Most of that just looks like carpet shading, where rubbing the carpet one way looks darker compared to rubbing it the other way. http://carpetswalltowall.com/shading-footprints-pooling/

However, the brown stain on the far right definitely stands out.

SD? SD 3? The weights? All the above?

Stable Diffusion is an open source image generating machine learning model (similar to Midjourney).

Stable Diffusion 3 is the next major version of the model and, in a lot of ways, it looks better to work with than what we currently have. However, up until recently we were wondering if we would even get the model since Stability AI ran out of funding and they’re in the midst of being sold off.

The “weights” refer to the values that make up the neural network. Basically by releasing the weights they are essentially saying that they are making the model open-source so that the community can retrain/fine-tune the model as much as we want.

They made a wait list for those who are interested in getting notified once the model is released, and they turned it into a pun by calling it a “weights list”.

Correction: “Weight List” ;)

Similar use cases to what I’m doing right now, running LLMs like Mixtral8x7B (or something better by the time we start seeing these), Whisper (STT), or Stable Diffusion.

I use a fine tuned version of Mixtral (dolphin-Mixtral) for coding purposes.

Transcribing live audio for notes/search, or translating audio from different languages using Whisper (especially useful for verifying claims of translations for Russian/Ukrainian/Hebrew/Arabic especially with all of the fake information being thrown around).

Combine the 2 models above with a text to speech system (TTS), a vision model like LLaVA and some animatronics and then I’ll have my own personal GLaDOS: https://github.com/dnhkng/GlaDOS

And then there’s Stable Diffusion for generating images for DnD recaps, concept art, or even just avatar images.

I’m just glad to hear that they’re working on a way for us to run these models locally rather than forcing a connection to their servers…

Even if I would rather run my own models, at the very least this incentivizes Intel and AMD to start implementing NPUs (or maybe we’ll actually see plans for consumer grade GPUs with more than 24GB of VRAM?).

Great video. Always great to learn something new.

By the way, you linked to the video with a timestamp that’s only a few seconds from the end… not sure if that was intended or not.

Yes, there are NAS grade SSD’s that can be used.

As long as you use the right kind of SSD, there aren’t any problems with doing this.