site banner
ArjinFerman  Tinfoil Gigachad  3mo ago (text post)   563 thread views

Tinker Tuesday for September 9, 2025

This thread is for anyone working on personal projects to share their progress, and hold themselves somewhat accountable to a group of peers.

Post your project, your progress from last week, and what you hope to accomplish this week.

If you want to be pinged with a reminder asking about your project, let me know, and I'll harass you each week until you cancel the service

2
Top Bottom Old Controversial Comments
Jump in the discussion.

No email address required.

Now that I have a 5070 Ti I am ready to dabble with some local AI. What's a good guide for tech-literate AI n00bs? I am interested in generating images and maybe using it to classify my photo archive.

For imagegen, you've got two generalist options:

  • Automatic1111 (install guide is the moderate tech-savvy option. It's relatively easy to set up (ie, will handle your python venv and download a default model for you, though I recommend looking for more specialized models from civitai yourself after setup), and while it exposes some complicated options, you can just start with the prompt and negative prompt and get some outputs first, upscale them, and/or do basic img2img. There are some powerful options built-in, and even more with well-supported plugins, but you're not going to have to go into hackerman mode to get anything out of it.
  • ComfyUI (install guide) is the more complicated and powerful one, at the cost of being a little (more) obnoxious to work with. To do anything, you need to set up a workflow made of multiple nodes, and while they're easy to pull a simple template or to download prebuilt workflows, it can be a little overwhelming and it's always a little obnoxious to get used to. It has much wider support, and support for other types of models (eg, with plugins Wan V2V generation), and can even queue a bunch of wildly different imagegens (eg, queuing different models, settings, or even workflows), but at the cost of taking a lot more time to handle.

There are some specialty cases (eg, Wan2GP is like Automatic1111, but only for running video models on mere-mortal-level GPUs; a big stack of options for 3d model generation), but those are the big ones.

For classification and categorization, there's a lot of options, but most of them are intended to run on servers with less powerful graphics cards passively, rather than on-demand from a desktop client. The three I've tried are PhotoPrism, Immich, NextCloud Memories. All worked well enough for my purposes, but the user experience and setup difficulty is wildly different from one to the other -- I'd probably point to immich if you are okay with Docker now, and NCM if you absolutely won't, but there's a bunch of tradeoffs to each.

I'd assume there's some desktop tools for this, but I haven't found any that were good and turnkey. You do have the VRAM necessary to train your own AI classifier (I'd recommend YOLOV4 using WANB) pretty quickly if you've got the training data, but it does take a lot of preclassified photos to train it (>200 per category minimum, imo), and you'll need to do some (high-school-level, simple CSV munging) code to actually do the sorting or tagging.

What is this place?

This website is a place for people who want to move past shady thinking and test their ideas in a court of people who don't all share the same biases. Our goal is to optimize for light, not heat; this is a group effort, and all commentators are asked to do their part.

The weekly Culture War threads host the most controversial topics and are the most visible aspect of The Motte. However, many other topics are appropriate here. We encourage people to post anything related to science, politics, or philosophy; if in doubt, post!

Check out The Vault for an archive of old quality posts. You are encouraged to crosspost these elsewhere.


Why are you called The Motte?

A motte is a stone keep on a raised earthwork common in early medieval fortifications. More pertinently, it's an element in a rhetorical move called a "Motte-and-Bailey", originally identified by philosopher Nicholas Shackel. It describes the tendency in discourse for people to move from a controversial but high value claim to a defensible but less exciting one upon any resistance to the former. He likens this to the medieval fortification, where a desirable land (the bailey) is abandoned when in danger for the more easily defended motte. In Shackel's words, "The Motte represents the defensible but undesired propositions to which one retreats when hard pressed."

On The Motte, always attempt to remain inside your defensible territory, even if you are not being pressed.


New post guidelines

If you're posting something that isn't related to the culture war, we encourage you to post a thread for it. A submission statement is highly appreciated, but isn't necessary for text posts or links to largely-text posts such as blogs or news articles; if we're unsure of the value of your post, we might remove it until you add a submission statement. A submission statement is required for non-text sources (videos, podcasts, images).

Culture war posts go in the culture war thread; all links must either include a submission statement or significant commentary. Bare links without those will be removed.

If in doubt, please post it!


Rules


Recommended Posts And Communities

Recommended Realtime Chats