UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer
This addresses the need for more flexible controllable generation in AI, offering a solution for multi-conditional tasks, though it appears incremental as it builds on existing diffusion models.
The paper tackles the problem of effectively combining multiple conditional inputs like text, spatial maps, and subject images in diffusion-based image generation, and introduces UniCombine, a framework that achieves state-of-the-art performance with demonstrated universality and capability.
With the rapid development of diffusion models in image generation, the demand for more powerful and flexible controllable frameworks is increasing. Although existing methods can guide generation beyond text prompts, the challenge of effectively combining multiple conditional inputs while maintaining consistency with all of them remains unsolved. To address this, we introduce UniCombine, a DiT-based multi-conditional controllable generative framework capable of handling any combination of conditions, including but not limited to text prompts, spatial maps, and subject images. Specifically, we introduce a novel Conditional MMDiT Attention mechanism and incorporate a trainable LoRA module to build both the training-free and training-based versions. Additionally, we propose a new pipeline to construct SubjectSpatial200K, the first dataset designed for multi-conditional generative tasks covering both the subject-driven and spatially-aligned conditions. Extensive experimental results on multi-conditional generation demonstrate the outstanding universality and powerful capability of our approach with state-of-the-art performance.