IMO the "safety" in Stable Diffusion is becoming more overzealous where most of my images are coming back blurred, where I no longer want to waste my time writing a prompt only for it to return mostly blurred images. Prompts that worked in previous versions like portraits are coming back mostly blurred in SDXL.
If this next version is just as bad, I'm going to stop using Stability APIs. Are there any other text-to-image services that offer similar value and quality to Stable Diffusion without the overzealous blurring?
Edit:
Example prompt's like "Matte portrait of Yennefer" return 8/9 blurred images [1]
It’s a play for dev mindshare where they get to control the platform and have access to devs using their software, they have no intentions of making money from it directly only to maximize its appeal & marketshare. It’s a cross-platform dev environment they can easily deliver extensions to connect to their commercial products.
There’s no point in them continuing to invest in fragmenting the dev community by developing 2 competing platforms now that they own GitHub so I’m not expecting to see any increased investments in Atom.
I’m definitely one of them, I refuse to play any IAP games as I view them as a Trojan virus social engineering experiment (masquerading as a game) designed to trick you into maximizing their IAP revenue.
An IAP-free game subscription is exactly what I’m looking for and the only thing I’ll be letting my kids play when they come of age.
and why would anyone down vote you for calling this out, like who wants to see more low effort traffic-grab posts like this?