You’re thinking too hard. Chill.

Both of them have their pros and cons. It’s a matter of sacrificing convenience or security. I2P is surely a go to for me over Tor/VPN when it comes to anonymity. You will come across variety of information which is not available on clearnet/tor, but clearnet has the upper hand in abundance.

pirates?

I was in the same circumstances when I started. But then I asked around which helped me properly configure it.

working on my end

You can find plenty of versions on Demonoid https://www.dnoid.to/. I’ve used them on bare metal and on virtualization.

I just checked my DNS blocked list. Topaz software do download their models from their repositories, but I haven’t come across any issues. About safety, well, its upto your threat model.

Its high time we add N(vidia) to GAFAM too.

I smell a puff piece. Someone is real angry.

Privacy focused frontend of YouTube

We got freetube too, you can always play on mpv

Umm… Yeah I’m not so sure. Check the prompt in the screenshot image. Although detailed, but ain’t exactly optimised for sd prompts.

Would prefer to use LLM in a manner of guiding or inspiring, but won’t crucially depend on an LLM to create prompts.

In excitement of trying out stable cascade I installed it but went out of memory. Damn!

Cool! I’ll keep making new pages as I come across new stuff!

I’ve signed up on the wiki. How do I start?

this list helped me get started with SD. Looking back it at now, I think it needs to be updated. How can I contribute?

I can’t login through the photon UI on desktop.

I had a really hard time installing the tensorRT extension for 1111

Nvm, https://www.kaggle.com/code/timothyalexisvass/latent-space-experiments

Has someone implemented this? I want to try out this shift

What I dislike about lower quantization is quality degradation. In my small experience, i find 7b models dumb (I’ve only tested Q4KM GGUF), and needed to be provided proper context before moving forward with the constructive conversation (be chat or instruct).

If this issue can be circumvented in lower quantization, I’m all in.

In context of SD, going below fp16 would only make things faster at cost of quality, and I personally like to go in depth with my prompts. For simpler prompts sure, even lighting and turbo are good in that regard.