Update README.md

README.md

@@ -45,6 +45,21 @@ image = pipe(
 image.save("flux.png")
 ```
 
+<table>
+    <td style="text-align: center;">
+      BF16<br>
+      <medium-zoom background="rgba(0,0,0,.7)"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/quantization-backends-diffusers/combined_flux-dev_bf16_combined.png" alt="Flux-dev output with BF16: Baroque, Futurist, Noir styles"></medium-zoom>
+    </td>
+    <td style="text-align: center;">
+      BnB 4-bit<br>
+      <medium-zoom background="rgba(0,0,0,.7)"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/quantization-backends-diffusers/combined_flux-dev_bnb_4bit_combined.png" alt="Flux-dev output with BnB 4-bit: Baroque, Futurist, Noir styles"></medium-zoom>
+    </td>
+  <tr>
+    <td colspan="3" style="text-align: center;"><em>Visual comparison of Flux-dev model outputs using BF16 (left), BnB 4-bit (right) (Click on an image to zoom) </em></td>
+  </tr>
+</table>
+
+
 
 # How to generate this quantized checkpoint ?