Update README.md

README.md

@@ -47,6 +47,7 @@ control_image = load_image(
 w, h = control_image.size
 
 # Upscale x4
+# This can be set to any arbitrary target resolution
 control_image = control_image.resize((w * 4, h * 4))
 
 image = pipe(
@@ -65,21 +66,6 @@ image
    <img style="width:500px;" src="examples/output.jpg">
 </p>
 
-💡 Note: You can compute the conditioning map using for instance the `MidasDetector` from the `controlnet_aux` library
-
-```python
-from controlnet_aux import MidasDetector
-from diffusers.utils import load_image 
-
-midas = MidasDetector.from_pretrained("lllyasviel/Annotators")
-
-# Load an image
-im = load_image(
-  "https://huggingface.co/jasperai/jasperai/Flux.1-dev-Controlnet-Depth/resolve/main/examples/output.jpg"
-)
-
-surface = midas(im)
-```
 
 # Training
 This model was trained with a synthetic complex data degradation scheme taking as input a *real-life* image and artificially degrading it by combining several degradations such as amongst other image noising (Gaussian, Poisson), image blurring and JPEG compression. In a similar spirit as [1]