futurevessel

Yes, same problem for me, it can eat up ~1gb of ram per generation, which is never returned to the system, so a lot of shutting down Stable Diffusion and...

Still had the same problem, nothing changed after latest git pull. Decided to reinstall from scratch, and lo and behold, no more memory leaks.

Ok, so I ran automatic1111 through this docker image: https://github.com/AbdBarho/stable-diffusion-webui-docker And it had the same problem for me, eating ram. So I went back to compare my previous installation of...

I can use Shivam's repo with 3060 12gb if I enable accelerate and 8-bit adam, I can even do 'train_text_encoder' if I enable gradient_checkpointing. I don't see this working ever...

Ah, that sounds fantastic, I would love using a 'all-in-one' solution like this repo for Dreambooth training since I do everything else with it. Was this running on 12gb without...

Pretty sure you need to convert it into 'diffusers' format, so assuming you have a terminal open in the diffusers/examples/dreambooth/ directory, you should be able to do: python ../../scripts/convert_original_stable_diffusion_to_diffusers.py --checkpoint_path...

Hmm, pretty sure this is how I did it, but I get the same error now, so perhaps something has changed or I misremembered. Have you tried having it download...

Ok, but if you just leave the --pretrained_vae_name_or_path="stabilityai/sd-vae-ft-mse" as is, it should load the VAE from the place where the download ended up, on my Linux system that is .cache/huggingface/diffusers/models--stabilityai--sd-vae-ft-mse/...

I hadn't used this repo for a while and tried to install it again, yesterday. Like you, I didn't get it to work at first, but by looking at the...