Spaces:

---

bytedance-research

/

USO

like 123

Running on Zero

USO is a academic project space demo for our paper:
USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

it is a unified style-subject optimized customization model and can freely combine any subjects with any styles in any scenarios

Some relative links about it:

arxiv: https://arxiv.org/abs/2508.18966
github: https://github.com/bytedance/USO
project pages: https://bytedance.github.io/USO/
model weight: https://huggingface.co/bytedance-research/USO
Here is the abstract of our paper:

Existing literature typically treats style-driven and subject-driven generation as two disjoint tasks: the former prioritizes stylistic similarity, > > > whereas the latter insists on subject consistency, resulting in an apparent antagonism. We argue that both objectives can be unified under a single framework because they ultimately concern the disentanglement and re-composition of content and style, a long-standing theme in style-driven research. To this end, we present USO, a Unified Style-Subject Optimized customization model. First, we construct a large-scale triplet dataset consisting of content images, style images, and their corresponding identity1d content images. Second, we introduce a disentangled learning scheme that simultaneously aligns style features and disentangles content from style through two complementary objectives, style-alignment training and content-style disentanglement training. Third, we incorporate a style reward-learning paradigm denoted as SRL to further enhance the model's performance. Finally, we release USO-Bench, the first benchmark that jointly evaluates style similarity and subject fidelity across multiple metrics. Extensive experiments demonstrate that USO achieves state-of-the-art performance among open-source models along both dimensions of subject consistency and style similarity.

Could someone please grant GPU and storage for our demo in this space? Thank you so much for your support!