Neat! I’ve known that Regional Prompter is powerful, but it’s too much of a pain for me to bother using. Hopefully this makes it easier.

These aren’t exactly exploration games, but they’re simple games that my toddler likes too:

• Animal Crossing is easily her favorite. She loves “helping” my wife pick outfits and fish.
• A Building Full of Cats is short, cheap, and cute. She likes making up stories about each apartment and cat. There’s also tons of similar games in different locations.
• Cats in Time has simple puzzles that she can do with a bit of help.
• Slime Rancher might be a good fit. It’s simple and cute with a focus on exploration.
• Dorf Romantik is a relaxing and cute game that’s a good introduction to resource management. She might not be good at the actual goal of the game, but she likes placing tiles.
• Subnautica in creative mode might be interesting for exploration, depending on how sensitive your kid is about some of the darker areas and creatures.

I guess this is neat, but I don’t understand what the point is. Here’s what it says this program offers:

The program provides a digital studio environment, access to advanced AI tools and technologies, partnership with experts in the field, and opportunities for collaboration within our established artist community. It also includes a $1000 grant and promotion to our community of millions.

$1000 is nothing nowadays; I’m not sure what that would even do. Buy most of a 4090?

I already have a “digital studio environment” set up on my computer. I like it the way it is.

Partnership with experts and community collaboration are already pretty easy with social media. The generative AI community is generally helpful.

I guess this program might help people who aren’t already using generative AI get into it?

I’m all for blocking intrusive ads, but so far CivitAI’s are pretty normal. Why not support one of the biggest sites that’s helping this community thrive?

Every job will have some sort of crunch time. Even just staying in a programming position, the definition of “crunch time” will vary wildly. I’m lucky enough that “crunch time” just means that I set aside all my other tasks until I fix whatever is on fire, but I still get to go home on time unless I really want the overtime pay.

I don’t envy positions with forced 80-hour workweek crunch times. That’s a sign of bad management.

Because I am addicted to solving puzzles.

Looks like this may be a known issue for some users.

Bluey.

It wasn’t that hard if you kept feeding it quarters. It took a lot of trial and error, but having infinite lives means it was eventually beatable.

I don’t really understand the science behind it, but in my experience I’ve had much more success using basic models for training.

Also, I’ve found that LoRAs are generally much easier and faster to train than embeddings. Is there a reason you’re going for an embedding over a LoRA?

Embeddings should generally be trained on base models to improve compatibility with models derived from the base. For SD 1.5, that means using either regular SD 1.5 or the NovelAI leak. You can sometimes get away with using more “basic” models that don’t have many merges, but that can be tough to gauge.

Writing is not hardware-intensive; a Chromebook would be much cheaper if that’s all she does. What else will she use this laptop for that makes you want a MacBook?

A couple dozen devices maybe. I don’t really need dedicated ranges, but it’s nice to know exactly which device I’m looking at just by the IP when reading logs.

I know they exist and vaguely what they do, but I don’t know how to set them up. What’s their advantage over simple DHCP reservations for a small client list?

I like the range for new devices- hadn’t thought of that!

I’ve found that AI generation is good if you have a vague idea of what you want, but it can be frustrating if have something specific in mind. I try to approach generation with that in mind: I’ll plan out the large points of what I want but keep an open mind on the finer details.

If I wanted to generate a more specific image, I would first try to do a sketch in another program and then feed that into ControlNet. I haven’t actually done this though since I’m usually able to get something close enough that I can work with.

I meant the quantity of generated images, not the number of tokens. I rarely go over 50 tokens now. As you said, too many tokens and things start to interact in really odd ways. That’s why I’m not a fan of massive lists of negative tokens either; they are much more efficient as a textual inversion like badhandv4 or Easynegative.

However, I only use txt2img to get the rough composition of an image; most of my work is done in inpainting afterwards. If you’re looking to have good images just from txt2img then sometimes lots of tokens are necessary.

Just like traditional art though, this is all based on individual style. It’s important to use what works best for you.

I don’t bother with prompt enhancers any more. Stable Diffusion isn’t MidJourney; quantity is far more important than quality. I just prompt for what I want and add negative prompts for things that show up that I don’t want. I’ll use textual inversions like badhandv4 if the details look really bad. If the model isn’t understanding at all then I’ll use ControlNet.

That should be easy enough to do with a cron job. What OS is your seedbox running?

Is this Midjourney? What’s your workflow?