Emad Profile picture
Aug 22 11 tweets 4 min read
Delighted to announce the public open source release of #StableDiffusion!

Please see our release post and retweet! stability.ai/blog/stable-di…

Proud of everyone involved in releasing this tech that is the first of a series of models to activate the creative potential of humanity
We are also delighted to announce the public beta release of #DreamStudio, our reference implementation to allow anyone to create anything.

The public API will be available here shortly to extend your creativity and enable new experiences.

We have more to come and expect an explosion of originality in UI/UX and new ways to create both from our efforts and those of the community, which everyone should join at discord.gg/stablediffusion !

Developers, creatives and those inspired by this, all are welcome to come & dream
A sneak peek at some of the futures to come for #DreamStudio, including local GPU usage, animation, logic-based pipeline flow with more such as inpainting, dynamic variation and latent space exploration to come..

Very proud of the whole team and look forward to the future
We look forward to highlighting the work of all those who build on #StableDiffusion (note per the license you have to say if you are! But use the hashtag anyway as that's the cool thing to do), as well as supporting them in various ways with some big announcements to come..
To the license itself and the extra work done, this comes in two parts.

The license is ethical use and should be distributed with model and made available to end users. It is permissive and respectful of individual responsibility.

We hope it sets a standard for these models.
The safety filters incorporated in the default package can be adjusted (you can even add things like removing clowns), but are important given the various limitations highlighted in the model card for this general first model that is reflective of humanity huggingface.co/CompVis/stable…
... or at least what humanity is reflected in a scrape of the internet.

It does not target any specific group and sets a basis from which far better and diverse models can be built.

We will be building models and datasets for all cultures, races and countries.

We are making it so every individual can create, fine-tune and train their own models that take their information and condense them down to a few gigabytes.

These are really generative search engines that take our information and turn it into compressed knowledge.
By making these frameworks we look forward to the diversity this will create and encourage you to come and share on our community and let us know how we can support you.

Many more models to come but this is only possible through the work of our communities, partners and you.
Today we all made the World a more creative, happier and communicative place.

More to come in the next few days but I for one can't wait to see what you all create.

Let's activate humanity's potential.

• • •

Missing some Tweet in this thread? You can try to force a refresh

Keep Current with Emad

Emad Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!


Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @EMostaque

Aug 21
Some thoughts on #StableDiffusion vs #DALLE2 vs #midjourney

They are actually all different (complementary?).

First this whole field was catalysed by @OpenAI releasing CLIP publicly last year (!) which @RiversHaveWings, @advadnoun and others built on openai.com/blog/clip/
This allowed image generation to be guided, the output of which was surprising and led to a burst of developer and artist creativity from @ClaireSilver12 and many others.

Proud to say we supported & funded most of the open tools in this space.

It is now good enough, fast enough
So #dalle2 is a model and a service.

It is focused on a certain usage subset that will broaden.

Inpainting is it’s best feature but by default it is random and best used for ideation and more corporate usage, hence it’s clear training on licensed stock images
Read 13 tweets
Mar 12, 2020
Hi all, I am back and I know a lot of you are scared.
This is a thread on why this will end up ok.
I say this having warned what would happen/get bad at the end of January saying it would go exponential over the period it did ()
1. As humans our greatest ability is to come together to form something @waitbutwhy calls the "Human Colossus".
The Colossus can split the atom or reach the stars.
Little versions of it can also do big things, some good, some bad.
2. We are tied together by our common stories, from family to sports team to nations.
Even money is just a common story that allows us to store and exchange value at scale, helping connect between and across communities
Read 18 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!


0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy


3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!