Queenie
  1. Queenie
  2. Hits
  3. Retro photos
  4. 红星小卖部
Retro photos · Xiaohongshu 3:4 carousel · potential 49 · Machine-translated

Old Photos Generated by Different AIs: Who Wins?

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: 红星小卖部
Cover · 1 of 4Original on Xiaohongshu ↗
Layers
Spec sheet

1Hook

红星小卖部. The four big characters directly point out the era and scene, instantly evoking shared memories of the corner store and making people want to tap in for details.

Text
红星小卖部
Position
Upper part of the image, slightly to the right
Relative size
The largest group of text in the image
101 likes 29 saves 17 shares

Posted by 山里阿慢🐱 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.

The prompt, as used

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

Referencing the old photo restoration approach, vintage texture, visual storytelling, and posting tone of the case study "Old Photos Generated by Different AIs: Who Wins?", generate a new set of retro old-photo image-and-text content. New topic: {fill in the photo topic you want to restore, rebuild or recreate} Reference platform: Xiaohongshu Content direction: retro old-photo image-and-text Creation method: keep the nostalgic emotion, film/photo-paper texture, character relationships, era atmosphere of the scene, and restoration constraints of the original case; 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, era/texture keywords, and a save prompt; 3. Visual prompts that can be used directly for image generation or photo restoration, specifying requirements for characters, scene, 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 characters, 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.

More retro photos recipes

All retro photos hits →
AI科技79
Retro photosXiaohongshu

AI Gives Old Photos New Life: Childhood Memories

12K likes 2.7K saves 760 shares
See the recipe
周一闭馆78
Retro photosXiaohongshu

The era when images and memory confirmed each other has ended

5.8K likes 1.1K saves 3.7K shares
See the recipe
料到Ai68
Retro photosXiaohongshu

How to restore pore-level detail from a blurry image?

2K likes 1K saves 191 shares
See the recipe
7.zip68
Retro photosXiaohongshu

AI video: A day in the life of an 80s "popsicle-selling woman."

9.6K likes 1.2K saves 61 shares
See the recipe
Icetea冻柠66
Retro photosXiaohongshu

Recreating the life of young people in 2008 with AI

1.1K likes 243 saves 476 shares
See the recipe
衣修哥66
Retro photosXiaohongshu

I'm Not Fixing Old Photos

6K likes 376 saves 111 shares
See the recipe