diff --git a/python/sglang/multimodal_gen/apps/webui/main.py b/python/sglang/multimodal_gen/apps/webui/main.py
index 9ca6079cd..1245a2683 100644
--- a/python/sglang/multimodal_gen/apps/webui/main.py
+++ b/python/sglang/multimodal_gen/apps/webui/main.py
@@ -22,7 +22,6 @@ def add_webui_args(parser: argparse.ArgumentParser):
 
 def run_sgl_diffusion_webui(server_args: ServerArgs):
     # import gradio in function to avoid CI crash
-
     import gradio as gr
 
     # init client
@@ -32,7 +31,6 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
     def gradio_generate(
         prompt,
         negative_prompt,
-        reference_image_paths_str,
         seed,
         num_frames,
         frames_per_second,
@@ -47,23 +45,9 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
         So we use global variable sampling_params_kwargs to avoid pass this param, because gradio does not support this.
         return [ np.ndarray, None ] | [None, np.ndarray]
         """
-        if (
-            reference_image_paths_str is not ""
-            and reference_image_paths_str is not None
-        ):
-            if "，" in reference_image_paths_str:
-                print(
-                    f"Warning: please use English comma to separate the reference image paths, and the reference image paths is: {reference_image_paths_str}"
-                )
-                reference_image_paths_str = reference_image_paths_str.replace("，", ",")
-            image_path = [path.strip() for path in reference_image_paths_str.split(",")]
-        else:
-            image_path = None
-
         sampling_params_kwargs = dict(
             prompt=prompt,
             negative_prompt=negative_prompt,
-            image_path=image_path,
             seed=seed,
             num_frames=num_frames,
             fps=frames_per_second,
@@ -84,11 +68,6 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
         )
         result = sync_scheduler_client.forward([batch])
         save_file_path = str(os.path.join(batch.output_path, batch.output_file_name))
-        if result.output is None:
-            raise ValueError(
-                f"No output is generated by client, and their sampling params is: \n{ '\n'.join([f'{key}: {value}' for key, value in sampling_params_kwargs.items()])}"
-            )
-
         frames = post_process_sample(
             result.output[0],
             batch.data_type,
@@ -125,10 +104,6 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
                 frames_per_second = gr.Slider(
                     minimum=4, maximum=60, value=16, step=1, label="frames_per_second"
                 )
-                reference_image_paths_str = gr.Textbox(
-                    label="reference images",
-                    placeholder="Examples: 'image1.png, image2.png' or 'https://example.com/image1.png, https://example.com/image2.png'",
-                )
                 width = gr.Number(label="width", precision=0, value=720)
                 height = gr.Number(label="height", precision=0, value=480)
                 num_inference_steps = gr.Slider(
@@ -152,7 +127,6 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
             inputs=[
                 prompt,
                 negative_prompt,
-                reference_image_paths_str,
                 seed,
                 num_frames,
                 frames_per_second,
@@ -169,7 +143,6 @@ def run_sgl_diffusion_webui(server_args: ServerArgs):
             server_port=server_args.webui_port,
             quiet=True,
             prevent_thread_lock=True,
-            show_error=True,
         )
 
         # print banner