Update README.md

README.md

@@ -29,8 +29,8 @@ optimum-cli export openvino -m ""input-model"" --task image-text-to-text --weigh
 ### What does the test code do?
 
 Well, it demonstrates how to inference in python *and* what parts of that code are important for benchmarking performance.
-Text generation offers different challenges than text-generation with images; for examples, vision encoders often use different strategies for handling properties an image can have.
-In practice this translates to higher memory usage, reduced throughput or bad results.
+Text generation offers different challenges than text-generation with images; for examples, vision encoders often use different strategies for handling properties an image can have; to get good performance **be mindful of image resolution**.
+In practice this can translate to higher memory usage, reduced throughput and greater variety in results. Gemma-3 uses SigLIP 2 which has many SOTA optimizations; even so, effort in the preprocessing stage of a pipeline makes a world of difference. 
 
 To run the test code: