ByteDance
/

InfiniteYou

@@ -36,7 +36,7 @@ This repository provides the official models for the following paper:
 [Hao Kang](https://scholar.google.com/citations?user=VeTCSyEAAAAJ),
 [Xin Lu](https://scholar.google.com/citations?user=mFC0wp8AAAAJ)<br />
 ByteDance Intelligent Creation<br />
-**ICCV 2025**
 > **Abstract:** Achieving flexible and high-fidelity identity-preserved image generation remains formidable, particularly with advanced Diffusion Transformers (DiTs) like FLUX. We introduce **InfiniteYou (InfU)**, one of the earliest robust frameworks leveraging DiTs for this task. InfU addresses significant issues of existing methods, such as insufficient identity similarity, poor text-image alignment, and low generation quality and aesthetics. Central to InfU is InfuseNet, a component that injects identity features into the DiT base model via residual connections, enhancing identity similarity while maintaining generation capabilities. A multi-stage training strategy, including pretraining and supervised fine-tuning (SFT) with synthetic single-person-multiple-sample (SPMS) data, further improves text-image alignment, ameliorates image quality, and alleviates face copy-pasting. Extensive experiments demonstrate that InfU achieves state-of-the-art performance, surpassing existing baselines. In addition, the plug-and-play design of InfU ensures compatibility with various existing methods, offering a valuable contribution to the broader community.

 [Hao Kang](https://scholar.google.com/citations?user=VeTCSyEAAAAJ),
 [Xin Lu](https://scholar.google.com/citations?user=mFC0wp8AAAAJ)<br />
 ByteDance Intelligent Creation<br />
+**ICCV 2025 (<span style="color:#F44336">Highlight</span>)**
 > **Abstract:** Achieving flexible and high-fidelity identity-preserved image generation remains formidable, particularly with advanced Diffusion Transformers (DiTs) like FLUX. We introduce **InfiniteYou (InfU)**, one of the earliest robust frameworks leveraging DiTs for this task. InfU addresses significant issues of existing methods, such as insufficient identity similarity, poor text-image alignment, and low generation quality and aesthetics. Central to InfU is InfuseNet, a component that injects identity features into the DiT base model via residual connections, enhancing identity similarity while maintaining generation capabilities. A multi-stage training strategy, including pretraining and supervised fine-tuning (SFT) with synthetic single-person-multiple-sample (SPMS) data, further improves text-image alignment, ameliorates image quality, and alleviates face copy-pasting. Extensive experiments demonstrate that InfU achieves state-of-the-art performance, surpassing existing baselines. In addition, the plug-and-play design of InfU ensures compatibility with various existing methods, offering a valuable contribution to the broader community.