InstructX: Towards Unified Visual Editing with MLLM Guidance

Chong Mou(Peking University), Qian He, Fulong Ye(Intelligent Health (United Kingdom)), Xinghui Li(Tsinghua–Berkeley Shenzhen Institute), Pengze Zhang, Songtao Zhao(Beijing Dance Academy), Yanze Wu(Tencent (China))
arXiv (Cornell University)
October 9, 2025
Cited by 0


Related Papers

T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models
|Proceedings of the AAAI Conference on Artificial Intelligence|2024|724
Deep Generalized Unfolding Networks for Image Restoration
|2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)|2022|266
Robust Invertible Image Steganography
|2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)|2022|163