Strictly-ID-Preserved and Controllable Accessory Advertising Image Generation
This addresses the need for strictly-ID preserved image generation in e-commerce advertising, but it is incremental as it builds on existing Control-Net and customization methods.
The paper tackles the problem of generating advertising images where the product's identity must be preserved, using earrings as an example, and achieves fine-grained control over the model's face for diverse displays.
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.