diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000..1aa34da
Binary files /dev/null and b/.DS_Store differ
diff --git a/README.md b/README.md
index 1767fe8..beb8adc 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,5 @@
 # Segment-Everything-Everywhere-All-at-Once
+![SEEM design](assets/model.pdf?raw=true)
 This paper presents a model **SEEM** that can Segment Everything Everywhere all at once. Our SEEM allows users to easily segment visual an image using prompts of different types including visual prompts (points, marks, boxes, scribbles and image segments) and language prompts (text and audio), etc. It can also handle any combination of prompts or generalize to custom prompts. 
 We emphasize $4$ important features of **SEE** here.
 1. Versatility: work on various types of prompts;
diff --git a/assets/compare_with_sam.pdf b/assets/compare_with_sam.pdf
new file mode 100644
index 0000000..6fa0c23
Binary files /dev/null and b/assets/compare_with_sam.pdf differ
diff --git a/assets/model.pdf b/assets/model.pdf
new file mode 100644
index 0000000..f641eec
Binary files /dev/null and b/assets/model.pdf differ