diff --git a/examples/offline_inference/text_to_video/text_to_video.md b/examples/offline_inference/text_to_video/text_to_video.md
index a14bf1070..da622dcd2 100644
--- a/examples/offline_inference/text_to_video/text_to_video.md
+++ b/examples/offline_inference/text_to_video/text_to_video.md
@@ -10,7 +10,7 @@ python text_to_video.py \
   --negative_prompt "<optional quality filter>" \
   --height 480 \
   --width 640 \
-  --num_frames 32 \
+  --num_frames 33 \
   --guidance_scale 4.0 \
   --guidance_scale_high 3.0 \
   --num_inference_steps 40 \
diff --git a/pyproject.toml b/pyproject.toml
index 2dfb74c3f..2234d3d19 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -40,6 +40,7 @@ dependencies = [
     "tqdm>=4.66.0",
     "torchsde>=0.2.6",  # Required for Stable Audio scheduler
     "openai-whisper>=20250625",
+    "imageio[ffmpeg]>=2.37.2",
     # "vllm==0.14.0",  # TODO: fix the entrypoints overwrite problem
 ]