AIGC | AI's Vision of Facial Portraits Across Different Professions

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: AIGC | AI's Vision of Facial Portraits A — Cover · 1 of 6Original on Xiaohongshu ↗

Layers

Hook · Text layerNo text in image
Palette · Color layerMainly warm brown and earthy yellow
Mood · Mood layerQuiet and rustic

Spec sheet

1Hook

. The image has no text at all; it stops people with a rough face in extreme close-up.

Text: None
Position: —
Note: The portrait itself serves entirely as the hook

9 likes 4 saves 0 shares

Posted by 画画不是我的强项 on Xiaohongshu, 28 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 "AIGC | AI's Vision of Facial Portraits Across Different Professions" for its old photo restoration approach, vintage texture, visual storytelling, and publishing tone, generate a new set of vintage old-photo image-text posts. New topic: {fill in the photo topic you want to restore, reconstruct, or replicate} Reference platform: Xiaohongshu Content direction: vintage old-photo image-text Creation method: retain the original case's nostalgic emotion, film/photo paper texture, character relationships, era-appropriate scene feel, 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 modern digital plastic feel. Please output: 1. Cover title and subtitle; 2. A 6-9 page image-text script, each page including visual description, main copy, era/texture keywords, and save prompt; 3. Visual prompts that can be directly used for image generation or photo restoration, specifying 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 real people's photos are involved, prioritize identity consistency, and do not do age regression, beautification, face slimming, or facial feature rewriting.