AI Image Prompts

The anatomy of a winning prompt

A good image prompt is built from layers. The more specific layers you add, the more control you have over the result. The components:

1. Subject: what's in the image. Specific — not "a dog" but "a young golden retriever."
2. Action/context: what's happening. "running on a beach at sunset."
3. Style: photography, oil painting, anime, 3D render, minimalist.
4. Composition: close-up, wide shot, from above, rule of thirds.
5. Lighting: golden hour, soft light, dramatic, neon — a huge influence on the feel.
6. Camera/lens: shot on 85mm, shallow depth of field, cinematic.
7. Color & mood: warm tones, moody, pastel.
8. Quality: highly detailed, 4k, sharp focus.

Example: before and after

Weak prompt:

a coffee shop

Strong prompt:

cozy specialty coffee shop interior, warm morning light through
large windows, wooden tables, plants, shallow depth of field,
shot on 35mm, cinematic, highly detailed, warm color palette

Same subject — a completely different result. The second prompt gives the model all the context: atmosphere, lighting, photographic style and color palette.

Negative prompts

In Stable Diffusion (and many tools) you can define what not to include — a negative prompt. Useful for removing common distortions:

Negative: blurry, low quality, distorted hands, extra fingers,
watermark, text, deformed, ugly

In Midjourney you use the --no parameter (e.g. --no text). It cleans up a lot of problems at once.

Parameters & aspect ratio

• Aspect ratio: in Midjourney --ar 16:9 (video/banner), --ar 9:16 (story/Reel), 1:1 (post). Match it to the destination.
• Weights: you can emphasize a word — in SD with parentheses (word:1.3), in Midjourney with ::.
• Seed: save the seed to reproduce, or to vary a result you liked.
• Reference image: you can supply a reference image for style/composition.

Iteration — the real secret

Nobody gets the perfect image on the first try. The process: generate → pick the closest → change one element → repeat. Change one thing at a time (only the lighting, only the style) to understand what affects what. Save prompts that worked — they become your own templates.

Quick tips

• English is better for prompts — the models were trained mostly on it. Think in your language, write in English.
• Sometimes less is more. Too many contradictory words confuse. Balance detail with clarity.
• Steal a style. Saw an image you loved? Analyze which elements (lighting, style) built it.
• For brand consistency (the same style every time) — Stable Diffusion with LoRA gives full control.
• Grab ready-made prompts from the prompt library as a starting point.