Roope Rainisto Profile picture
Oct 25, 2022 10 tweets 7 min read Read on X
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
It's the one and same Dreambooth, trained for photographic style.

I didn't train the cars, I didn't train the vegetables, I didn't train the offices, I didn't train the landscapes.

All of that stuff is already in the SD model. The style just makes them photographic!
I'm not going to share you my trained model, but I'll tell you how to train your own. Use JoePenna's Dreambooth. github.com/JoePenna/Dream…

Pick training material that is photographic. Invent a token, pick "style" class, train enough. Try different training sets.
It's not even super sensitive to the training material. I've trained two photorealistic styles using different materials. You can fine-tune the style by the training material. I use about 20 training images myself.

All the content is in the model already.
#dreambooth
You just prompt usually: "Car on fire, <any modifiers that you like>, zyxyourstylename style"

Modifiers = "trending on artstation" or whatever you like. You can use the automatic1111 prompt modifiers to emphasize or de-emphasize things as you see fit.
Here's what my Lightroom looks like. It's all done using the same style class. You don't like this particular hipster-ish photographic style? Train your own!

#stablediffusion #lightroom
This all started from the vegetables. I made funny pictures of a model eating vegetables. Thought that the vegetables look oddly good, prompted for them only. And realized it does this style no matter what I prompt it to do. I'm so dumb I didn't at first even try!
Note #1: I did my Dreambooth training with the SD1.5 model. I'm fortunate enough to have a A6000 card, the training hits 32GB VRAM, at least a few days ago when I did this. I haven't tried this same for SD1.4, I can't say how much better or worse the results are with it.

• • •

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

Aug 14
Hey did you know that Flux can do more than just photo models!

Flux 1 dev with 3 Loras + Magnific + Luminar for film grain

View end of🧵 for details. @bfl_mlImage
Image
Image
Image
For these images, I didn't run the ultimate upscale step so they're a bit rougher in overall appearance (which I think fits).

If you want them smoother, run the Ultimate SD step before @Magnific_AI / your favourite upscaler.


Image
Image
Image
Image
With the settings I used here, 50% of the generations are "too broken weird" and not posted here but who doesn't like weird (there's some awesomeness in there I will use for other purposes)


Image
Image
Image
Image
Read 5 tweets
Oct 5, 2023
I am probably the last person to do this tutorial - everyone did this a while ago - but no matter;

Consistent characters in MidJourney and SD

It's quite useful! 🧵


Image
Image
Image
Image
Step 1

Prompt something like this: "Two images side by side, <your character description>, photo booth portrait --ar 2:1"

And you'll get nice candidates. Let's go with image 3, press U3. Image
Step 2
Looks good. Press "Vary (Region)" for inpainting. Image
Read 15 tweets
Feb 27, 2023
THIS IS THE NEXT.

Post Photographic Perspectives
A @fellowshiptrust project

Featuring my upcoming 500-piece main collection "REWORLD" (Day 1) and the fantastic post-photography group collection from 10 super-talented AI artists (Day 2), all pieces curated by yours truly.
Check out the info and samples from the "REWORLD" collection from my interview with @halecar2

postphotography.xyz/in-conversation
See the fantastic work from all the 10 artists participating in the Post Photographic Perspectives -group collection.

postphotography.xyz/gallery

Our goal is to make this THE ultimate collection of post-photography artwork currently out there in early 2023.
Read 4 tweets
Nov 28, 2022
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
Read 8 tweets
Nov 26, 2022
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, 2022
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

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!

:(