There have been a lot of Pixel leaks today, and now we have another one. This is all about the camera features of the Pixel 10 and Pixel 11, which unsurprisingly have AI.
But let’s start with the hardware first. The Pixel 11 Pro, due in 2026, is expected to have a next-generation telephoto camera, one that will use the hardware in combination with AI features to provide 100x zoom for both photos and videos.
Cinematic Blur will also be updated on the Pixel 11 Pro, with support for 4K30fps and a new “video relight” option that does what it implies: changes the lighting conditions in videos. This is made possible by a Cinematic Rendering Engine in the Tensor G6‘s image signal processor, which also reduces the power consumption of blurred shots by almost 40%.
Ultra Low Light video is also coming to the Pixel 11, and this is also called Night Sight video. While Night Sight video already exists, the current implementation relies on the cloud for processing, while the Pixel 11 will run entirely on-device. The intended ambient light level for this is around 5 to 10 lux.
Now let’s go back to 2025 and the Pixel 10. This series will be powered by the Tensor G5 SoC, which enables “Post-capture Generative AI-based Intuitive Video Editing for the Photos app”. This could also be available for YouTube Shorts.
Speak-to-Tweak will be a new AI feature for photo editing, and Google is also working on Sketch-to-Image, which is essentially the same thing Samsung’s Galaxy AI already offers. There will also be a “Magic Mirror” feature, but it’s unclear what this is, while the Tensor G5 should also be able to run Stable Diffusion-based models locally, which could be used in the Pixel Studio app.
The Tensor G5 will finally add support for 4K60fps HDR video, compared to the Tensor G4’s 4K30fps HDR video.