PixelDiT generates images in pixel space with a dual-level transformer and reaches 1.61 FID on ImageNet 256, outperforming prior pixel-space models.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2025 2representative citing papers
citing papers explorer
-
PixelDiT: Pixel Diffusion Transformers for Image Generation
PixelDiT generates images in pixel space with a dual-level transformer and reaches 1.61 FID on ImageNet 256, outperforming prior pixel-space models.
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation