Pith. sign in

Test-time prompt refinement for text-to-image models.ArXiv, abs/2507.22076

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.CV 1

years

2026 2

representative citing papers

DuET: Dual Expert Trajectories for Diffusion Image Editing

cs.CV · 2026-06-11 · conditional · novelty 6.0

Switching a diffusion editor from image-conditioned to caption-only mode for a mid-trajectory interval and back improves edit fidelity and naturalness on FLUX2-Klein and BAGEL, while predictably reducing source-image preservation.

citing papers explorer

Showing 2 of 2 citing papers.

  • DuET: Dual Expert Trajectories for Diffusion Image Editing cs.CV · 2026-06-11 · conditional · none · ref 5

    Switching a diffusion editor from image-conditioned to caption-only mode for a mid-trajectory interval and back improves edit fidelity and naturalness on FLUX2-Klein and BAGEL, while predictably reducing source-image preservation.

  • Evolutionary Token-Level Prompt Optimization for Diffusion Models cs.AI · 2026-04-10 · unverdicted · none · ref 8

    A genetic algorithm evolves CLIP token vectors to optimize aesthetic quality and prompt alignment in diffusion models, outperforming Promptist and random search by up to 23.93% on a combined fitness score.