OmniPSD: Layered PSD Generation with Diffusion Transformer Paper • 2512.09247 • Published Dec 10, 2025 • 50
FreeFine Collection Training-Free Diffusion for Geometric Image Editing • 3 items • Updated Feb 17 • 1
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding Paper • 2603.22458 • Published 7 days ago • 130
TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering Paper • 2602.20903 • Published Feb 24 • 1
TextPecker Collection Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering • 8 items • Updated Feb 25 • 1
SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting Paper • 2504.09966 • Published Apr 14, 2025 • 1
Training-free Geometric Image Editing on Diffusion Models Paper • 2507.23300 • Published Jul 31, 2025 • 2