AI Old Photos of Empress Dowager Cixi: These Two Guards Are Stealing the Show.

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: AI Old Photos of Empress Dowager Cixi: T — Cover · 1 of 1Original on Xiaohongshu ↗

Layers

Hook · Text LayerNo text in the image
Palette · Color LayerBlack background with deep blue and brick red
Mood · Mood LayerDeep background, calm old photo feel

Spec sheet

1Hook

. Without text, the first-glance question is thrown entirely by the image, and viewers want to know what occasion this is.

Text: None
Position: No text area
Function: Relies on the figures and clothing themselves to carry the first-glance appeal

114 likes 35 saves 4 shares

Posted by 意漫 on Xiaohongshu, 16 Nov 2025. 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.

Refer to the old photo restoration method, vintage texture, visual storytelling, and publishing tone of the case study "AI Old Photos of Empress Dowager Cixi: These Two Guards Are Stealing the Show." to generate a new set of retro old photo image-text posts. New theme: {fill in the theme of the photo you want to restore, reconstruct, or recreate} Reference platform: Xiaohongshu Content direction: Retro old photo image-text Creation method: Retain 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 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. 6-9 page image-text script, each page includes scene description, main copy, era/texture keywords, and save guide; 3. Visual prompts that can be directly used 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 characters, or brand logos; do not fabricate historical facts; when involving photos of real people, prioritize preserving identity consistency, and do not make them younger, beautify, slim the face, or alter facial features.