There are 3 levels of AI and image prompting

LEVEL 1 LEVEL 2 LEVEL 3 are 3 of AI and never past 1But formula give level every time after thousands this is reliable structure Subject Setting Style Lighting Technical Details Subject What am I looking at? Describe the main person, object, material, texture, or action. Setting What does it happen? Add the location, time of day, background, and environment. Style What should it look like? Choose the visual direction, such as cinematic, editorial, vintage, or product photo. Lighting How is it lit? Control the light source, direction, surface, color, and mood. Technical How will it be captured? Add camera, depth of field, exposure, and aspect ratio. I found Subject Setting Style and technical details. You don't always need all 5 but the more specific you are, the less the model decides for you. And the more control you get over the image. A classic hourglass on a wooden table. level 1 only subject and the setting. A classic hourglass on a wooden table. that's enough the object, model almost everything else. 2 A clear glass hourglass with a dark wooden frame on a rustic wooden table. The sand in the top half is almost gone, with most of it collected in the bottom. Soft morning light comes from a window on the left. A small stack of old books sits beside it. Now about hourglass the the books beside it and lighting. And particles light cinematic style, photography, composition, Fujifilm the 56 1.2 lens depth shot on a Fujifilm X-T4 with a 58mm f/1.2 lens, shallow depth of field, Kodak Portra tones, warm earthy color palette, soft film grain. Portra warm soft grain, you control the image. not generate, but final image should look. So generating remember rules results you want.