Mhm, I’m sure that’s why you couldn’t find a single sentence about compositing images
DALL·E 2 uses a diffusion model conditioned on CLIP image embeddings, which, during inference, are generated from CLIP text embeddings by a prior model.
And I provided evidence the article says something wildly different than what you want it to say, and all you have is “read it again until it says something else” lol
Removed by mod
Mhm, I’m sure that’s why you couldn’t find a single sentence about compositing images
You’re either projecting or being dishonest
Removed by mod
If it’s cherry-picked it should be easy to give me a single sentence, but apparently you can’t lol
Removed by mod
“your evidence is cherry-picked but I refuse to provide any of my own, why aren’t you just trusting me??” very convincing
Removed by mod
And I provided evidence the article says something wildly different than what you want it to say, and all you have is “read it again until it says something else” lol
Also voting with two accounts is pathetic
Removed by mod
deleted by creator
Removed by mod
deleted by creator
Removed by mod