diff --git a/readme.md b/readme.md
index f8d36e2..44d4629 100644
--- a/readme.md
+++ b/readme.md
@@ -13,7 +13,7 @@ So - very much like IPAdapter - but VLM will do the heavy lifting for you!
 Now this is a tuning free approach but with further task specific tuning we can expand the use scenarios.
 
 <img src="examples/ip2v/example_input.png" height=256></img>
-<video src="examples/ip2v/example_output.mp4" height=256></video>
+<img src="examples/ip2v/example_output_with_workflow.jpg" height=256></img>
 ----
 
 # Guide to Using `xtuner/llava-llama-3-8b-v1_1-transformers` for Image-Text Tasks