
The latest AI image trend is taking social media back several decades. From Bollywood-inspired portraits to photographs resembling old family albums, users are turning their present-day selfies into 1980s-style images with ChatGPT. The resulting pictures typically feature film grain, bold colours, dramatic lighting, period hairstyles and other visual elements associated with the decade.
The trend has spread across platforms, including Instagram, where users are sharing their AI-generated retro portraits through posts and Reels.
However, getting a convincing 1980s photograph is not simply a matter of uploading a selfie and asking ChatGPT to make it look old. The wording of the prompt and the visual details specified can significantly affect the result.
Quick answers to key questions
Common mistakes include using vague prompts, not specifying the photographic look, forgetting to preserve identity, leaving modern elements in the image, not describing surroundings, over-stylising the photograph, and ignoring small period details.
To create a convincing 1980s-style photo, provide detailed instructions in your prompt about the year, photographic style, colors, hairstyles, and surroundings, while ensuring your identity and recognizable features are preserved.
Specifying the photographic look helps achieve the aesthetic qualities of the 1980s, such as analog film grain, faded colors, and characteristic lighting, which are crucial for creating a convincing vintage image.
Your prompt should ask the AI to retain your identity, facial features, skin tone, age, and recognizable appearance while modifying elements like clothing, accessories, and surroundings for an authentic 1980s look.
Including modern elements, such as contemporary clothing or objects, can quickly undermine the retro effect, making the image appear less authentic and more like a modern creation than a true 1980s photograph.
OpenAI has shared a prompt that users can use to recreate their appearance in a mid-1980s setting.
The prompt asks ChatGPT to retain the person's identity and key facial characteristics while changing elements such as their hairstyle, clothes, accessories and surroundings to reflect the period.
"Using my uploaded photo, show me what I would have looked like around 1985. Preserve my identity, facial features, skin tone, age, and recognizable appearance. Reimagine my hair, clothing, accessories, and surroundings with bold, unmistakably mid-1980s styling - expressive silhouettes, statement accessories, layered details, distinctive colors, and textures. Make it feel like a genuine 1985 photograph with analog grain, faded color, direct flash, and subtle softness. Add a period-accurate 1980s red-orange date stamp in the lower corner. No modern objects or text.”
Simply telling ChatGPT to “make my photo look like the 80s” may not provide enough direction for the image.
A more detailed prompt can specify the decade, photographic characteristics, clothing, hairstyles, lighting, colours, surroundings and other elements that should appear in the final image.
The clothes and hairstyle alone do not necessarily make an image look like it was photographed in the 1980s.
Details such as analog film grain, faded colours, direct flash and slight softness can help establish the intended vintage photographic aesthetic.
AI-generated transformations can alter facial characteristics if the prompt focuses too heavily on changing the person's appearance.
OpenAI's prompt specifically asks ChatGPT to preserve the user's identity, facial features, skin tone, age and recognizable appearance while modifying the styling around them.
A contemporary object can quickly undermine the retro effect.
Users should be specific about removing or avoiding things that would not fit the intended period, such as smartphones, modern clothing, contemporary backgrounds or other recognisably modern elements.
OpenAI's suggested prompt explicitly states: “No modern objects or text.”
Changing the person without addressing the setting can produce an image where the subject looks vintage but the background remains contemporary.
For a more cohesive result, the prompt should also establish the desired 1980s surroundings and visual context.
Adding too many exaggerated retro elements can make the result look like an AI-generated interpretation rather than an old photograph.
The objective of the trend is generally to recreate the appearance of an authentic period photograph, so visual details should work together rather than overwhelm the original subject.
Accessories, colours, textures, hairstyles and clothing silhouettes can all influence whether an image convincingly evokes the 1980s.
OpenAI's prompt, therefore, calls for “statement accessories, layered details, distinctive colours, and textures” alongside the broader styling changes.
The key is to give ChatGPT enough information about what should change and what should remain unchanged.
Users can specify the approximate year, photographic style, lighting, colours, clothing, hairstyle, surroundings and film characteristics. At the same time, they can explicitly ask the tool to retain their identity and recognisable facial features.
The result can then be further refined with additional instructions if certain elements do not match the intended period.
For users participating in the viral trend, the difference between a generic “old photo” and a convincing 1980s recreation largely comes down to the level of detail included in the prompt.
Anjali Thakur is a Senior Assistant Editor with Mint, reporting on trending news, entertainment and health, with a focus on stories driving digital conversations. Her work involves spotting early signals across news cycles and social media, sharpening stories for SEO and Google Discover, and mentoring young editors in digital-first newsroom practices. She is known for turning fast-moving developments—whether news-driven or culture-led—into clear, tightly edited journalism without compromising editorial rigour.<br><br> Before joining Mint, she was Deputy News Editor at NDTV.com, where she led the Trending section and covered viral news, breaking developments and human-interest stories. She has also worked as Chief Sub-Editor at India.com (Zee Media) and as Senior Correspondent with Exchange4media and Hindustan Times’ HT City, reporting on media, advertising, entertainment, health, lifestyle and popular culture.<br><br> Anjali holds a Bachelor of Arts degree from Miranda House, and is currently pursuing an MBA, strengthening her understanding of business strategy and digital media economics. Her writing balances newsroom discipline with a clear instinct for what resonates with readers.
Oops! Looks like you have exceeded the limit to bookmark the image. Remove some to bookmark this image.