Recent advancements in diffusion-based generative image editing have sparked a profound revolution, reshaping the landscape of image outpainting and inpainting tasks. Despite these strides, the field grapples with inherent challenges, including: i) inferior quality; ii) poor consistency; iii) insufficient instrcution adherence; iv) suboptimal generation efficiency. To address these obstacles, we present ByteEdit, an innovative feedback learning framework meticulously designed to Boost, Comply, and Accelerate Generative Image Editing tasks. ByteEdit seamlessly integrates image reward models dedicated to enhancing aesthetics and image-text alignment, while also introducing a dense, pixel-level reward model tailored to foster coherence in the output. Furthermore, we propose a pioneering adversarial and progressive feedback learning strategy to expedite the model's inference speed. Through extensive large-scale user evaluations, we demonstrate that ByteEdit surpasses leading generative image editing products, including Adobe, Canva, and MeiTu, in both generation quality and consistency. ByteEdit-Outpainting exhibits a remarkable enhancement of 388% and 135% in quality and consistency, respectively, when compared to the baseline model. Experiments also verfied that our acceleration models maintains excellent performance results in terms of quality and consistency.
@article{arxiv.2404.04860,
title = {ByteEdit: Boost, Comply and Accelerate Generative Image Editing},
author = {Yuxi Ren and Jie Wu and Yanzuo Lu and Huafeng Kuang and Xin Xia and Xionghui Wang and Qianqian Wang and Yixing Zhu and Pan Xie and Shiyin Wang and Xuefeng Xiao and Yitong Wang and Min Zheng and Lean Fu},
journal= {arXiv preprint arXiv:2404.04860},
year = {2024}
}