Retro photos · Xiaohongshu 3:4 carousel · potential 64 · Machine-translated

Beicha County, AI-generated, exists in a '90s dream

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.

Cover of the original post: 百货大楼 — Cover · 1 of 8Original on Xiaohongshu ↗

Layers

Hook · Text layerBig signboard text
Palette · Palette layerGrey low saturation
Mood · Mood layerOld-photo feel

Spec sheet

1Hook

百货大楼. The big signboard overhead is seen first, and at a glance you know this is a period county-town main street.

Text: 百货大楼
Position: Upper right of the frame
Relative font size: The largest group among the street signboards

907 likes 339 saves 86 shares

Posted by 我是姚粒绒 on Xiaohongshu, 7 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.

Make your version4 cards Stick it together

The prompt, as used

Verbatim. Copy it, or let Queenie swap in your own details.

Referencing the case study "Beicha County, AI-generated, exists in a '90s dream" — its old-photo restoration approach, period texture, visual storytelling and posting tone — generate a new set of retro old-photo image-text posts. New topic: {fill in the photo topic 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 mood, film/photo-paper texture, human relationships, period sense of scene and restoration constraints; if it's photo restoration, it must stay faithful to the original image's identity, facial features, composition and historical context, avoiding over-beautification, redrawing, 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, period/texture keywords and a save prompt; 3. Visual prompts that can be used directly for image generation or photo restoration, explaining requirements for people, scene, lighting, film grain, damage repair and colour restoration; 4. Posting 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, prioritise identity consistency, and do not make them younger, beautify, slim the face or rewrite facial features.