waifu-diffusion VS merge-models

It's slander to say that the WD team is milking donations in the same way UD is. They already have a public working model which they are continuing to train. The WD team has also implemented features like aspect ratio bucketing into their custom trainer. If they were really milking the project for donations they would have just used the base compvis trainer it was forked from.

Use one of the original SD repos, or the code for Waifu Diffusion, or the Smirkingface refactor.

My model is based off waifu-diffusion.

waifu diffusion (free) and NovelAI (paid afaik) is what I know

This is the one I use: https://github.com/harubaru/waifu-diffusion

This is called textual inversion which use many images and a small group of promtps to describe a single element, and there are two methods: with frozen model and with unfrozen model. The first one just creates a new “word” to “guide” the model, in other words, a word that means the same as a chunk of a prompt. The resulting data is a tiny file. The second one (better known dreamboth training) adds new data to de model, so it can copy the character’s characteristics and artist style more effecively resulting in a new model file (cpkt) There are not a single tutorial, so you can find many info on r/StableDiffusion. Also, there is a third method which is based on the original training (many images and its own description) Instruction are here: Training guide I don’t know if this guide is finished though

The model is a tweaked version of waifu-diffusion using textual inversion. Still not perfect but the AI can create pretty plausible images.

Merging models takes a lot of memory and 16 GB isn't that much these days. So getting 8 or 16 more GB wouldn't be a bad idea. Can you merge 2 models? If you need to merge more than 2 maybe you could do it in stages to save memory. You could also try adapting a standalone script to merge them without loading webui.

Yes, VAEs can be merged. In fact, most scripts capable of merging checkpoints should work as-is with VAEs, since they're fundamentally very similar. Try using this script while specifying VAE files for the model0 and model1 arguments.

Once this new model is trained, you can also merge models into models: https://github.com/eyriewow/merge-models

Finally I was able to merge two checkpoints using this merge-models, Drop the two models in the same folder extracted and follow the steps, dont forget to write .ckpt in the name of the models

I'm not an expert with this, but I have been using this repo to merge models. Pretty basic process... choose two .ckpt files to combine, and specify the ratio you want to use. This is not any kind of concatenation, like an additive process where you can smush two models together without losing anything in the process. If you're looking for something like that, you'll want to look into proper fine-tuning, but that's a much more intensive process.

So, I found https://github.com/eyriewow/merge-models which merges models

According to my understanding dreambooth is a model, so using dreambooth to train stable diffusion is just combining/fusing these two models together? What' the difference between dreambooth x something vs github.com/eyriewow/merge-models ?