arXiv 2508.033202025-08-05cs.CV

Skywork UniPic：用于视觉理解与生成的统一自回归建模

Skywork UniPic: Unified Autoregressive Modeling for Visual Understanding and Generation

Multimodality Team, Skywork AI（Skywork AI 多模态团队）

Peiyu Wang, Yi Peng, Yimeng Gan, Liang Hu, Tianyidan Xie, Xiaokun Wang, Yichen Wei, Chuanxin Tang, Bo Zhu, Changshi Li, Hongyang Wei, Eric Li, Xuchen Song, Yang Liu, Yahui Zhou

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

Skywork UniPic是一个15亿参数的自回归模型，统一了图像理解、生成和编辑，在GenEval等基准上取得领先成绩，且仅需不到15GB显存，为高保真多模态AI提供了高效实用方案。

摘要：

我们推出了Skywork UniPic，一个拥有15亿参数的自回归模型，它在单一架构内统一了图像理解、文生图以及图像编辑功能，无需任务特定的适配器或模块间连接器，并证明了紧凑的多模态系统可以在商用硬件上实现最先进的性能。Skywork UniPic在GenEval上取得了0.86的分数，超越了大多数现有的统一模型；在DPG-Bench上创下了85.5的复杂生成新纪录；在GEditBench-EN上达到5.83，在ImgEdit-Bench上达到3.49（用于图像编辑）；并且生成1024×1024的图像仅需不到15GB的GPU内存（例如RTX 4090）。(1)一种解耦编码策略，利用掩码自回归编码器进行合成，使用SigLIP2编码器进行理解，两者均馈送给共享的自回归解码器；(2)一种渐进式、分辨率感知的训练计划，从256×256扩展到1024×1024，同时动态解冻参数以平衡容量和稳定性；(3)精心策划的、1亿规模的数据集，并辅以任务特定的奖励模型来优化生成和编辑目标。通过证明高保真多模态集成不必承受高昂的资源需求，Skywork UniPic为可部署的高保真多模态AI建立了一种实用范式。代码和权重可在https://huggingface.co/Skywork/Skywork-UniPic-1.5B公开获取。

英文摘要：

We introduce Skywork UniPic, a 1.5 billion-parameter autoregressive model that unifies image understanding, text-to-image generation, and image editing within a single architecture-eliminating the need for task-specific adapters or inter-module connectors-and demonstrate that compact multimodal systems can achieve state-of-the-art performance on commodity hardware. Skywork UniPic achieves a GenEval score of 0.86, surpassing most existing unified models; sets a new DPG-Bench complex-generation record of 85.5; attains 5.83 on GEditBench-EN and 3.49 on ImgEdit-Bench for image editing; and generates 1024 x 1024 images with under 15 GB of GPU memory (e.g., RTX 4090). (1) a decoupled encoding strategy that leverages a masked autoregressive encoder for synthesis and a SigLIP2 encoder for understanding, all feeding a shared autoregressive decoder; (2) a progressive, resolution-aware training schedule scaling from 256 x 256 to 1024 x 1024 while dynamically unfreezing parameters to balance capacity and stability; and (3) meticulously curated, 100 million-scale datasets augmented with task-specific reward models to refine generation and editing objectives. By demonstrating that high-fidelity multimodal integration need not incur prohibitive resource demands, Skywork UniPic establishes a practical paradigm for deployable, high-fidelity multimodal AI. Code and weights are publicly available at https://huggingface.co/Skywork/Skywork-UniPic-1.5B.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。