The internet buzzes with a new trend of transforming personal photos into vintage and retro-style portraits, complete with aesthetic lighting and mood. Google Gemini has been impressively accurate when generating these portraits.
We have experimented with multiple instructions and even put together a guide to help create these looks. In this article we also compare chatgpt and gemini to see which better images produces and which records Pinterest atmosphere.
Our experiment: AI portraits in retro style
We have experimented by generating the 90s-inspired viral retro-style AI portraits of two characters, a man and a girl, with the same prompt on both AI platforms. The results turned out to be surprisingly different. View the instructions and the portraits made by Chatgpt and Gemini.
Results: Gemini vs. Chatgpt
Gemini delivered flawlessly manufactured retro portraits that really recorded the 90's aesthetics and at the same time kept the Pinterest-like atmosphere intact. Chatgpt, on the other hand, changed the features of both the male and female characters.
Another difference was in the processing time, Chatgpt took about 5-7 minutes to generate the images, while Gemini completed the task in less than 30 seconds. That said, Chatgpt has a commendable work with the background and lighting, which was well in accordance with the promptly given.
FAQ
What Gemini Ai does
Image generation: Gemini can produce images with high resolution based on prompts, such as vintage portraits, cinematic effects or 3D style figures.
Visual styles: it can emulate specific art styles, lighting, eras (such as polaroid vibes from the 70s or 1970s) and textures.
Direct output: You get a real image file that you can download or post.
What chatgpt does
Making prompt: it can write detailed, creative prompts that Gemini (or an image AI) tell exactly what to generate.
Image descriptions: it can describe a scene, mood, lighting and style in text in as much detail as necessary.
Ascii or concept sketches: Moreover, the Platform of OpenAI can produce very simple visualisations in text, but not of high quality images.
What Chatgpt can't do
It cannot immediately generate high-res images such as Gemini or Midjourney. It can only guide or create the instructions for an AI.
So consider it essentially as your AI director: it makes the vision, style, mood and instructions. Gemini is the AI painter who visually brings them to life.
Note: Both images that used the comparison are generated themselves.
