discoart VS disco-diffusion

Just look at basic Python syntax and read through the discoart readme and it should all make sense :). If you still get lost, me and other people are always here to help more

just install latest Python from official page, then PyTorch from here (make sure it's some of the CUDA versions) and then follow the steps here and you should be good to go

discoart is a python library that significantly simplifies interacting with disco diffusion. Install the library with pip, a single import statement, and call the create() function and you're running. I've used it with a Google Colab sheet set to use a GPU runtime and had a good time generating until I hit Big G's limits.

try out discoart! Takes a bit of practice though

It's part of my fork of DD 5.6 and listed in the tutorial section, if someone want to take a look, it's here

I integrated 9 additional models in my 5.6 fork here and it would be neat to have a nice gui, the basic jupyter server browser interface isn't nice at all.

I did a fork of 5.6 and included 9 additional models, maybe you want to do this too. If you want to take a look, it's here

It's open on colab or take a look at the Github page. Colab is linked, so if anything changes on Github, the Colab notebook is updated along.

I've added a few new models to the test-new-models branch of my 5.6 fork. Not sure if this is what you are looking for. Make sure to use the new_models notebook if you want to have a look.

I integrated it in my fork of 5.6 in the test-new-models branch along with other new models like Kaliyuga 'lithography_diffusion / medieval_diffusion', BrainArtLabs 'liminal_diffusion_v1 / liminal_diffusion_source' as well as the new 'portrait_generator_v1.5' from Felipe3DArtist. Link to repo if anyone is interested.