Thank you. I just found this additional info on huggingface:
An NVIDIA GPU with CUDA support is required.
- The model is tested on a single 80G GPU.
- Minimum: The minimum GPU memory required is 60GB for 720p.
- Recommended: We recommend using a GPU with 80GB of memory for better generation quality.
Wont they take your money before the VPN is disabled/undetected?
Not choosing to vote [...] is endorsing the establishment.
Where is the logic in that? By voting you're actively acknowledging the legitimacy of the State. How would not voting be an endorsement of anything, as you see it?
This looks great! Any idea of realistic hardware requirements?
Do you see installing a .dmg file (or installing through homebrew) on macOS as a workaround, or what do you mean? I'm not sure I have ever installed a single app from their store, so maybe it's just that such a "workaround" feels normal to me, but scary to others?
Red Pavilion with Pool
Or red pool with pavilion? Hmmm...
Have you been using Postiz? I'm curious about their built-in AI features, but haven't been able to find more info on it. Do you happen to know how they implemented it, and is it actually useful? Is it running local models on the server for text and image generation, or is it calling some proprietary APIs for that?
I installed this by adding the github URL to Obtainium. It was very easy to set up, and worked fine in my brief testing. Thanks for the recommendation.
Does the PDF contain all the products of all the brands associated with each top-level US company (owner)? If not, the LLM can help finding the connections between product/brand and US-based owner, given that it was trained on data about those relations. However, if the relevant training data is lacking or faulty, it could also sometimes result in wrong answers... (but with confidence!)