Spawning (@spawning_) 's Twitter Profile
Spawning

@spawning_

Public Domain AI
source.plus | haveibeentrained.com

ID: 1347894933357781002

linkhttps://spawning.ai calendar_today09-01-2021 13:17:14

734 Tweet

4,4K Followers

164 Following

Spawning (@spawning_) 's Twitter Profile Photo

Early access: test Public Diffusion, our image-text model training on 30 million public domain images. Sign up to join the private beta! source.plus/public-diffusi…

Early access: test Public Diffusion, our image-text model training on 30 million public domain images. Sign up to join the private beta!

source.plus/public-diffusi…
Gus Coldebella (@g_co) 's Twitter Profile Photo

While lawsuits about training data and copyright law wend their way through the courts... ...Spawning is building image generation tools trained on public domain/CC0. Check out Public Diffusion.

Jordan Meyer (@jordancmeyer) 's Twitter Profile Photo

███░░░░░░░░░ ~25% trained "A painting of a mountain lake with a boat in the foreground, surrounded by lush green grass, trees, and rocks. The sky is filled with white, fluffy clouds, creating a peaceful atmosphere."

███░░░░░░░░░ ~25% trained

"A painting of a mountain lake with a boat in the foreground, surrounded by lush green grass, trees, and rocks. The sky is filled with white, fluffy clouds, creating a peaceful atmosphere."
Alexander Doria (@dorialexander) 's Twitter Profile Photo

First visual model trained on fully open data coming. Like for text, the striking thing is not only that it is possible in the first place but that it brings so much more variety and diversity of outputs. There’s an entire world beyond web archives.

Nayan Saxena (@saxenanayan) 's Twitter Profile Photo

Public Diffusion proves a radical idea: you don’t need infinite data—you need curated data. With just public domain images, the early results rival top-tier AI art models with just 30% training complete. The future isn’t owned. It’s shared. cc: Spawning Nick Padgett Jordan Meyer

Jordan Meyer (@jordancmeyer) 's Twitter Profile Photo

Here are some images from our first candidate model for Public Diffusion. It still needs a lot more time in the oven, but these early results are very promising. Prompts in the alt text.

Here are some images from our first candidate model for Public Diffusion. 

It still needs a lot more time in the oven, but these early results are very promising.

Prompts in the alt text.
Nick Padgett (@ncpadge) 's Twitter Profile Photo

More Public Diffusion samples! It’s still very early on (<33% done), but I’m optimistic with the quality of these outputs. Some interesting examples in 🧵, all prompts in the alt text. My favorites:

More Public Diffusion samples! It’s still very early on (&lt;33% done), but I’m optimistic with the quality of these outputs.

Some interesting examples in 🧵, all prompts in the alt text. My favorites:
Spawning (@spawning_) 's Twitter Profile Photo

Our CTO, Nick Padgett, took a step back from Public Diffusion beta prep to share some results from the model he's been tirelessly working on.

Spawning (@spawning_) 's Twitter Profile Photo

Help us shape Public Diffusion—our t2i model trained on 30 million highly-aesthetic public domain images. Join the private beta! source.plus/public-diffusi…