Update README.md

README.md

@@ -14,6 +14,7 @@ language:
     - [v2 Drone orbit right](#v2-drone-orbit-right)
     - [v2 Drone orbit left](#v2-drone-orbit-left)
     - [v2 Drone backing](#v2-drone-backing)
+    - [v2 Flying backwards](#v2-flying-backwards)
     - [v2 Drone forward](#v2-drone-forward)
     - [v2 Drone walking back-view](#v2-drone-walking-back-view)
     - [v2 walking front-view](#v2-walking-front-view)
@@ -66,6 +67,13 @@ language:
 
 <video controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/dronebacking-candidate_00019.mp4" title="Drone backing"></video>
 
+### v2 Flying backwards
+
+- The difference compared to the Drone LoRA is that this LoRA was trained on a dataset containing also flying footage.
+
+<video controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/800_cseti_3730960_flying_backwards-3vid_mv2_0.00031_56_w768_h512_fr16.mp4" title="Drone backing"></video>
+
+
 ### v2 Drone forward
 
 <video controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/droneforward-comparison_00002.mp4" title="Drone backing"></video>
@@ -86,7 +94,7 @@ language:
 
 - recommended to use words like "front-view"
 - play with the strength: 0.6-0.8 can already give good results
-- 
+
 <video width="576" height="384" controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/AD-IPA-testing-upscale_00002.mp4" title="casual walking front-view"></video>
 
 ### v2 running front-view