stable-diffusion VS long_stable_diffusion

1. git clone https://github.com/neonsecret/stable-diffusion 2. pip install --upgrade -r requirements.txt 3. conda env create -f environment.yaml

neonsecret's fork is the only one I can get to run on my 4gb GeForce GTX 1050 Ti. I also use OptiomizedSD "just" the optimizedsd scripts folder copied over to neonsecrets. I've never been able to get automatic1111's fork to work for me.

You can also clone neonsecret's version of optimized repository, if you want a better GUI, or use Arki's guide for AUTOMATIC1111's repo, which also has an optimized mode, and is pretty feature-packed.

sd gui

Hey guys, today I produced the first ever 4k image using this: https://github.com/neonsecret/stable-diffusion/

https://github.com/neonsecret/stable-diffusion/ https://github.com/neonsecret/neonpeacasso I have two of those, for both low-end and high-end GPUs

using https://github.com/neonsecret/stable-diffusion

Open source: https://github.com/sharonzhou/long_stable_diffusion

Stable Diffusion outputs images

Open source: https://github.com/sharonzhou/long_stable_diffusion

Here's a published story, illustrated by this repo, titled "Never Hire a Herd of Goats to Mow your Lawn": https://storiesby.ai/p/never-hire-a-herd-of-goats-to-mow

That story is AI-written, AI-narrated, AI-illustrated story, which a couple friends and I have been generating.

An earlier story made the top of HackerNews a week ago: https://news.ycombinator.com/item?id=32652673. I was too slow to illustrate that earlier week's piece, so it became clear to me that I had to automate myself with this repo... definitely not overengineering the solution.

Anyways, hope you like it or parts of it. Pull requests veryyyy welcome. This was just a weekend project to keep my GPUs company.

Tweet with more stuff, if at all interesting: https://twitter.com/realSharonZhou/status/156703103573259468...