Skip to content

PaperCodex

Subscribe

Diffusion Transformers

LightningDiT: Break the Reconstruction-Generation Trade-Off with 21.8x Faster, SOTA Image Diffusion

LightningDiT: Break the Reconstruction-Generation Trade-Off with 21.8x Faster, SOTA Image Diffusion 1315

Latent diffusion models (LDMs) have become a cornerstone of modern high-fidelity image generation. However, a persistent challenge has limited their…

12/27/2025Diffusion Transformers, Image Generation, Latent Diffusion Models
In-Context LoRA: Generate High-Fidelity Multi-Image Sets with Minimal Data and No Model Changes

In-Context LoRA: Generate High-Fidelity Multi-Image Sets with Minimal Data and No Model Changes 2024

Imagine you need to generate a cohesive set of images—say, a film storyboard, a series of product design mockups, or…

12/26/2025Diffusion Transformers, In-context Learning, Multi-image Generation
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex