Strictly-ID-Preserved and Controllable Accessory Advertising Image Generation

TL;DR

This paper introduces a novel image generation pipeline that ensures strict identity preservation of accessories in advertising images, enabling precise control over model attributes for e-commerce applications.

Contribution

The paper presents a Control-Net based pipeline and a multi-branch cross-attention architecture for controllable, identity-preserving accessory image generation in advertising.

Findings

Achieves strict accessory identity preservation in generated images.

Enables control over scale, pose, and appearance of models.

Produces diverse, high-quality advertising images.

Abstract

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.