| ▲ | Tiberium 5 hours ago |
| 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) |
|
| ▲ | gpt5 5 hours ago | parent | next [-] |
| 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). |
| |
| ▲ | vunderba 5 hours ago | parent | next [-] | | 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... | | |
| ▲ | gpt5 3 hours ago | parent [-] | | 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. | | |
| ▲ | vunderba 2 hours ago | parent [-] | | 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. |
|
| |
| ▲ | Tiberium 2 hours ago | parent | prev [-] | | It's not upscaling for NB2, 4K outputs are very different from 1K, and output tokens count is also different. |
|
|
| ▲ | ls612 4 hours ago | parent | prev [-] |
| Is SDXL still the best local image model all these years later? Damn, that’s sad… |
| |
| ▲ | vunderba 4 hours ago | parent [-] | | 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. | | |
| ▲ | ls612 4 hours ago | parent [-] | | 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. | | |
|
|
