✦PROMPT ATLASIMAGE PROMPT · VISUAL PROMPT ATLASGitHub ↗中文

小红书封面

Read the complete source prompt and attribution. Titles and source text retain their original language.

GPT-4o / gpt-image-1(合集Category)Text onlyPosters & covers
小红书封面 · Source example
Upstream maintainer reproduction using Sora; not regenerated by this site.
Image credit: @jamez-bondos.Previews were resized and converted to WebP; they were not regenerated by this site.

Complete prompt

MarkdownJSON
Draw an image: Create a cover for a Xiaohongshu (RED) post.

Requirements:
– It must be visually compelling enough to attract user clicks.
– Use bold, characterful fonts.
– Vary font sizes to reflect the hierarchy of information; emphasize the structure of the copy.
– The main title should be at least twice the size of regular text.
– Leave white space between text sections.
– Only use bright accent colors to highlight key words and draw attention.
– The background should feature an eye-catching pattern (such as paper texture, notebook, or a WeChat chat window—choose one).
– Add appropriate icons or illustrations to enhance visual layers, but avoid visual clutter.

Copy text:
BREAKING: ChatGPT just got even better!
– Superior multitasking ✨
– Stronger coding ability 💪
– Creativity off the charts 🎨
Try it now!

Image aspect ratio: 9:16
Source Chinese translation
画图:画一个小红书封面。
要求:
有足够的吸引力吸引用户点击;
字体醒目,选择有个性的字体;
文字大小按重要度分级,体现文案的逻辑结构;
标题是普通文字的至少2倍;
文字段落之间留白。
只对要强调的文字用醒目色吸引用户注意;
背景使用吸引眼球的图案(包括不限于纸张,记事本,微信聊天窗口,选择一种)
使用合适的图标或图片增加视觉层次,但要减少干扰。

文案:重磅!ChatGPT又变强了!
多任务处理更牛✨
编程能力更强💪
创造力爆表🎨
快来试试!

图像9:16比例

Make it your own

Start from the source text. Add your own authorized reference for a specific person, logo or product when needed.

Change one element at a time. Keep useful composition and lighting, and use your own reference material when required.

Structure: [Subject] + [Composition] + [Light] + [Material or style] + [Text or details to preserve] + [Aspect ratio]

Open the gallery workbench ↗

Sources & attribution

Prompt author
@balconychy
Original source
Original post / source page ↗
Source collection
Awesome GPT-4o Images
Model
GPT-4o / gpt-image-1(合集Category) (source label; not a current-version claim)
Source date
2025-05-24 · Reproduction date from the upstream attribution file.
Snapshot
2026-10-20
Evidence
来源Collection entry;8,149 Stars 是整个合集的历史记录,不属于单张作品.
Content rights
CC BY 4.0 as declared by the source; attribution, exceptions and third-party rights apply..Retain attribution and source links. Upstream exceptions and third-party rights apply.
Source notes
保留合集公开 Prompt;部分提示词是合集翻译或适配版.实际效果还受Model版本、Reference与采样差异影响.

Examples were not regenerated by this site. Results vary with tools, model versions, references and editing rounds.Sources & methods

More examples: Posters & covers