diff --git a/.changeset/dull-garlics-lie.md b/.changeset/dull-garlics-lie.md
new file mode 100644
index 0000000000..9aed6983a2
--- /dev/null
+++ b/.changeset/dull-garlics-lie.md
@@ -0,0 +1,5 @@
+---
+"gradio": patch
+---
+
+fix:Fix multimode interface double box on file upload
diff --git a/gradio/chat_interface.py b/gradio/chat_interface.py
index 1bc678e9f6..554e0bd232 100644
--- a/gradio/chat_interface.py
+++ b/gradio/chat_interface.py
@@ -202,7 +202,10 @@ class ChatInterface(Blocks):
             with Group():
                 with Row():
                     if textbox:
-                        textbox.container = False
+                        if self.multimodal:
+                            submit_btn = None
+                        else:
+                            textbox.container = False
                         textbox.show_label = False
                         textbox_ = textbox.render()
                         if not isinstance(textbox_, (Textbox, MultimodalTextbox)):
@@ -469,7 +472,11 @@ class ChatInterface(Blocks):
     ):
         for x in message["files"]:
             history.append([(x,), None])
-        if message["text"] is not None and isinstance(message["text"], str):
+        if message["text"] is None or not isinstance(message["text"], str):
+            return
+        elif message["text"] == "" and message["files"] != []:
+            history.append([None, response])
+        else:
             history.append([message["text"], response])
 
     async def _display_input(