fast-stable-diffusion
fast-stable-diffusion copied to clipboard
TheLastBen
fast-stable-diffusion + DreamBooth
Hello, I'm getting this error in colab. Steps: 3% 46/1600 [01:15
Could we get the version as an option? It doesn't have to be a UI item, can just be a variable for us to change. Currently it's not too hard...
Edit: sorry for bad title – cannot correct it Hi, I did a classical training (Dreambooth with class images – _not_ the new Fast Method) and tripped on __ Test...
can someone help e figure this out? since the updates things are acting really weird sometimes i can generate 1-2 images before the errors begin, other times it begins at...
I used 4 different subjects, with unique names, and high quality/cured 30 photos each using the recommended settings, however the results with multiple samplers, cgf scale and steps, do not...
mentioned this before but got no help. there are NO ERRORS. prior preservation is always set to YES, but the code always runs the "if prior preservation=NO" section of code....
Can you add the possibility to train several subjects using a json like in https://github.com/ShivamShrirao/diffusers/commit/351f3b6206f0453706346fd34a337cdf6ac6ef07. The captioned images look unnecessarily complicated unlike this commit where you just have to specify...
where will it be saved when i choose to save every 500 steps? thanks
Hi. I updated the notebook to the latest changes which include using the 1.5 model and the VAE usage improvements, but when I trained a model (tried 1500 and 3000...
This makes all notebooks universal. Instead of just using the colab folders, this uses `os.getcwd()` to get the folder it's started in and sets `working_dir` to that, then bases everything...
