Roope Rainisto Profile picture
Nov 28 8 tweets 5 min read
Fashion 2.0

First try training Stable Diffusion v2.0 (512-base).

Some individual photos + tech details in the🧵

#stablediffusion #ai #portrait #fashion
Fashion 2.0
Fashion 2.0 - 2
Fashion 2.0 - 3
For training these, I used TheLastBen's solution colab.research.google.com/github/TheLast…

v2-512px - 20 images - 8000 steps - 15% text encoder training.

Same training set as what I used for v1.5, allowing me to better compare the results.
I'll be comparing against Kohya and other solutions soon enough - trying to train them all with the same training set, plus I'll try 768 - just wanted to get the "easy one done first".

Overall: I need to re-learn prompting + lots to tune in settings I'm sure. But it's a start!
@EMostaque @williamcusick @KaliYuga_ai you might like them!
BTW, friendly tip: if you're using automatic1111, make sure "use VAE weights" launch option is off.

• • •

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

Keep Current with Roope Rainisto

Roope Rainisto 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!

PDF

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 @rainisto

Nov 26
Broken Camera

Selected images from the Rejected pile.

If you're not a fan of cursed images, best not to watch this video.
#stablediffusion #fashion #photos
Broken Camera 1 ImageImageImageImage
Broken Camera 2 ImageImageImageImage
Read 4 tweets
Nov 23
Film Camera

Trained a new model for 'realistic photos' - whatever that ever means. It works pretty well.
Imagine where the quality will be in a year.
#stablediffusion #portrait
Film Camera - few individual portraits ImageImageImageImage
Film Camera 2 ImageImageImageImage
Read 7 tweets
Nov 5
Songs of Wander

#ai #street #photography ImageImageImageImage
Songs of Wander 2

#stablediffusion #dreambooth ImageImageImageImage
Songs of Wander 3

Feel like losing my mind a bit, getting lost in creating these images. But it's a fine feeling. ImageImageImageImage
Read 4 tweets
Oct 25
Dreambooth training for Stable Diffusion is extremely powerful. You can train a new token to the "person" class to create very convincing looking images of them. I've posted some examples in the past days.

But it's not the coolest thing you can do...
You can train the "style" class to create new styles. For instance the "arcane" style is well known - it skews all results to this particular Riot games style.

But - that's not the coolest thing you can do...
It's ridiculous, but you can just train the "style" class to be photographic. And you get back results that - well, look photographic.

EVERYTHING BECOMES PHOTOGRAPHIC.

#stablediffusion
Read 10 tweets
Oct 23
Black portraits

Dreambooth training SD 1.5 model for photographic style.

#dreambooth #stablediffusion #portrait
Read 5 tweets
Oct 21
"Model Drinking Water"

#stablediffusion
"Model Eating Bread"

#stablediffusion
"Model Drinking Beer"

#stablediffusion
Read 12 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!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

:(