merge-models VS stable-diffusion

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 ?

Download this training project: git clone https://github.com/justinpinkney/stable-diffusion.git

looks like it's using the https://github.com/justinpinkney/stable-diffusion/blob/4ac995b6f663b74dfe65400285e193d4167d259c/scripts/gradio_image_mixer.py to do the bulk of the work meaning the core functionality is built into stable diffusion, seems the UI just isn't built to support it. Their ckpt is here too https://huggingface.co/lambdalabs/image-mixer/tree/main.

Any idea how to make Image Mixer work in this build? On RTX 3060 with 12Gb of memory I get the message:

References: ►Read the full article: https://www.louisbouchard.ai/imagic/ ►Kawar, B., Zada, S., Lang, O., Tov, O., Chang, H., Dekel, T., Mosseri, I. and Irani, M., 2022. Imagic: Text-Based Real Image Editing with Diffusion Models. arXiv preprint arXiv:2210.09276. ► Use it with Stable Diffusion: https://github.com/justinpinkney/stable-diffusion/blob/main/notebooks/imagic.ipynb ►My Newsletter (A new AI application explained weekly to your emails!): https://www.louisbouchard.ai/newsletter/

The notebook: https://github.com/justinpinkney/stable-diffusion/blob/main/notebooks/imagic.ipynb

There's a script for the SD --> Diffusers here: https://github.com/justinpinkney/stable-diffusion/blob/main/scripts/convert_sd_to_diffusers.py

You can start with the github which contains the code: https://github.com/justinpinkney/stable-diffusion

Hmmm, I just double checked the hashes of my local file, what's on huggingface, and what you showed above and they all match. I'm not familiar with that repo, so maybe something weird is going on. I tested it using the original txt2img script in the stable diffusion repo:

*PICK\* (Added Sep. 12, 2022) Web app Stable Diffusion Image Variations by lambdalabs. GitHub repo. Generates variations of an input image without use of a text prompt. Censored.