Giannis Daras Profile picture
May 31, 2022 10 tweets 4 min read Read on X
DALLE-2 has a secret language.
"Apoploe vesrreaitais" means birds.
"Contarra ccetnxniams luryca tanniounons" means bugs or pests.

The prompt: "Apoploe vesrreaitais eating Contarra ccetnxniams luryca tanniounons" gives images of birds eating bugs.

A thread (1/n)🧵 Image
A known limitation of DALLE-2 is that it struggles with text. For example, the prompt: "Two farmers talking about vegetables, with subtitles" gives an image that appears to have gibberish text on it.

However, the text is not as random as it initially appears... (2/n) Image
We feed the text "Vicootes" from the previous image to DALLE-2. Surprisingly, we get (dishes with) vegetables! We then feed the words: "Apoploe vesrreaitars" and we get birds. It seems that the farmers are talking about birds, messing with their vegetables! (3/n) Image
Another example: "Two whales talking about food, with subtitles". We get an image with the text "Wa ch zod rea" written on it. Apparently, the whales are actually talking about their food in the DALLE-2 language. (4/n) Image
Some words from the DALLE-2 language can be learned and used to create absurd prompts. For example, "painting of Apoploe vesrreaitais" gives a painting of a bird. "Apoploe vesrreaitais" means to the model "something that flies" and can be used across diverse styles. (5/n) Image
The discovery of the DALLE-2 language creates many interesting security and interpretability challenges.

Currently, NLP systems filter text prompts that violate the policy rules. Gibberish prompts may be used to bypass these filters. (6/n)
We wrote a small paper with @AlexGDimakis summarizing our findings.
Please find the paper here: giannisdaras.github.io/publications/D…
Arxiv version coming soon.
(7/n, n=7).
Based on valid comments, we updated our paper with a discussion on Limitations and changed the title to Discovering the Hidden Vocabulary of DALLE-2. Thanks to @mraginsky @rctatman @benjamin_hilton and others for useful comments.
Paper is now on arXiv: arxiv.org/abs/2206.00169
Responses to some of the criticism can be found here:

• • •

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

Keep Current with Giannis Daras

Giannis Daras 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 @giannis_daras

Dec 1, 2022
Multiresolution Textual Inversion.

Given a few images, we learn pseudo-words that represent a concept at different resolutions.

"A painting of a dog in the style of <jane(number)>" gives different levels of artistic freedom to match the <jane> style based on the number index.
The key idea of our method is to condition the embedding of the learned concept on the diffusion time.

Instead of learning one embedding to represent the concept, we learn a set of embeddings: each element of the set represents the object at different resolutions.
During inference, we can use the embeddings in many creative ways to access the learned object at different resolutions.

For example, given a painting made of buttons, we can isolate the buttons and create new objects with that texture.
Read 7 tweets
Sep 13, 2022
Announcing Soft Diffusion: A framework to correctly schedule, learn and sample from general diffusion processes.

State-of-the-art results on CelebA, outperforms DDPMs and vanilla score-based models.

A 🧵to learn about Soft Score Matching, Momentum Sampling and the role of noise
Typically, diffusion models generate images by reversing a known corruption process that gradually adds noise.

We show how to learn to reverse diffusions that involve a linear deterministic degradation and a stochastic part (additive noise).
Ingredient 1: Soft Score Matching.

Soft Score Matching incorporates the filtering process in the network. It trains the model to predict an image that after corruption matches the diffused observation.
Read 12 tweets
Jun 3, 2022
An update on the hidden vocabulary of DALLE-2.

While a lot of the feedback we received was constructive, some of the comments need to be addressed.

A thread, with some new gibberish text and some discussion 🧵 (1/N)
@benjamin_hilton said that we got lucky with the whales example.

We found another similar example.

"Two men talking about soccer, with subtitles" gives the word "tiboer". This seems to give sports in ~4/10 images. (2/N) ImageImageImage
A few people, including @realmeatyhuman, asked whether our method works beyond natural images (of birds, etc).

Yes, we found some examples that seem statistically significant.

E.g. "doitcdces" seems related (~4/10 images) to students (or learning). (3/N) ImageImage
Read 11 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!

:(