Miguel Angel Bautista
@itsbautistam.bsky.social
I am a research scientist @ Apple MLR, seeking a grand unification of generative modeling 🇪🇸🇺🇸
When we started getting this results on ImageNet-256 I was impressed that a model that predicts each pixel independently (through a cross-attention block), can generate these high-frequency details.
December 6, 2024 at 7:55 PM
When we started getting this results on ImageNet-256 I was impressed that a model that predicts each pixel independently (through a cross-attention block), can generate these high-frequency details.