{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ominicontrol2-efficient-conditioning-for","title":"OminiControl2: Efficient Conditioning for Diffusion Transformers","arxiv_id":"2503.08280","date":"2025-03-11","proceeding":null,"authors":["Zhenxiong Tan","Qiaochu Xue","Xingyi Yang","Songhua Liu","Xinchao Wang"],"abstract":"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$\\times$ 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.","url_abs":"https://arxiv.org/abs/2503.08280v1","url_pdf":"https://arxiv.org/pdf/2503.08280v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ominicontrol2-efficient-conditioning-for","repo_url":"https://github.com/Yuanshi9815/OminiControl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.08280","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}