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.
. There is no text on the image; it relies entirely on two similar old photos placed side by side, making people want to stop and figure out which one looks unnatural.
Text
There is no readable text in the image
Traces
There are tiny blurry marks on the photo whose content cannot be identified
♥ 57 likes★ 71 saves↗ 14 shares
Posted by 辛澄游 on Xiaohongshu, 2 Apr 2024. 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 "Can you tell which old photo was made by AI?" — its old-photo restoration approach, vintage texture, visual narrative, and posting tone — generate a new set of retro old-photo image-text content. New topic: {fill in the photo theme you want to restore, rebuild, or recreate} Reference platform: Xiaohongshu Content direction: retro old-photo image-text Creation method: keep the original case's nostalgic emotion, film/photo-paper texture, character relationships, era-specific scene feel, and restoration constraints; if it is photo restoration, it must stay faithful to the original image's identity, facial features, composition, and historical context, avoiding excessive beautification, repainting, false historical information, and a modern digital plastic feel. Please output: 1. Cover title and subtitle; 2. A 6–9 page image-text script, each page containing a visual description, main copy, era/texture keywords, and a save prompt; 3. Visual prompts that can be used directly for image generation or photo restoration, specifying requirements for people, scenes, lighting, film grain, damage repair, and color restoration; 4. Posting suggestions: title length, tags, image ratio, and platform tone. Constraints: do not replicate the original author, original people, or brand identity; 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 alter facial features.