Initialize project page

README.md

@@ -0,0 +1,19 @@
+# FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
+
+[Ganggui Ding](dingangui.github.io)\*, Canyu Zhao\*, [Wen Wang](https://scholar.google.com/citations?user=1ks0R04AAAAJ&hl=zh-CN)\*, [Zhen Yang](https://zhenyangcs.github.io/), [Zide Liu](https://github.com/zideliu), [Hao Chen](https://scholar.google.com/citations?user=FaOqRpcAAAAJ)†, [Chunhua Shen](https://cshen.github.io/)† (*equal contribution, †corresponding author)
+
+[Project Page](https://aim-uofa.github.io/FreeCustom/docs) | [Paper(Todo)]()
+
+## Customized image generation
+![results_of_multi_concept](docs/static/images/results_of_multi_concept.png)
+![results_of_single_concept](docs/static/images/results_of_single_concept.png)
+Our method excels at *rapidly* generating high-quality images with multiple concept combinations and single concept customization, without any model parameter tuning. The identity of each concept is remarkably preserved. Furthermore, our method exhibits great versatility and robustness when dealing with different categories of concepts. This versatility allows users to generate customized images that involve diverse combinations of concepts, catering to their specific needs and preferences. Best viewed on screen.
+
+## Code will be released soon
+
+<!-- ### BibTeX
+
+```bibtex
+
+``` -->
+