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
Jump in the discussion.
No email address required.
Notes -
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.
I highly recommend Conrad's "Making Images with Stable Diffusion" guide; it's what really got me into the hobby. Some parts are a little outdated (for example, he recommends SD 1.5 models like AbyssOrangeMix3 and RealBiter, but the meta has long since moved on to SDXL models for photorealism and Pony models for anime) but his description of the basic workflow is both excellent and still relevant.
As for software, I strongly recommend Fooocus over the standard choices of Automatic111 and ComfyUI. It's incredibly simple to set up and use; after you download, unzip, and run, Fooocus will automatically download several useful models and LoRAs into the right folders, as well as any necessary VAEs, and set them up as helpful presets. The presets include lists of positive and negative prompts to improve your images; in less than three clicks from the time you download the zip file, you can already type "forest elf" and get four stunning results. But despite this user-friendliness, Fooocus is not just a toy; it is a powerful and flexible tool that has a lot of options hidden under the hood. As you get more comfortable generating images, you can open the various menus and customize your settings, download other models, create your own presets, etc. See this guide for more.
More options
Context Copy link
More options
Context Copy link