activity
20242026
collaborators

5 papers

cs.CV2026

SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models

Zhengxuan Wei, Yi Dong, Zonghui Li +6

Low-Rank Adaptation (LoRA) merging can efficiently combine diverse generative capabilities from multiple trained LoRAs for a diffusion model. However, existing LoRA merging techniq…

cs.CV2026

Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer

Yanqi Ge, Jiaqi Liu, Qingnan Fan +6

In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. The main challenge is consistent structure preservation while…

cs.CV2025

CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models

Gaoyang Zhang, Bingtao Fu, Qingnan Fan +5

Text-to-image (T2I) diffusion models excel at generating photorealistic images but often fail to render accurate spatial relationships. We identify two core issues underlying this…

cs.CV2025

Textualize Visual Prompt for Image Editing via Diffusion Bridge

Pengcheng Xu, Qingnan Fan, Fei Kou +5

Visual prompt, a pair of before-and-after edited images, can convey indescribable imagery transformations and prosper in image editing. However, current visual prompt methods rely…

cs.CV2024

RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-Resolution

Jiangang Wang, Qingnan Fan, Jinwei Chen +3

Benefiting from their powerful generative capabilities, pretrained diffusion models have garnered significant attention for real-world image super-resolution (Real-SR). Existing di…