All good. For my liking, it’s too bloated, as I already stated, and changing the settings is also a hassle if you just want to quickly spin up a short video. All that automatic stuff—like the Qwen model, which I wasn’t going to use anyway—also gets shoved into the automatic loader the first time it starts up.
As a Linux user, I don’t like things like that. Maybe make it optional, or let users choose which models to autoload (X, Y, Z, or whatever).
Maybe it switched to CPU mode? Linux can be a bit tricky with llama.cpp; it uses the CPU if you don’t keep an eye on it. That would explain the five-hour generation time on my end. I checked the terminal once, and it said GPU usage was enabled, so I don’t want to fiddle with it too much. Like I said, I wanted an easy, ready-to-use solution—not a doctorate in making short videos and all that. But it’s moved on, and that’s okay, so I’ll move on too.
Thanks, Blizzy.