严格身份保持且可控的配饰广告图像生成
Strictly-ID-Preserved and Controllable Accessory Advertising Image Generation
AI总结：
针对电商广告中商品身份必须严格保持的需求，本文提出基于 Control-Net 的定制化图像生成流程，并通过多分支交叉注意力实现模特尺度、姿态与外观的细粒度可控生成。
摘要：
定制化文本到图像生成模型能够生成与给定主体高度相似的图像。然而，在面向电子商务场景生成广告图像时，生成主体的身份必须与所宣传的产品完全一致，这一点至关重要。为满足严格身份保持的广告图像生成需求，我们开发了一条基于 Control-Net 的定制化图像生成流程，并以耳饰模特广告为例。该方法在确保耳饰身份保持不变的同时，实现了耳饰与模特面部之间自然无缝的交互。此外，为实现多样化且可控的展示效果，我们提出了一种多分支交叉注意力架构，能够对模特的尺度、姿态和外观进行控制，突破了文本提示词的局限。我们的方法实现了对生成模特面部的细粒度控制，从而获得可控且富有吸引力的广告效果。
英文摘要：
Customized generative text-to-image models have the ability to produce images that closely resemble a given subject. However, in the context of generating advertising images for e-commerce scenarios, it is crucial that the generated subject's identity aligns perfectly with the product being advertised. In order to address the need for strictly-ID preserved advertising image generation, we have developed a Control-Net based customized image generation pipeline and have taken earring model advertising as an example. Our approach facilitates a seamless interaction between the earrings and the model's face, while ensuring that the identity of the earrings remains intact. Furthermore, to achieve a diverse and controllable display, we have proposed a multi-branch cross-attention architecture, which allows for control over the scale, pose, and appearance of the model, going beyond the limitations of text prompts. Our method manages to achieve fine-grained control of the generated model's face, resulting in controllable and captivating advertising effects.
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。
