arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.02663cs.CVcs.AI
收藏

FaceStudio:数秒内将你的面孔放到任何地方

FaceStudio: Put Your Face Everywhere in Seconds

Tencent(腾讯)

Yuxuan Yan, Chi Zhang, Rui Wang, Yichao Zhou, Gege Zhang, Pei Cheng, Gang Yu, Bin Fu

AI总结:

本文提出FaceStudio,通过直接前馈机制与融合风格图像、面部图像和文本提示的混合引导框架,在无需微调或多张参考图的情况下快速生成高保真身份保持人物图像。

摘要:

本研究考察身份保持图像合成,这是图像生成中一项引人关注的任务,旨在保持主体身份,同时加入个性化、风格化的处理。Textual Inversion和DreamBooth等传统方法已在定制图像创建方面取得进展,但它们存在显著缺陷,包括需要大量资源和时间进行微调,以及需要多张参考图像。为克服这些挑战,我们的研究提出了一种用于身份保持合成的新方法,尤其聚焦于人物图像。我们的模型采用直接前馈机制,避免了密集微调需求,从而实现快速、高效的图像生成。我们创新的核心是一个混合引导框架,该框架结合风格化图像、面部图像和文本提示来引导图像生成过程。这种独特组合使模型能够产生多种应用,例如艺术肖像和身份融合图像。我们的实验结果包括定性与定量评估,证明了本方法相较现有基线模型和先前工作的优越性,尤其体现在其出色效率以及高保真保持主体身份的能力上。

英文摘要:

This study investigates identity-preserving image synthesis, an intriguing task in image generation that seeks to maintain a subject's identity while adding a personalized, stylistic touch. Traditional methods, such as Textual Inversion and DreamBooth, have made strides in custom image creation, but they come with significant drawbacks. These include the need for extensive resources and time for fine-tuning, as well as the requirement for multiple reference images. To overcome these challenges, our research introduces a novel approach to identity-preserving synthesis, with a particular focus on human images. Our model leverages a direct feed-forward mechanism, circumventing the need for intensive fine-tuning, thereby facilitating quick and efficient image generation. Central to our innovation is a hybrid guidance framework, which combines stylized images, facial images, and textual prompts to guide the image generation process. This unique combination enables our model to produce a variety of applications, such as artistic portraits and identity-blended images. Our experimental results, including both qualitative and quantitative evaluations, demonstrate the superiority of our method over existing baseline models and previous works, particularly in its remarkable efficiency and ability to preserve the subject's identity with high fidelity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑