HiT: Hierarchical Diffusion Transformer Enables End-to-End Pixel-Space Image Generation
Researchers introduce HiT, a Hierarchical Diffusion Transformer that learns its own abstraction hierarchy end-to-end from pixels without a separately trained encoder, achieving an FID of 1.48 on ImageNet 256.
2026-11-19 ~ 2026-11-19 · 2 related posts
- HiT image generator learns its own abstraction hierarchy, hits 1.48 FID on ImageNet 256 — LucaAmb · 2026-11-19
- Hierarchical Diffusion Transformer hits 1.48 FID on ImageNet 256 in end-to-end pixel-space generation — niloofar_mire · 2026-11-19