2025/03/11 by Zhenxiong Tan, Tan, Zhenxiong, Qiao Xue +7 · 20 citations
Engineering · Computer Science · #Low-power high-performance VLSI design #Interconnection Networks and Systems #VLSI and FPGA Design Techniques
paper · pdf · doi:10.48550/arxiv.2503.08280
Fine-grained control of text-to-image diffusion transformer models (DiT) remains a critical challenge for practical deployment. While recent advances such as OminiControl and others have enabled a controllable generation of diverse control signals, these methods face significant computational inefficiency when handling long conditional inputs. We present OminiControl2, an efficient framework that achieves efficient image-conditional image generation. OminiControl2 introduces two key innovations: (1) a dynamic compression strategy that streamlines conditional inputs by preserving only the most semantically relevant tokens during generation, and (2) a conditional feature reuse mechanism that computes condition token features only once and reuses them across denoising steps. These architectural improvements preserve the original framework's parameter efficiency and multi-modal versatility while dramatically reducing computational costs. Our experiments demonstrate that OminiControl2 reduces conditional processing overhead by over 90% compared to its predecessor, achieving an overall 5.9× speedup in multi-conditional generation scenarios. This efficiency enables the practical implementation of complex, multi-modal control for high-quality image synthesis with DiT models.