Hi-DiT: Hybrid Latent-Pixel Diffusion Transformer for Image Generation
- 15 September 2026
- book chapter
- Published by Springer Nature
- p. 194-212
Abstract
No abstract availableKeywords
This publication has 28 references indexed in Scilit:
- SiT: Exploring Flow and Diffusion-Based Generative Models with Scalable Interpolant Transformers2024
- All are Worth Words: A ViT Backbone for Diffusion Models2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Vector Quantized Diffusion Model for Text-to-Image Synthesis2022
- Cross-Modal Contrastive Learning for Text-to-Image Generation2021
- AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks2018
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Microsoft COCO: Common Objects in Context2014
- ImageNet: A large-scale hierarchical image database2009