Rosanne Liu Profile picture
Jun 25 6 tweets 3 min read
A quick thread on "How DALL-E 2, Imagen and Parti Architectures Differ" with breakdown into comparable modules, annotated with size 🧵
#dalle2 #imagen #parti

* figures taken from corresponding papers with slight modification
* parts used for training only are greyed out A compilation of model architecture diagrams of three recent
By now we know that
- DALL-E & Imagen = diffusion; Parti = autoregressive
- Imagen & Parti use generic text encoders; DALLE uses CLIP enc

But in fact, one version of Imagen also used CLIP, one version of DALL-E also had AR prior. So there are more connections than it seemed.
If we break each architecture down into *modules*, the similarity/comparability is even more clear.

First of all, they all have a "text encoder", but differ in types and sizes:
- DALL-E uses CLIP text encoder
- Imagen uses T5-XXL
- Parti uses a generic transformer
Then, they all convert text embeddings into image embeddings.
- DALL-E uses "prior + decoder" components, where the prior can be either AR or diffusion
- Imagen uses pure diffusion
- Parti uses a transformer decoder + transformer-based tokenizer (pretrained and finetuned)
Lastly, they all have a "super-resolution" block that upsamples generated images from 64x64 to 256x256, all the way to 1024x1024.
- DALL-E uses diffusion, 700M from 64 -> 256, 300M from 256 -> 1024
- Imagen uses diffusion, 600M + 300M
- Parti uses convolution, 15M + 30M (LOL)
End of thread. All of them are amazing! 😆

This is a deeper dive from an earlier tweet of mine that was well circulated but lacked clarity.

(Some numbers are estimates from descriptions in paper. Please send in corrections if you think they are off.)

• • •

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

Keep Current with Rosanne Liu

Rosanne Liu 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 @savvyRL

Dec 13, 2020
Favorite #NeurIPS2020 presentations and posters this year

PS: heavily biased by what I happened to catch and whom I happened to talk to
PPS: still catching up on talks so the list is rather incomplete and I'd hope to grow
PPPS: with contributions from @ml_collective members
[Talk] No. 1 has to go to -- keynote talk by @isbellHFh @mlittmancs et al simply brilliant 🎉🎉
slideslive.com/38935825/you-c…
Read 20 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!

:(