Update README.md

README.md

@@ -1,12 +1,15 @@
 ---
-pipeline_tag: text-to-image
+pipeline_tag: image-to-image
 inference: false
 ---
+# Changes in this fork:
+This is a copy of https://huggingface.co/microsoft/sd-turbo-webnn/ that has been added the VAE encoder from https://huggingface.co/schmuell/sd-turbo-ort-web/ after casting the instance-normalization nodes to float32 using https://github.com/eyaler/webnn-developer-preview/blob/main/demos/sd-turbo/fix_instance_norm.js
+
 
 # Model summary
 This Stable Diffusion Turbo model has been optimized to work with WebNN. This model is licensed under the [STABILITY AI NON-COMMERCIAL RESEARCH COMMUNITY LICENSE AGREEMENT](https://huggingface.co/stabilityai/sd-turbo/blob/main/LICENSE). For terms of use, please visit the [Acceptable Use Policy](https://stability.ai/use-policy). If you comply with the license and terms of use, you have the rights described therin. By using this Model, you accept the terms.
 
-SD-Turbo-WebNN is meant to be used with the corresponding sample [here](https://microsoft.github.io/webnn-developer-preview/) for educational or testing purposes only.
+SD-Turbo-WebNN is meant to be used with the corresponding sample [here](https://eyaler.github.io/webnn-developer-preview/) (originally: [here](https://microsoft.github.io/webnn-developer-preview/)) for educational or testing purposes only.
 
 # WebNN changes
 This original model is [SD-Turbo](https://huggingface.co/stabilityai/sd-turbo). SD-Turbo-WebNN is an ONNX version of the SD-Turbo model that optimizes for WebNN by using static input shapes and eliminates operators that are not in use.
@@ -127,4 +130,4 @@ The model is intended for both non-commercial and commercial usage.
 
 ## How to Get Started with the Model
 
-Check out https://github.com/Stability-AI/generative-models
+Check out https://github.com/Stability-AI/generative-models