Update README.md

README.md

@@ -6,4 +6,22 @@ license: openrail
 
 🔬 Original paper and models by https://github.com/vislearn/ControlNet-XS
 
-👷🏽‍♂️ Translated into diffusers architecture by https://twitter.com/UmerHAdil
+👷🏽‍♂️ Translated into diffusers architecture by https://twitter.com/UmerHAdil
+
+This model is trained for use with [StableDiffusion 2.1](https://huggingface.co/stabilityai/stable-diffusion-2-1)
+
+---
+
+ControlNet-XS was introduced in [ControlNet-XS](https://vislearn.github.io/ControlNet-XS/) by Denis Zavadski and Carsten Rother. It is based on the observation that the control model in the [original ControlNet](https://huggingface.co/papers/2302.05543) can be made much smaller and still produces good results.
+
+As with the original ControlNet model, you can provide an additional control image to condition and control Stable Diffusion generation. For example, if you provide a depth map, the ControlNet model generates an image that'll preserve the spatial information from the depth map. It is a more flexible and accurate way to control the image generation process.
+
+Using ControlNet-XS instead of regular ControlNet will produce images of roughly the same quality, but 20-25% faster ([see benchmark](https://github.com/UmerHA/controlnet-xs-benchmark/blob/main/Speed%20Benchmark.ipynb)) and with ~45% less memory usage.
+
+---
+
+Other ControlNet-XS models:
+
+- [StableDiffusion-XL and canny edges input](https://huggingface.co/UmerHA/ConrolNetXS-SDXL-canny)
+- [StableDiffusion-XL and depth input](https://huggingface.co/UmerHA/ConrolNetXS-SDXL-depth)
+- [StableDiffusion 2.1 and canny edges input](https://huggingface.co/UmerHA/ConrolNetXS-SD2.1-canny)