Prompts Generate Xiaohongshu-Style Infographics for Content Breakdown

A new set of prompts has been developed to convert input content into a series of Xiaohongshu-style infographics. The system generates independent prompts for each image, which can then be used with AI models like Gemini Pro and Nano banana Pro to create a sequence of visuals. The prompts are compatible with large language models such as Gemini, Claude, and ChatGPT, allowing for the generation and fine-tuning of image prompts.

Diagram showing text input transforming into a sequence of AI-generated infographic visuals.

The system is designed to break down complex information into visually engaging, cartoon-style infographic series. It aims to produce between one and ten images per series, each with a distinct generation prompt.

Infographic Breakdown Principles

The breakdown follows specific principles for image creation:

The first image serves as a cover, designed for strong visual impact, incorporating the core title and an attractive point.

Middle images focus on a single core idea, maintaining moderate information density.

The final image provides a summary, a call to action, or a concluding statement.

Infographic illustrating the structure of a multi-image series: cover, middle, and final images.

The number of images generated depends on the content's complexity: simple ideas or single topics yield 2-3 images, medium complexity or tutorials result in 4-6 images, and in-depth insights or multi-dimensional analyses produce 7-10 images.

Visual Style Guidelines

The infographics adhere to specific visual style guidelines:

Basic Settings: All images are infographics with a vertical aspect ratio (3:4 or 9:16) and an overall cartoon or hand-drawn style.

Background and Color Scheme: Backgrounds use gentle tones such as Morandi colors, cream, off-white, light pink, or mint green. The color scheme is soft and unified, aligning with Xiaohongshu aesthetics.

Text Style: Text is exclusively hand-drawn. Main titles are prominent, and key text is bolded and enlarged. Highlight effects can be used for emphasis, while realistic fonts are prohibited.

Decorative Elements: Simple cartoon elements, icons, or celebrity portraits are added to enhance visual appeal. These can include emoji-style icons, hand-drawn stickers, sticky note textures, and speech bubbles. If sensitive or copyrighted figures are involved, a cartoon substitute with a similar style is drawn. All image elements must be hand-drawn or cartoon style, with no realistic elements.

Layout Principles: Information is concise, highlighting keywords and core concepts. Ample white space ensures readability, and key points are presented in bullet points for clear hierarchy.

Infographic detailing visual style guidelines: color, text, decorations, and layout.

Output Format

For each image, the output includes its position (e.g., Image X / Total N), its role (Cover image, Content image, or Ending image), a one-sentence core message, and specific text content (Main Title, Subtitle/Key Points, Additional Notes). A detailed visual prompt is also provided, specifying the style, background color, layout, decorative elements, and overall aesthetic, including a "Baoyu" watermark in the bottom right corner.