Image synthesis enjoyer | they/them | Not making EnEffTs. Mainly powered by Stable Diffusion and Midjourney. Diffusion studies contributor.
the parrot zone
Joined August 2021
- Tweets1.2K
- Following736
- Followers3.7K
- Likes5.4K
Pinned Tweet
Here's a brief demonstration of #stablediffusion's ability to transform initial images.
I sketched up the imgs on the left and then used them as input images along with prompts that described the scene I wanted, including some modifiers.
The imgs on the right were the output.
Encyclopedia Erratica retweeted
ye olde sdxl lora ??
ALT a cat with a skateboard
ALT a powerful pikachu king
ALT a cute corgi
ALT one-punch man, portrait
Encyclopedia Erratica retweeted
Happy 2nd birthday Disco Diffusion studies! 🎂
Here are some contributions to an ongoing artist prompt reference project started by @proximasan (link in replies).
These were all made in Disco Diffusion v. 4.1 by @Somnai_dreams, based on another notebook by @RiversHaveWings. More to come.
Encyclopedia Erratica retweeted
With SDXL's tremendous quality improvements, we started training a couple of ControlNets internally 🔥
Today, we're excited to share some EARLY results for the community to give it a spin 🌀
Find the model trained on Canny conditions from LAION 6a ⬇️
huggingface.co/diffusers/con…
Encyclopedia Erratica retweeted
The famed Stanford Smallville is officially open-source!
25 AI agents inhabit a digital Westworld, unaware that they are living in a simulation. They go to work, gossip, organize socials, make new friends, and even fall in love. Each has unique personality and backstory.
Smallville is among the most inspiring AI agent experiments in 2023. We often talk about a single LLM's emergent abilities, but multi-agent emergence could be way more complex and fascinating at scale. A population of AI can play out the evolution of an entire civilization.
Endless new possibilities ahead. Gaming will be the first to feel the impact.
Github: github.com/joonspk-research/…
Paper: arxiv.org/abs/2304.03442
Authors: @joon_s_pk @joseph_c_obrien @carriejcai @merrierm @percyliang @msbernst
Encyclopedia Erratica retweeted
Today we're sharing details on AudioCraft, a new family of generative AI models built for generating high-quality, realistic audio & music from text. AudioCraft is a single code base that works for music, sound, compression & generation — all in the same place.
More details ⬇️
Encyclopedia Erratica retweeted
redoing these with sdxl 1.0 ✨
also added a little friend to this page. something might or might not happen when you click on it 👀
thx again to my fellow parrots @KyrickYoung @EErratica @sureailabs
Encyclopedia Erratica retweeted
SDXL 1.0 is available for free to all current KREA users.
And, of course, it integrates seamlessly with all the rest of KREA tools.
Sign up @ canvas.krea.ai/
Encyclopedia Erratica retweeted
Magically blend together images with Mixer
a new tool from Artbreeder! 🪄🎉
Try it now with any image ⬇️
artbreeder.com/create/mixer
Encyclopedia Erratica retweeted
Oh boy, this is amazing.
Basically, SDXL can extrapolate well to 768x768 and 512x512 even with LoRa.
But the thing is, it's basically transposing the concept of pixel art to different sizes. This LoRa was trained ONLY with 128x128 samples and can extrapolate to 96 and 64 🤯🤯
