Queenie
  1. Queenie
  2. Hits
  3. Retro photos
  4. 千禧年初中国家庭老照片风格,2000年代早期,室内随手拍
Retro photos · Xiaohongshu 3:4 carousel · potential 48 · Machine-translated

I "Generated" My 2005 Self with ChatGPT 2.0

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: 千禧年初中国家庭老照片风格,2000年代早期,室内随手拍
Cover · 1 of 6Original on Xiaohongshu ↗
Layers
Spec sheet

1Hook

千禧年初中国家庭老照片风格,2000年代早期,室内随手拍. Place the full parameters of "AI-generated old photo" right in the center of the frame like a copyable recipe, making people want to screenshot and save it.

Text
千禧年初中国家庭老照片风格,2000年代早期,室内随手拍
Position
Center of the frame
Relative size
About 60% of the frame width, small font size
92 likes 33 saves 15 shares

Posted by Limbo'梦话 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.

The prompt, as used

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

Referencing the case study "I 'Generated' My 2005 Self with ChatGPT 2.0"—its old-photo restoration approach, period texture, visual storytelling, and posting tone—generate a new set of vintage old-photo image-and-text posts. New topic: {fill in the photo topic you want to restore, rebuild, or recreate} Reference platform: Xiaohongshu Content direction: vintage old-photo image-and-text Creation method: retain the original case's nostalgic emotion, film/photo-paper texture, character relationships, period feel of the 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 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, specifying requirements for people, scene, lighting, film grain, damage repair, and color restoration; 4. Posting suggestions: title length, tags, image aspect ratio, and platform tone. Constraints: do not replicate the original author, original subjects, or brand logos; do not fabricate historical facts; when real people's photos are involved, prioritize identity consistency—no age regression, beautification, face slimming, or feature rewriting.

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