textual_inversion VS Cold-Diffusion-Models

Checking out https://github.com/rinongal/textual_inversion, which has some possibly informative examples and scripts.

I think currently you will need about 20GB VRam..., options are: 1. https://github.com/rinongal/textual_inversion - localy

Rinongal and nicolai256 versions, the latter of which is also the one explained in Nerdy Rodent's youtube video https://www.youtube.com/watch?v=WsDykBTjo20, work but they also have an issue of lacking editability in comparison to one made by huggingface's collab which is followed up in a very long issue on Rinongal's Github. You can add accumulate_grad_batches: 4 to the end of the finetune files like shown in Nerdy Rodent's video at this time stamp to try to alleviate this issue, but the quality isn't as good as one made in the online collab.

That may mostly solve that but it’s too early right now: https://github.com/rinongal/textual_inversion

For fun I tried to make an entire animated music video but it took over one week of processing and basically fell apart coherently by 30 seconds so just did one third:

https://youtu.be/f3GfUKJBUYA

The huggingface models don't work with the local stable diffusion, only the models trained locally with this repo https://github.com/rinongal/textual_inversion can be installed, at least for now.

Sure you can. You might be interested in cold diffusion (https://arxiv.org/abs/2208.09392) which tries doing a bunch of different kinds of degradation processes besides adding gaussian noise. You can kind of choose whatever input corruption process you want and teach the model to reverse it, and it works kinda well (I think gaussian noise might be better though)

I wrote a response yesterday but did not post it or send it, ops.

I still don't understand the problem, if you ask model trained on a noise pattern "trees" for a forest it will still give you a random forest, that's what it was trained on, also: https://arxiv.org/abs/2208.09392, to see the diffusion process applied to processes other than Gaussian noise.

What about this research: https://arxiv.org/abs/2208.09392

Found relevant code at https://github.com/arpitbansal297/Cold-Diffusion-Models + all code implementations here

This claims to explain diffusion models from first principles, but the issue with explaining how they work is we don't know how they work.

The explanation in the original paper turns out not to be true; you can get rid of most of their assumptions and it still works: https://arxiv.org/abs/2208.09392

Check out the cold-diffusion repo, which has nice clean implementations, and also is useful in pointing out that the multi-step computation idea isn’t limited to denoising. https://github.com/arpitbansal297/Cold-Diffusion-Models