Awesome
<div align="center"> <h1>IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation</h1> <!-- <div> Yinwei Wu<sup>1,2</sup> Xianpan Zhou<sup>1</sup> Bing Ma<sup>1</sup> Xuefeng Su<sup>1</sup> Kai Ma<sup>1</sup> Xinchao Wang<sup>2</sup><sup>†</sup> </div> <div> <sup>1</sup>Tencent PGC  <sup>2</sup>National University of Singapore  <sup>†</sup>corresponding author </div> --> <div> <a target="_blank" href="https://arxiv.org/abs/2409.08240"> <img src="https://img.shields.io/badge/arXiv-2409.08240-b31b1b.svg" alt="arXiv Paper"/> </a> <a target="_blank" href="https://ifadapter.github.io/"> <img src="https://img.shields.io/badge/Project-Page-blue" alt="arXiv Paper"/> </a> </div> <!-- <div> --> </div> <!-- <div> <a target="_blank" href="https://arxiv.org/abs/2403.20249"> <img src="https://img.shields.io/badge/arXiv-2312.17142-b31b1b.svg" alt="arXiv Paper"/> </a> <a target="_blank" href="https://wuyinwei-hah.github.io/rrnet.github.io/"> <img src="https://img.shields.io/badge/Project-Page-blue" alt="arXiv Paper"/> </a> </div>--> <!-- --- --> <!-- # Overview ![overall_structure](./assets/fig1.png) We introduce the **I**nstance **F**eature **Adapter**(IFAdapter) to to exert fine-grained control over the generation of multiple instances. --> <!-- # Feature --> <!-- ## Plug-and-play The IFAdapter is readily integrated with various community models and LoRAs! ![loras](./assets/lora.png) We show the results of IFAdapter in combination with [PixelArt](https://civitai.com/models/120096/pixel-art-xl), [Lelo-Lego](https://civitai.com/models/92444/lelo-lego-lora-for-xl-and-sd15), [Claymation](https://huggingface.co/DoctorDiffusion/doctor-diffusion-s-claymation-style-lora), and [Bluepencil](https://civitai.com/models/119012/bluepencil-xl). We express our gratitude for these great work contributed by these communities! --> <!-- ## Detailed features generation The IFAdapter is capable of generating detailed instance features with high fidelity. ![compare](./assets/compare.png) We present the generation results for various types of features, including mixed colors, diverse materials, and intricate textures. -->The code is coming soon!
Citation
@article{wu2024ifadapter,
title={IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation},
author={Yinwei Wu and Xianpan Zhou and Bing Ma and Xuefeng Su and Kai Ma and Xinchao Wang},
journal={arXiv preprint arXiv:2409.08240},
year={2024}
}