works on
CLIP integration 1diffusion models 1inference-time control 1semantic alignment 1text-to-image generation 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.CVShow all

1 paper · 1 filter

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…