Put the cover under the lamp. Each of the five things that made it work is a layer you can switch on: the words, the grid it sits on, the colours it uses, the subject, the light.
GPT Image 2. The big text spans the seam between the two puzzle pieces, and at a glance you can tell this is a new AI image-generation trick — you can't help but want to see what it made.
Posted by 雅涵学姐AIGC🎬6月深圳.山东开课 on Xiaohongshu, 23 Apr 2026. Shown with credit and a link back.
Keep all five layers and swap what’s under them: your shop, your budget, your city. You get four covers and the post text.
Verbatim. Copy it, or let Queenie swap in your own details.
Referencing the case study "I Made AI Generate: My Family Portrait in a Parallel World" — its old-photo restoration approach, period texture, visual storytelling, and publishing tone — generate a new set of retro old-photo image-and-text content. New theme: {fill in the photo theme you want to restore, rebuild, or recreate} Reference platform: Xiaohongshu Content direction: retro old-photo image-and-text Creation method: keep the original case's nostalgic emotion, film/photo-paper texture, relationships between people, period feel of the scene, and restoration constraints; if it's photo restoration, it must stay faithful to the identity, facial features, composition, and historical context of the original image, avoiding excessive beautification, redrawing, false historical information, and a modern digital plastic look. Please output: 1. Cover title and subtitle; 2. A 6-9 page image-and-text script, each page including a visual description, main copy, period/texture keywords, and a save prompt; 3. Visual prompts that can be used directly for image generation or photo restoration, specifying the people, scene, lighting, film grain, damage repair, and color restoration requirements; 4. Publishing suggestions: title length, tags, image ratio, and platform tone. Constraints: do not recreate the original author, original people, or brand logos; do not fabricate historical facts; when real people's photos are involved, prioritize identity consistency, and do not make them younger, beautify, slim the face, or rewrite facial features.
