Skip to content

PaperCodex

Subscribe

Image Generation

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
GANformer: Compositional, Controllable Image Generation with Fewer Training Steps

GANformer: Compositional, Controllable Image Generation with Fewer Training Steps 1342

Traditional generative adversarial networks (GANs) often act as “black boxes”—they produce compelling images but offer little insight into how those…

12/27/2025Compositional Scene Modeling, Image Generation, Layout-to-image Synthesis
OOTDiffusion: High-Fidelity, Controllable Virtual Try-On Without Garment Warping

OOTDiffusion: High-Fidelity, Controllable Virtual Try-On Without Garment Warping 6482

OOTDiffusion represents a significant leap forward in image-based virtual try-on (VTON) technology. Built on the foundation of pretrained latent diffusion…

12/26/2025Diffusion Models, Image Generation, Virtual Try-on
Show-o: One Unified Transformer for Multimodal Understanding and Generation Across Text, Images, and Videos

Show-o: One Unified Transformer for Multimodal Understanding and Generation Across Text, Images, and Videos 1809

In today’s AI landscape, developers and researchers often juggle separate models for vision, language, and video—each with its own architecture,…

12/18/2025Image Generation, Multimodal Understanding, Video Understanding
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex