UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

TL;DR

UniReason is a unified framework that integrates reasoning, generation, and editing for complex image synthesis tasks, leveraging world knowledge and self-reflection to improve accuracy and versatility.

Contribution

It introduces a novel unified architecture combining textual reasoning and visual editing, supported by a large-scale reasoning dataset for improved multimodal synthesis.

Findings

Achieves state-of-the-art results on reasoning benchmarks

Demonstrates superior generalization in image generation and editing

Effectively integrates knowledge-based reasoning with visual refinement

Abstract

Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address this, we propose UniReason, a unified framework that harmonizes these two tasks through two complementary reasoning paradigms. We incorporate world knowledge-enhanced textual reasoning into generation to infer implicit knowledge, and leverage editing capabilities for fine-grained editing-like visual refinement to further correct visual errors via self-reflection. This approach unifies generation and editing within a shared architecture, mirroring the human cognitive process of planning followed by refinement. We support this framework by systematically constructing a large-scale reasoning-centric dataset (~300k samples) covering five major knowledge domains (e.g., cultural commonsense, physics, etc.) for textual reasoning, alongside an agent-generated corpus for visual refinement. Extensive experiments demonstrate that UniReason achieves advanced performance on reasoning-intensive benchmarks such as WISE, KrisBench and UniREditBench, while maintaining superior general synthesis capabilities.