[DOCS] Review release docs for master (#19152)

docs/optimization_guide/dldt_deployment_optimization_common.md

@@ -46,13 +46,13 @@ In the example below, inference is applied to the results of the video decoding.
 
 Below are example-codes for the regular and async-based approaches to compare:
 
-* Normally, the frame is captured with OpenCV and then immediately processed:<br>
+* Normally, the frame is captured with OpenCV and then immediately processed:
 
   .. doxygensnippet:: docs/snippets/dldt_optimization_guide8.cpp
      :language: cpp
      :fragment: [part8]
 
-* In the "true" async mode, the ``NEXT`` request is populated in the main (application) thread, while the ``CURRENT`` request is processed:<br>
+* In the "true" async mode, the ``NEXT`` request is populated in the main (application) thread, while the ``CURRENT`` request is processed:
 
   .. doxygensnippet:: docs/snippets/dldt_optimization_guide9.cpp
      :language: cpp

docs/optimization_guide/model_optimization_guide.md

@@ -20,10 +20,10 @@ Model optimization is an optional offline step of improving the final model perf
 
 Post-training Quantization is the fastest way to optimize a model and should be applied first, but it is limited in terms of achievable accuracy-performance trade-off. In case of poor accuracy or performance after Post-training Quantization, Training-time Optimization can be used as an option.
 
-Once the model is optimized using the aforementioned methods, it can be used for inference using the regular OpenVINO inference workflow. No changes to the inference code are required.
-
 .. image:: _static/images/DEVELOPMENT_FLOW_V3_crunch.svg
 
+Once the model is optimized using the aforementioned methods, it can be used for inference using the regular OpenVINO inference workflow. No changes to the inference code are required.
+
 .. image:: _static/images/WHAT_TO_USE.svg
 
 Additional Resources