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 readable text in the image at all; it relies entirely on a wedding-banquet photo that looks like a re-shot old film to make people believe it first, then look back at the title.
Posted by KimWang on Xiaohongshu, 24 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 "GPT-image2 If I said this was an old photo, some people would believe it" — its old-photo restoration approach, period texture, visual storytelling and publishing tone — generate a new set of retro old-photo image-and-text posts. New topic: {fill in the photo topic you want to restore, reconstruct or recreate} Reference platform: Xiaohongshu Content direction: retro old-photo image-and-text Creation method: keep the original case's nostalgic mood, film/photo-paper texture, relationships between people, period feel of the scene 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, 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 containing a visual description, main copy, period/texture keywords and a save prompt; 3. Visual prompts ready for image generation or photo restoration, explaining requirements for people, scene, lighting, film grain, damage repair and colour restoration; 4. Publishing advice: title length, tags, image ratio and platform tone. Constraints: do not replicate the original author, original people or brand marks; do not fabricate historical facts; when real people's photos are involved, prioritise identity consistency, with no making younger, beautifying, face slimming or facial feature rewriting.
