Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

image-prompt-reverse Tested for Structured Image Prompts

AI summary

Author Xiaohu installed the open-source, prompt-only image-prompt-reverse skill in Loomy and tested it with Van Gogh’s Wheat Field with Cypresses. The skill reportedly analyzed the image in two reference passes and produced an eight-part package with restoration and enhanced prompts, three variants, Midjourney, Stable Diffusion, DALL·E and Flux adaptations, negative constraints and a variable template. The author then sent the enhanced prompt unchanged to Loomy’s built-in image generator and reported that key elements and impasto-like texture appeared in the result.

In-depth insight

The report documents a reusable, API-independent workflow for turning reference images into structured prompts across multiple image-generation platforms, although its results come from a single author’s account.

一次不掺水的 Agent Skill 实测:image-prompt-reverse 是纯提示词技能,无接口依赖、无运行时,一个文件夹复制过去就能用。我在 Loomy 里装好(Ctrl+K 技能面板搜「反推」,绿色标签即挂载成功),用公有领域的梵高《麦田与柏树》跑了一遍。它先连读两轮参考文件调出维度表和增强词库,再按场景归类逐项拆解,最后输出 8 件套并适配四大出图平台语法。本文按步骤还原:安装 → 派活 → 读词库 → 8 件套 → 回传生图验证 → 29 积分算账,附 5 组完整可抄文本。

我是小虎,浙大计算机本硕,破局行动家,《AI超级个体——一人公司完全指南》作者,专注于AI培训、超级个体打造、公司提效陪跑。

上一篇写 Loomy 的文章发出后,评论区问得最多的是:积分能白领,技能呢?WorkBuddy 里那一堆 skill,这边能不能装?

大家好,我是小虎。

#image-prompt-reverse#Loomy#WorkBuddy#Midjourney#Stable Diffusion#DALL·E#Flux#GLM 5.3 Flash

Original · 8 min readRead the original
Group chat

No comments yet. Start the conversation.