Those might just be LoRA merged models, not full fine-tuning. From what I heard, fine-tuning doesn’t work because the models are distilled. You’d have to find a way to undistill them to train them.
Last I heard, LoRAs cause catastrophic forgetting in the model, and full fine-tuning doesn’t really work.
You can never learn anything with these clickbait headlines.
I don’t think so. They’re going to have to do a lot better than a tutorial to win people back. That said, the two Flux models being distilled making them close to impossible to fine-tune sucks too.
Or just not show people what you’re typing.
I can’t tell if this is a joke or not.
The way you described is already how Civitai works. Maybe it’s to keep the moderation of the two sites cleanly separated. This way the team on green can do what ever they want, on green.
A computer like that is useful outside of work. I’d pay for it out of pocket if I had to.
You keep moving the goal posts and putting words in my mouth. I never said you can do new things out of nothing. Nothing I mentioned is approaching, equaling, or exceeding the effort of training a model.
You haven’t answered a single one of my questions, and you are not arguing in good faith. We’re done here. I can’t say it’s been a pleasure.
Do you have any examples of how they fail? There are plenty of ways to explain new concepts to models.
https://arxiv.org/abs/2404.19427 https://arxiv.org/abs/2406.11643 https://arxiv.org/abs/2403.12962 https://arxiv.org/abs/2404.06425 https://arxiv.org/abs/2403.18922 https://arxiv.org/abs/2406.01300
What kind of creativity are you talking about then? I’ve also never heard of a bloated model. Which models are bloated?
But at what point does that guidance just become the dataset you removed from the training data?
The whole point is that it didn’t know the concepts beforehand, and no it doesn’t become the dataset. Observations made of the training data are added to the model’s weights after training, the dataset is never relevant again as the model’s weights are locked in.
To get it to run Doom, they used Doom.
To realize a new genre, you’ll “just” have to make that game the old fashion way, first.
Or you could train a more general model. These things happen in steps, research is a process.
There are more forms of guidance than just raw words. Just off the top of my head, there’s inpainting, outpainting, controlnets, prompt editing, and embeddings. The researchers who pulled this off definitely didn’t do it with text prompts.
I mean, you’ve never seen a purple elephant with a tennis racket. None of that exists in the data set since elephants are neither purple nor tennis players. Exposure to all the individual elements allows for generation of concepts outside the existing data, even though they don’t exit in reality or in the data set.
If you’re on Windows, you should return it before it’s too late. It isn’t going to get better.
Yeah, I didn’t notice the login since I was signed in.
Oh, that makes sense.
I don’t really know myself. I assumed it would install and update stuff for you.
That was really cool.