-<][ Cy ][>-

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.

Yeah, it’s insane how freaking bloated this got. No, I hadn’t written down a version number, but you can look up when Mini H3 dropped—something around that point in time. Maybe another app would work more easily. With all this bloated crap, I bet there are cleaner solutions out there. At the moment, I don’t use any generative video AI; it takes too long to generate a 14-second video.

 

Wangp was my runner i used before it was an standalone

that was pretty good to use

 

 

Bloated and unusable. It used to function properly when Mini came out—that was when I first installed it. Back then, it took around 10–12 minutes to generate something; now, it gives me estimated times of about five hours.

 

It also comes with a lot of unnecessary content preloaded.

 

Thanks.

 

I’ve already removed it, so there’s no need to troubleshoot—it’s gone.

 

Maybe this will help someone: it was functioning with 12 GB of VRAM and 32 GB of RAM, but now it’s broken and completely unusable for me. It also takes up a lot of space on your SD or hard drive.