JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation

TL;DR

JoyAI-Image is a unified multimodal model that integrates visual understanding, text-to-image generation, and image editing, enhancing spatial reasoning and controllable visual synthesis.

Contribution

It introduces a novel architecture combining a spatially enhanced MLLM with MMDiT, along with a scalable training recipe for broad multimodal capabilities.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Enhances geometry-aware reasoning and spatial editing abilities.

Demonstrates strong spatial intelligence beyond general visual competence.

Abstract

We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language Model (MLLM) with a Multimodal Diffusion Transformer (MMDiT), allowing perception and generation to interact through a shared multimodal interface. Around this architecture, we build a scalable training recipe that combines unified instruction tuning, long-text rendering supervision, spatially grounded data, and both general and spatial editing signals. This design gives the model broad multimodal capability while strengthening geometry-aware reasoning and controllable visual synthesis. Experiments across understanding, generation, long-text rendering, and editing benchmarks show that JoyAI-Image achieves state-of-the-art or highly competitive performance. More importantly, the bidirectional loop between enhanced understanding, controllable spatial editing, and novel-view-assisted reasoning enables the model to move beyond general visual competence toward stronger spatial intelligence. These results suggest a promising path for unified visual models in downstream applications such as vision-language-action systems and world models.