After Ghibli-style images earlier in the year, a new trend has engulfed social media, where users are generating 3D model images of themselves using Google’s new and powerful Gemini 2.5 Flash model, AKA Nano Banana. The new model, which was released to the public last month, has quickly garnered praise for its ability to help users make complex changes in their images with natural language prompts.
While OpenAI’s ChatGPT also possesses similar capabilities, the chatbot often takes a few minutes to generate images, while in my experience, Nano Banana is able to accomplish the same task in seconds. Moreover, Nano Banana is also better at creating photorealistic images and offers superior editing features like removing spots, coloring photos, or altering elements, all while preserving the quality of the original image.
If that wasn’t enough, the Nano Banana model also allows up to 100 image generations per day for free users. Meanwhile, ChatGPT not only takes longer to generate images but also reaches its image generation limits usually after 3-4 images.
Gemini 3D Model Trend
Open any social media app at the moment, and all you see are the photorealistic 3D models people have created of themselves. And if you have been struggling with getting the details right in your edits or if you are trying to generate the 3D model images for the first time, you’ll want to check out the next few steps very closely.
How to Generate 3D Model Images Using Gemini Nano Banana AI?
Open the Gemini app.
Tap on the Gemini Nano Banana icon and upload your desired image.
If you already have an idea of how you want your image to look, enter the exact prompt, or you can just follow any of the three prompts below to get the desired look.
1) “Use the supplied photo as the primary reference for face, hair and posture. Generate a 1/7-scale, fixed-pose collectible figurine (high-quality PVC/resin look) of the subject in modern streetwear — backpack, coffee cup in hand — standing on a round transparent acrylic base (no text or logos). Place the figurine on a real wooden computer desk. To the left, a widescreen monitor shows the 3D modelling process of this very figurine (wireframe viewport, material/shader node editor, object hierarchy and a small thumbnail of the reference photo). To the right, a premium toy packaging box sits upright — high-quality collectible style with flat 2D illustrations (orthographic front/side/back line art), matt cardboard texture and spot varnish on the photo panel. Lighting: warm desk lamp key, soft overhead fill, subtle rim light; camera: 35mm full-frame equivalent, f/2.0, shallow depth of field so the figurine is tack-sharp and background soft. Render photoreal, true skin tones, micro-detail on fabric, realistic paint finish on sculpted details. No text on the acrylic base; no watermarks”
2) “Use the supplied photo for exact facial likeness. Create a 1/7-scale limited-edition painted figurine with a specially curated paint job — subtle metallic flakes in jacket paint, hand-painted shading on face — fixed pose on a clear round acrylic base (no text). Arrange the figure on a real desk; the monitor shows the 3D modelling process (high-poly sculpt, texture paint layers, and a clay preview). Next to the monitor, a deluxe collector box features flat 2D hand-drawn illustrations (orthographic views and a small painted portrait spot) printed on textured board with visible emboss/spot varnish effects. Lighting: refined studio key + back rim, camera 85mm crop to 16:9, f/2.8 for buttery bokeh, emphasise paint texture and artisan finish. Photoreal, commercial catalogue quality.”
3) Based on the uploaded photo, create a 1/7-scale collectible of the subject as a (your profession): smart casual blazer over tee, press lanyard, tiny laptop accessory. Place on a round clear acrylic base (no text) on an office desk with a keyboard and notes. The computer screen shows the modelling process (viewport with wireframe and material slots, render preview window). Collector box to the side carries flat 2D editorial illustrations and a clean, premium layout printed on high-quality cardboard. Lighting: neutral daylight + soft desk lamp; camera 50mm, f/2.0, crisp detail in fabric weave and printed lanyard text (legible at close crop). Photoreal, editorial product shot.”
Pro Tip
In case you want to get rid of the Gemini watermark at the bottom-right corner or if you want to increase the detailing in your images, you have the option of using another AI tool.
All you need to do is download the Qwen app or open the Qwen website, and complete the sign-in process. Now, start a new chat, click on “Image Edit,” and upload the 3D model image.
Now give this prompt to the model: “Remove the Gemini logo at the bottom right and enhance the resolution while keeping all other elements exactly the same.”
