News for hackers. Stuff that matters.
Re:Direct pixel-space megapixel image generation with diffus... by clauer2024 on Wednesday January 24, 2024 @05:48AM (#39115854)
Can I ask one basic thing --> From what are the images generated?
Re:Direct pixel-space megapixel image generation with diffus... by stefanbaumann on Wednesday January 24, 2024 @06:01AM (#39115931)
The models presented in the paper are trained on class-conditional ImageNet (where the input is Gaussian noise and one of 1000 classes, e.g., "car") and unconditional FFHQ (where the input is only Gaussian noise).
Re:Direct pixel-space megapixel image generation with diffus... by ShamelessC on Wednesday January 24, 2024 @06:01AM (#39115930)
Not text but an id representing a class/category of images from the dataset. Or they are “unconditional” and the model tries to output something similar to a random image from the dataset each time.