Spaces:

---

bytedance-research

/

UNO-FLUX

like 420

Running on Zero

UNO-FLUX is a academic project space demo for our paper:
Less-to-More Generalization: Unlocking More Controllability by In-Context Generation

it aims to provide a subject image and text co-driven image generation pipeline.

Some relative links about it:

• arxiv: https://arxiv.org/abs/2504.02160
• github: https://github.com/bytedance/UNO
• project pages: https://bytedance.github.io/UNO/
• model weight: https://huggingface.co/bytedance-research/UNO

Here is the abstract of our paper:

Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic in-context generation capabilities of diffusion transformers and generates high-consistency multi-subject paired data. Additionally, we introduce UNO, which consists of progressive cross-modal alignment and universal rotary position embedding. It is a multi-image conditioned subject-to-image model iteratively trained from a text-to-image model. Extensive experiments show that our method can achieve high consistency while ensuring controllability in both single-subject and multi-subject driven generation.

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