Conversation

Replying to
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
28
1,503
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
13
1,474
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
15
1,831
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
8
1,126
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)
14
1,519
Replying to
I see some consistency in the generated outputs. It seems to me entirely possible that Midjourney has its' own vocabulary - a set of words that seem random to humans but are consistently mapped to visual concepts. Let us know if you find any!
1
17
Show replies