gives a calm, editorial feel; “dramatic side lighting” creates tension; “golden hour” adds warmth and nostalgia. For illustration styles, lighting language can often be skipped or replaced with color-mood language (“warm palette,” “muted tones”).

Composition tells the model where to place things in the frame. “Close-up portrait,” “wide establishing shot,” “rule of thirds, subject on left” — these are the vocabulary of photography and illustration, and most diffusion models respond well to them.

Camera and lens specs push output toward photography and away from illustration. “Shot on 35mm film, f/2.8, shallow depth of field” signals that the output should look like a physical photograph. Drop these entirely for painterly, illustration, or cartoon styles.

Tips and notes

Lead with the subject. All three models weight early tokens — put the concrete subject first and the stylistic modifiers after.
Camera specs add realism. “35mm, f/1.8, golden hour” pushes the output toward photography; drop them for illustration and painting styles.
Keep the negative prompt focused. For Stable Diffusion, a tight list (“blurry, extra fingers, watermark”) beats a wall of tokens.
Iterate one field at a time. Change only the lighting or only the style between runs so you can tell what each modifier actually does.