Skywork UniPic 3.0: Unified Multi-Image Composition via Sequence Modeling

2026-01-22

AI Summary

This work addresses the long-standing challenges of consistency and generation quality in multi-image synthesis for human-object interaction (HOI) scenes. It reformulates the task as a unified sequence generation problem and introduces a multimodal fusion framework capable of flexibly processing 1–6 input images of arbitrary resolution and producing high-quality outputs. By designing an efficient data synthesis pipeline that integrates trajectory mapping and distribution matching strategies, the method significantly accelerates inference while enhancing output fidelity. Evaluated on both single-image editing and multi-image composition benchmarks, the approach achieves state-of-the-art performance, outperforming Nano-Banana and Seedream 4.0. Notably, it attains a 12.5× speedup in inference and generates high-fidelity images in as few as eight denoising steps.

Technology Category

• Computer Vision: Multi-modal Vision
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The recent surge in popularity of Nano-Banana and Seedream 4.0 underscores the community's strong interest in multi-image composition tasks. Compared to single-image editing, multi-image composition presents significantly greater challenges in terms of consistency and quality, yet existing models have not disclosed specific methodological details for achieving high-quality fusion. Through statistical analysis, we identify Human-Object Interaction (HOI) as the most sought-after category by the community. We therefore systematically analyze and implement a state-of-the-art solution for multi-image composition with a primary focus on HOI-centric tasks. We present Skywork UniPic 3.0, a unified multimodal framework that integrates single-image editing and multi-image composition. Our model supports an arbitrary (1~6) number and resolution of input images, as well as arbitrary output resolutions (within a total pixel budget of 1024x1024). To address the challenges of multi-image composition, we design a comprehensive data collection, filtering, and synthesis pipeline, achieving strong performance with only 700K high-quality training samples. Furthermore, we introduce a novel training paradigm that formulates multi-image composition as a sequence-modeling problem, transforming conditional generation into unified sequence synthesis. To accelerate inference, we integrate trajectory mapping and distribution matching into the post-training stage, enabling the model to produce high-fidelity samples in just 8 steps and achieve a 12.5x speedup over standard synthesis sampling. Skywork UniPic 3.0 achieves state-of-the-art performance on single-image editing benchmark and surpasses both Nano-Banana and Seedream 4.0 on multi-image composition benchmark, thereby validating the effectiveness of our data pipeline and training paradigm. Code, models and dataset are publicly available.

Problem

• multi-image composition
• Human-Object Interaction
• image consistency
• high-fidelity synthesis
• arbitrary input resolution

Innovation

• sequence modeling
• multi-image composition
• trajectory mapping
• distribution matching
• unified multimodal framework