Update README.md

README.md

@@ -4,7 +4,10 @@ base_model:
 - ByteDance/Bernini-R
 ---
 ## Bernini-R-n4w
-
+<video controls width="100%">
+  <source src="https://huggingface.co/rzgar/Bernini-R-n4w/resolve/main/video__00179.mp4" type="video/mp4">
+  Your browser does not support the video tag.
+</video>
 ### Anatomy & Generation Quality
 
 This merge handles male and female anatomy well. Results become significantly stronger and more consistent when guided by reference images or reference videos.
@@ -22,7 +25,12 @@ Bernini-R is noticeably more complex than standard Wan2.2 models, so the short/s
 
 ### Tip – Refiner for Difficult Scenes
 
-For tricky or complex scenes, using the low-noise expert from another Wan2.2 merge (I used SmoothMix I2V V1 low-noise) as a refiner often further improves anatomy and fine details if the initial video isn’t too messy.
+For tricky or complex scenes, using the low-noise expert from another Wan2.2 merge (I used [SmoothMix I2V V1 low-noise](https://civitai.red/models/1995784/smooth-mix-wan-22-14b-i2vt2v?modelVersionId=2259006)) as a refiner often further improves anatomy and fine details if the initial video isn’t too messy.
+
+<video controls width="100%">
+  <source src="https://huggingface.co/rzgar/Bernini-R-n4w/resolve/main/video__00180.mp4" type="video/mp4">
+  Your browser does not support the video tag.
+</video>
 
 ### LightX2V LoRA
 - [wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/loras/wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors)