CLIP integration 1diffusion models 1inference-time control 1semantic alignment 1text-to-image generation 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CV2026
Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Time
Xinyi Wang, Yuyang Huang, Yalin Su +4
The paper introduces AnchorSteer, a training‑free method that improves text‑to‑image diffusion models by initializing with CLIP‑aligned latent noise and actively correcting semanti…
cs.CV2026
OSDM-MReg: Multimodal Image Registration based One Step Diffusion Model
Xiaochen Wei, Weiwei Guo, Wenxian Yu +2
Multimodal remote sensing image registration aligns images from different sensors for data fusion and analysis. However, existing methods often struggle to extract modality-invaria…