ForkFree

Prompts / Images and video

Reusable Image Style Template Builder

You get a reusable style template, with the look locked in and the scene left as variables, plus a finished image prompt. Fixing the style traits separately from the content keeps results consistent across many images.

Worked in our testAll four sections are present, with 7 style traits, a template with capitalised variables and a single-paragraph final prompt that quotes the text exactly. Small flaws: the headline is quoted as "focus / outlasts / noise." with slashes, not as three lines. The template's "HEADLINE LINE 1 / ..." fixes the headline layout as a style element. The final prompt adds "matte print finish" and "sharp focus on face and hands", which stretch the brief slightly.

The prompt

Act as an art director who turns visual references into reusable image-generation prompts.

Task: Turn the style description below into a fixed style lock plus a fill-in scene, then produce one final image prompt for the subject I give you.

Style description: {style_description}
Subject and scene: {scene_details}
Aspect ratio and headline text: {format_and_text}

Steps:
1. Extract the 5 to 7 visual traits that define the style (palette, lighting, composition, typography, texture, mood) and write them as a short "style lock".
2. List what must be avoided so the result does not copy any original subject, face or wording.
3. Build a template with the style lock fixed and the scene, aspect ratio and text as variables.
4. Fill the variables with my details and write the final prompt as one paragraph, stating any headline text exactly in quotation marks.

Output:
Four labelled sections: Style lock, Avoid list, Template (variables in capitals), Final prompt. No commentary beyond these.

Change the parts in curly braces. Use it when you need a set of images, such as posters or ads, that share one look but show different subjects.

What happened when we ran it

We sent

Act as an art director who turns visual references into reusable image-generation prompts.

Task: Turn the style description below into a fixed style lock plus a fill-in scene, then produce one final image prompt for the subject I give you.

Style description: A monochrome noir editorial poster. Black-and-white photographic portrait with a deep charcoal background and high contrast. A giant lowercase headline sits on the left in three short lines, with the first word in a white label. Lots of empty space, a tight close crop and shallow depth of field give it a serious, late-night mood.
Subject and scene: A tired architect with silver hair studies a folded blueprint in a dim concrete studio after midnight. She holds a rolled plan tube and a pencil low in one hand. The background is a soft charcoal wall and the blurred edge of a drafting table.
Aspect ratio and headline text: 16:9 landscape, subject weighted to the right. Headline: "focus / outlasts / noise." Small secondary text: "studio log 02:14".

Steps:
1. Extract the 5 to 7 visual traits that define the style (palette, lighting, composition, typography, texture, mood) and write them as a short "style lock".
2. List what must be avoided so the result does not copy any original subject, face or wording.
3. Build a template with the style lock fixed and the scene, aspect ratio and text as variables.
4. Fill the variables with my details and write the final prompt as one paragraph, stating any headline text exactly in quotation marks.

Output:
Four labelled sections: Style lock, Avoid list, Template (variables in capitals), Final prompt. No commentary beyond these.

The model replied

**Style lock** 1. Palette: strictly monochrome black-and-white, deep charcoal background, clean whites, rich blacks, no color cast. 2. Lighting: low-key, high-contrast, a single soft directional source with deep shadows and gentle highlight roll-off. 3. Composition: tight close crop, subject weighted to one side, generous empty negative space on the opposite side. 4. Typography: giant lowercase sans-serif headline in three short lines, left-aligned, first word set inside a solid white label with dark text; remaining lines in white; one small secondary caption in a quiet corner. 5. Texture: fine film grain, crisp photographic detail on the subject, matte print finish. 6. Depth: shallow depth of field, sharp focus on the face and hands, softly blurred background. 7. Mood: serious, quiet, late-night editorial tension. **Avoid list** - Do not reproduce any original subject, face, likeness, pose, or props from the reference. - Do not reuse any original wording, logos, names, or captions. - No color, no color tints, no sepia or duotone. - No busy backgrounds, clutter, or extra people. - No cartoon, illustration, or 3D-render look. - No extra text, watermarks, misspellings, or distorted lettering. - No centered symmetrical layout or wide environmental shots. **Template (variables in capitals)** Monochrome noir editorial poster, black-and-white photographic portrait, deep charcoal background, high contrast, low-key lighting from a single soft source, fine film grain, tight close crop, shallow depth of field, serious late-night mood. SUBJECT AND SCENE, with the subject weighted to SUBJECT SIDE and generous empty negative space on the opposite side. Aspect ratio ASPECT RATIO. Giant lowercase sans-serif headline on the left in three short lines reading "HEADLINE LINE 1 / HEADLINE LINE 2 / HEADLINE LINE 3", with the first word inside a solid white label with dark text and the other lines in white. Small secondary text "SECONDARY TEXT" in a quiet corner. No color, no extra text, no watermarks. **Final prompt** Monochrome noir editorial poster, 16:9 landscape, black-and-white photographic portrait on a deep charcoal background with high contrast and low-key lighting from a single soft directional source, fine film grain and a matte print finish. A tired architect with silver hair studies a folded blueprint in a dim concrete studio after midnight, holding a rolled plan tube and a pencil low in one hand; tight close crop, shallow depth of field with sharp focus on her face and hands, and a soft charcoal wall and the blurred edge of a drafting table behind her. She is weighted to the right of the frame, leaving generous empty negative space on the left. Giant lowercase sans-serif headline on the left in three short lines reading exactly "focus / outlasts / noise.", with the first word "focus" inside a solid white label with dark text and the lines "outlasts" and "noise." in white. Small secondary text in a quiet corner reading exactly "studio log 02:14". Serious, quiet, late-night editorial mood. No color, no extra text, no watermarks, no distorted lettering.

Run on Claude Sonnet 5.5, 02 Nov 2026. Automatic check: 4 out of 5.

Mentioned for

ChatGPT, Claude, Nano Banana Pro

Where it came from

Found on GitHub, shared by VigoZhao: VigoZhao/AI-Visual-Prompt-Cookbook.

This is our own version of the idea, written and tested by us. The original may differ.

More images and video prompts

Images and video Struggled in our test
Code-Drawn Motion Film Brief

You get a style note, a timed beat sheet, working page code that can draw any frame, and a sound plan, all reviewed once. It works because the film is defined as a function of time, so it can be captured frame by frame and checked against clear style rules.

Found on GitHub, shared by Vincentwei1021
Images and video Partly worked
Timed Shot Script for AI Video

You get a clean, timed script where every beat has one shot, one action and one sound. Splitting the clip this way stops the generator blending several actions into a muddle.

Found on GitHub, shared by LearnPrompt
Images and video Worked in our test
Timed Shot-by-Shot Video Prompt Writer

It gives you a ready-to-paste video prompt that sets the look first, then breaks the action into timed shots. Video models cope better with clear timings, camera moves and one action per shot than with a loose paragraph.

Found on GitHub, shared by ZeroLu