1 code implementation • 18 Apr 2024 • Zhen Han, Chaojie Mao, Zeyinzi Jiang, Yulin Pan, Jingfeng Zhang
We integrate encoded textual instruction and image exemplar as a unified condition for diffusion model, enabling the editing of original image following multimodal instructions.
no code implementations • 28 Mar 2024 • Yulin Pan, Chaojie Mao, Zeyinzi Jiang, Zhen Han, Jingfeng Zhang
The process involves (i) Locate: concatenating the noise with masked scene image to achieve precise regional editing, (ii) Assign: employing decoupled cross-attention mechanism to accommodate multi-modal guidance, and (iii) Refine: using a novel RefineNet to supplement subject details.
no code implementations • 28 Dec 2023 • Chaojie Mao, Zeyinzi Jiang
Res-Tuning introduces a flexible and efficient paradigm for model tuning, showing that tuners decoupled from the backbone network can achieve performance comparable to traditional methods.
2 code implementations • 18 Dec 2023 • Zeyinzi Jiang, Chaojie Mao, Yulin Pan, Zhen Han, Jingfeng Zhang
Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable image synthesis.
no code implementations • 1 Mar 2023 • Zeyinzi Jiang, Chaojie Mao, Ziyuan Huang, Yiliang Lv, Deli Zhao, Jingren Zhou
The U-Tuning framework can simultaneously encompass existing methods and derive new approaches for parameter-efficient transfer learning, which prove to achieve on-par or better performances on CIFAR-100 and FGVC datasets when compared with existing PETL methods.