News for hackers. Stuff that matters.
Re:Remove AI Watermarks by Tiberium on Tuesday May 19, 2026 @06:52PM (#48200752)
This is a bit misleading as for Gemini it only properly removes the visible watermark. To remove SynthID it has to regenerate the image at low noise with SDXL, which will likely destroy a lot of small details, plus won't work for higher res properly (NB2 and GPT Image 2 support up to 4K image outputs)
Re:Remove AI Watermarks by gpt5 on Tuesday May 19, 2026 @07:00PM (#48200821)
Nano Banana 2 only supports 1K resolution (1024x1024) natively. Anything above that is upscaling. So this matches SDXL. GPT Image 2 does support 4k natively (but experimentally).
Re:Remove AI Watermarks by vunderba on Tuesday May 19, 2026 @07:09PM (#48200886)
Where did you get that info from? According to Google's own docs as well as my own image generation tests via the API, it supports up to 4K natively for gemini-3.1-flash-image-preview (aka NB2).

It just defaults to 1K. But I didn't see anything in the docs stating that it's just a simple upscale for larger resolutions.

https://ai.google.dev/gemini-api/docs/image-generation#gener...

Re:Remove AI Watermarks by gpt5 on Tuesday May 19, 2026 @08:47PM (#48201639)
From: https://aistudio.google.com/models/gemini-3-pro-image

> Produce production-ready assets with native 1K output and built-in upscaling to 2K and 4K resolutions

The API doc you linked is misleading.

Re:Remove AI Watermarks by vunderba on Tuesday May 19, 2026 @09:30PM (#48201939)
Yeah - if that's true then it's even worse because the output price says

  $0.067 per 1K image*, $0.101 per 2K image*, and $0.151 per 4K image*.
But if all the "compute time" is spent on a 1K image and they're just passing it to a ESRGAN or other upscaling technique, then there’s literally zero reason to generate anything above 1K. Just save the money and upscale it yourself.
Re:Remove AI Watermarks by Tiberium on Tuesday May 19, 2026 @10:11PM (#48202259)
It's not upscaling for NB2, 4K outputs are very different from 1K, and output tokens count is also different.
Re:Remove AI Watermarks by ls612 on Tuesday May 19, 2026 @07:41PM (#48201165)
Is SDXL still the best local image model all these years later? Damn, that’s sad…
Re:Remove AI Watermarks by vunderba on Tuesday May 19, 2026 @08:00PM (#48201311)
With the number of fine-tuned LoRAs and checkpoints - from a realism standpoint, yes SDXL is still very viable. From a prompt adherency perspective, absolutely not.

Qwen-Image-2512 / Z-Image / Flux.2 absolutely crush SDXL if you're actually generating moderately complex scenes.

Re:Remove AI Watermarks by ls612 on Tuesday May 19, 2026 @08:08PM (#48201354)
Do you still need a wacky backend to run them locally or does LM Studio make it easy nowadays? Last I use a local diffusion model was late 2022.
Re:Remove AI Watermarks by vunderba on Tuesday May 19, 2026 @09:33PM (#48201966)
So I use a combination of Neo Forge and ComfyUI. Forge has an easier learning curve but ComfyUI gets all the new "hotness" almost immediately since there's so much custom nodes for it.

If you're on a Mac, I've heard that Draw Things is supposed to be pretty "batteries included" simple for image gen along the same lines as LM Studio.

https://github.com/Haoming02/sd-webui-forge-classic/tree/neo

https://github.com/Comfy-Org/ComfyUI

https://drawthings.ai

Re:Remove AI Watermarks by Tepix on Wednesday May 20, 2026 @04:42AM (#48204799)
It claims to remove SynthID also.