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?
[ Parent
| on HN ]
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.