Giving old Illustrator characters a second life in 3D.
Years ago I drew a small cast of flat, vector-style characters in Illustrator and Photoshop. One weekend I fed them into Nano Banana, Google’s Gemini image model, just to see what would happen. Could it keep the same pose, personality, and silhouette but render them soft and dimensional, without me redesigning anything?
Before & after
Same character, same pose, new dimension.
I wanted to keep every illustration’s original pose, outfit and expression, and let the render add real fur, fabric and light. Drag each image to compare.
Fluffy: The flying cat
Fluffy has been floating through my sketchbooks for years. A round, sleepy tabby who drifts through the clouds like a stray balloon, more curious than worried about where he'll land.
Beyond the still render, Fluffy also got a short animated clip, drifting through the same clouds.
Two more clips drop Fluffy out of the clouds and into a city park.
He waves with both paws up, arms outstretched, same as the original pose.
Nano Banana
IllustratorLook closely and the proportions haven't budged: same round belly, same tabby stripes, same red sneakers. The fur is the only thing that's new.

Detail: fur, fabric, and light the original flat illustration never had.
Franky: The wolf on a bike
Franky is the neighborhood wolf everyone's actually glad to see. Scarf on, basket loaded with treats, always pedaling snacks over to share instead of chasing anyone down.
Another clip rides Franky across the bridge of Furville, basket and all.
Nano Banana
IllustratorThe cap sits at the same angle, the ears the same shape, the grin the same size. It's the coat and the light that make him look real.

Nano Banana also dropped Franky into a full scene. Same wolf, same bike, a country road to ride down.
When they met
One last generation for fun: Fluffy and Franky, together in the same frame.
A bonus clip puts them in the same scene. Franky rides up to Fluffy by the fountain, and they stop for a hug.
The approach
The original drawings went in as references.
Character identity first
I uploaded each original illustration as the reference, so the model had the actual silhouette, colors and outfit to match instead of inventing its own version of the character.
Same pose, new material
The prompts stayed focused on rendering treatment: fur, fabric, light, depth. I kept explicitly asking it to preserve the pose and composition, so Fluffy still floats through the exact same clouds and Franky still grips the same handlebars.
Where it needed a hand
Backgrounds, framing, and a few proportions still needed manual cropping and picking between generations. Characters usually came out right on the first try. Full scenes took more attempts.
Closing note
A weekend experiment.
It started and ended that weekend: a few old characters and a lot of prompting. If you want to talk through the workflow or try it on something of your own, I’m happy to chat.