Monkey beer island of green and fight!

Can we appreciate the beautiful 3D printed set? Lots of time must’ve gone into modeling and printing that!

Oh boy, Quantum Leap! 🎙️Volaree…

In a totally unrelated note, https://msty.app/ is extremely easy to use and runs the LLM locally. Good choices are Llama 3.2; Granite; Deepseek r1; Dolphin 3… can run on Nvidia, Apple and cpu. They say AMD too and know how to since November but it’s not working. Not as friendly but https://lmstudio.ai/ runs on just about any hardware.

Opinion: if you go in chronological order, the age and quality will progress nicely, rather than jumping all around if you start with one then go back and do that sort of thing.

Close the iris!

Those are quite the minimum specifications to run it! Damn! Have they ever heard of “optimization”? Because in 4 minutes, SD 3.5 medium got

out of my iPhone 13 Pro, running locally… with a total of 6gb of system ram. So I’m going to say that 32 gb AND a RX 7900 are a little laughable (even if much faster no doubt).

Fair, but neither is the regular kind. Generally speaking, lasagna, tagliatelle: eggs. Spaghetti, fusilli, penne and so on: no eggs.

Edit: actually, might be worth pointing out that this is in Italy. It’s true that recipes can change wildly in different countries…

Going with no, at least if you require the “pasta” to be the same thing for both, ingredients wise.

Please notice how the spaghetti have no egg (uovo) in the ingredients, as opposed to the lasagna.

There’s coffee in that nebula!

I have a few examples that I hope retain their metadata.

Seed mode is… basically, I stopped using Automatic1111 a long time ago and kinda lost track of what goes on there but in the app I use (Draw Things) there’s a seed mode called Scale Alike. Could be exclusive, could be the standard everywhere for what I know. It does what it says, changing resolution will keep things looking close enough.

Edit: obviously at some point they had to lose the bloody metadata….

“Better quality” is an interesting concept. Increasing steps, depending in the sampler, changes the image. The seed mode usually changes image with changes in size.

So, what exactly do you mean with “better quality”?

Go down to “Bugs can optimize for bad behavior”

https://openai.com/index/fine-tuning-gpt-2/

XD

Terrible, just terrible. I’m going to share this with everyone I know.

Any programmer today would think this is incredibly quaint.

Like using a keyboard :D

This isn’t what you asked specifically, but it’s related enough… have a look into https://apps.apple.com/it/app/draw-things-ai-generation/id6444050820?l=en-GB as it’s free, ad free, free from tracking and really well optimized. With that I can run Schnell on my iPhone 13 Pro!

Yep. No artistic skills here, fun shitposts like this one for me are only fueled by some sort of generative AI. In this instance I tried a few different models (initially I got a woman with a red shirt uniform and a bee logo, then a red shirt with yellow and black highlights, a different model gave me a buff, hairy bee in a red shirt uniform… on top of the enterprise, holding a small enterprise in a hand) but had to give up and use Flux even if it’s the most intensive to run. Hardly perfect, but it’s fun and easy to recognize :)

I can see him equally well in both roles, nice idea! I’d hope for a recurring/main cast Vulcan, personally.

https://dolfin.it/it/estate-da-gelare/polaretti-fruit