gen‑ai.news
← Back
Image

Google is preparing Nano Banana 3 Pro upgrade

Google is preparing Nano Banana 3 Pro upgrade

Code references discovered by TestingCatalog suggest that Google is quietly developing a new image generation model internally dubbed GemPix 3 Pro. The references indicate the model is built on Gemini 4 Argon, which would make it part of Google's next generation of foundation models. The trail leads to what is expected to become Nano Banana 3 Pro, an upgrade to Google's existing Nano Banana line.

Nano Banana is Google's branding for on-device AI experiences, typically optimized to run efficiently on Pixel hardware without relying entirely on cloud processing. A "Pro" tier within that line suggests Google is aiming to push the quality ceiling for locally run image capabilities, potentially bringing more detailed or higher-fidelity outputs to supported devices.

GemPix, as a naming pattern, appears to be Google's internal label for Gemini-based image models - a counterpart to the text-focused Gemini variants. If GemPix 3 Pro is indeed grounded in Gemini 4 Argon, it would represent a meaningful step up from whatever architecture currently underpins image generation in the Nano Banana 2 generation, inheriting improvements in reasoning and multimodal understanding from the broader Gemini 4 family.

No release timeline or feature specifics have been confirmed by Google. Findings like these, surfaced through app teardowns and early code analysis, often precede official announcements by weeks or months - and do not always result in a public launch in the exact form described. Still, the breadcrumbs point to Google continuing to invest in on-device generative image capabilities, an area where competitors like Apple and Qualcomm are also making steady progress.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

ARRI’s Film Lab Adds 8mm, 16mm, and 65mm Film Looks With This Major Update
Image

ARRI’s Film Lab Adds 8mm, 16mm, and 65mm Film Looks With This Major Update

ARRI has released version 1.5 of its Film Lab OpenFX plugin, a substantial update that expands the tool's analog film simulation beyond its original 35mm base to include 8mm, 16mm, and 65mm formats. The update also brings faster processing, new grain controls, and anamorphic squeeze options. Existing license holders can upgrade at no cost through RE:Vision Effects.

Apple, Content Authenticity, and the War to Prove What’s Real
Image

Apple, Content Authenticity, and the War to Prove What’s Real

As AI image generators make photorealistic fabrications increasingly easy to produce, the question of how to verify that a photograph reflects something that actually happened has become more urgent. Apple is among the players now engaging with content authenticity efforts aimed at answering that question. This piece from PetaPixel explores the tools and standards being developed to establish trust in visual media.

No image
Image

Alibaba Qwen Releases Qwen-Image-2.1-Turbo, an 8-Step 7B Image Model

Alibaba's Qwen team has released Qwen-Image-2.1-Turbo, an accelerated variant of its open-weight image model that generates and edits images in just 8 denoising steps, down from the 40-step default of the base model. The 7B-parameter architecture remains unchanged, meaning the speed gains come from a distilled inference process rather than a smaller model. A hosted API option accompanies the open-weight release.