I’m testing the Google Gemini 2.5 “Nano Banana” artificial intelligence engine in Photoshop’s latest beta release, with unreal results. Its focus on editing images over conjuring them is more useful professionally and ethically, offering repeatable output while retaining facial detail. Seeing old newsprint photos leap off the page in sharp color can bring a tear to your eye.
A.I. creations don’t belong in portfolios because we can’t take much credit. Though these source images were mine, I’m just typing specific instructions to modify them. Results are like a slot machine eating credits with hopes for each new iteration generated. Most were complete in one pass with minimal spot edits because it’s very responsive to cinematic and artistic terminology like lens/lighting specs, tone/texture, and color discipline. Overlaid text clarifies what else I generated besides the obvious subject treatment. Some of the originals live on my Photography page if wanting before/after comparisons. These are extreme examples, yet subtle adjustments are also possible.
We’ll start with a few old family photo retouches, followed by artistic treatments in every style I could think of. Applying combinations intelligently follows the actual strokes and geometry of a scene, so lighting and shadows harmonize. I’m surprised how closely it obeys when prompted to render trademarked content, though it will alter quoted text in certain contexts, as well as “slop” existing text.
UPDATE: I continue to edit and sort this gallery months later, trying not to repeat looks and moving new favorites up front.
