Disco_Diffusion_Local VS ru-dalle

I am using Ubuntu, Anaconda, and all installs as GitHub instructions say: https://github.com/MohamadZeina/Disco_Diffusion_Local

I tried DD on a Colab notebook but wanted to run it locally for faster render times. I’m now trying to use this package to run DD locally.

Initially I used this guide to setup a pytorch wsl environment but I installed a newer anaconda version (should be self explanatory when you reach this step), this environment works also fine for the newer DD 5.6 and my fork too.

I just followed the tutorial from MZ (https://github.com/MohamadZeina/Disco_Diffusion_Local) even if I never touched anything similar in my life (just have an artist background why I’m interested in doing more AI generated Art)

I used this repo to setup a local 5.2 instance.

Here’s a guide on how I ran this locally on my windows machine :). After I wrote this I saw that something similar has been posted here already - my approach is slightly different so some may find it useful.

It’s a custom trained model, built in rudalle https://github.com/ai-forever/ru-dalle

It's a custom model, built from rudalle

ru-dalle has had that feature for quite a while, as it was their first inpainting example notebook:

GitHub repo.

Colab notebook. There are actually 5 models, but I doubt the 12B parameter Kandinsky model is actually available per looking at this code.

This was made with a mini version of DALL-E: ruDALL-E

Specifically, I fine-tuned ru-DALLE using a dataset consisting of ~1000 images of imperial denarii (ranging from Augustus through Maximinus Thrax) coupled with descriptions of each coin grabbed from OCRE. For example, the obverse description of this coin would be "Head of Augustus, bare, right" and the reverse description would be "Round shield, spear-head, and curved sword".

One way to use the version 3 model is to use this official Colab notebook linked to in the ruDALL-E GitHub repo. I recommend making the changes mentioned in this post. If you want to use the older version 2 model with this Colab notebook, change 'Malevich' to 'Malevich_v2' in line "dalle = get_rudalle_model('Malevich', pretrained=True, fp16=True, device=device)" (relevant source code).

# !pip install rudalle==0.0.1rc8 > /dev/null !pip3 install git+https://github.com/sberbank-ai/ru-dalle.git@feature/new_malevich