NEAF (Natural image Editing with Attention Fusion), a novel zero-shot, universal tuning-free framework for arbitrary pre-trained T2I models, obviating the need for dataset curation or retraining, is proposed.
A training-free Dual-path Attention Modulation (DAR) framework that decouples semantic edits while preserving source image structure is proposed and Adaptive Self-Attention (ASA) and Adaptive Cross-Attention (ACA) modules that dynamically regulate attention replacement are introduced.
Tong Cui, Jie Yang, Kai-Ru Li et al.· International Conference on...· 0 citations
This work proposes InnoText, a unified DiT-based framework capable of performing both text generation and editing within a single model, and introduces a Font Size-Aware Modulation module to enhance representations across font scales, a Small-Character Aware Augmentation strategy to improve fine-grained fidelity, and a...
Hao-Wei Liu, Runze He, Jian Lu et al.· arXiv.org· 0 citations
Backbone training-free video editing built on pre-trained text-to-image (T2I) diffusion models enables lightweight, prompt-driven edits without additional finetuning. A critical yet often overlooked factor is cross-frame latent selection during DDIM inversion, which largely determines spatiotemporal coherence in the su...
Zhangkai Wu, Xuhui Fan, Zhongyuan Xie et al.· Proceedings of the 32nd ACM...· 0 citations
The results show that careful tokenizer--backbone--system co-design can deliver strong high-resolution generation and editing within an efficient 4B model family.
MIE-Bench is introduced, the first large-scale multiple image editing benchmark with fine-grained human preference annotations and MIEScore, a multimodal large language model (MLLM)-based evaluation model enhanced with skill optimization and multi-dimensional supervised fine-tuning, to provide human-aligned feedback fo...
Zi-Tong Xu, Huiyu Duan, Xinyu Zhang et al.· 0 citations
GRNEdit, a lightweight two-stage framework for instruction-based general video editing that outperforms multiple 14B open-source editors, while the 8B model performs on par with leading open-source editors.
Feng Xie, Jiagao Hu, Fuhao Li et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
