Heartbroken! Using GPT image-2 to Enrich Mom and Dad's 1981
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.
黑龙江 黑河市. The place name on the street sign is the only concrete, verifiable information in the image, making people want to ask about the location and story behind this group photo.
Text
黑龙江 黑河市
Position
On a street sign in the lower right corner of the image
Relative size
Smaller text in the image, occupying a very small corner of the whole picture
♥ 5 likes★ 1 saves↗ 0 shares
Posted by 周州昙 on Xiaohongshu, 21 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.
Verbatim. Copy it, or let Queenie swap in your own details.
Referencing the case study "Heartbroken! Using GPT image-2 to Enrich Mom and Dad's 1981" for its old photo restoration approach, era texture, visual storytelling and publishing tone, generate a new set of retro old-photo image posts. New theme: {fill in the photo theme you want to restore, rebuild or recreate} Reference platform: Xiaohongshu Content direction: retro old-photo image posts Creation method: retain the original case's nostalgic emotion, film/photo-paper texture, character relationships, scene era feel and restoration constraints; for photo restoration, you must stay faithful to the original image's identity, facial features, composition and historical context, and avoid over-beautification, repainting, 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, 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 people 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.