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 not a single line of copy; it relies entirely on the damaged old-photo texture to create the curiosity of "what era is this," making people want to tap in and see the before and after restoration.
Text
There is no readable text in the image
Visual focus
The area where the people are in the middle of the frame
Position and proportion
No text to measure
♥ 367 likes★ 522 saves↗ 79 shares
Posted by 老王课代表 on Xiaohongshu, 6 May 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.
Referring to the old photo restoration approach, vintage texture, visual storytelling and publishing tone of the case study "GPT Image 2 Old Photo Restoration Prompt", generate a new set of retro old photo image-text content. New theme: {填写你要修复、重建或复刻的照片主题} Reference platform: Xiaohongshu Content direction: retro old photo image-text Creation method: keep the nostalgic mood, film/photo paper texture, character relationships, era-specific scene feel and restoration constraints of the original case; if it is photo restoration, it must be faithful to the original image's identity, facial features, composition and historical context, avoiding excessive beautification, redrawing, false historical information and 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, explaining requirements for characters, scene, lighting, film grain, damage repair and color restoration; 4. Publishing suggestions: title length, tags, image ratio and platform tone. Constraints: do not replicate the original author, original people or brand logos; do not fabricate historical facts; when real people's photos are involved, prioritize preserving identity consistency, and do not make them younger, beautify, slim the face or alter facial features.