Add diffusers example

README.md

@@ -14,7 +14,7 @@ In addition to the textual input, it receives a `noise_level` as an input parame
 ![Image](https://github.com/Stability-AI/stablediffusion/raw/main/assets/stable-samples/upscaling/merged-dog.png)
 
 - Use it with the [`stablediffusion`](https://github.com/Stability-AI/stablediffusion) repository: download the `x4-upscaler-ema.ckpt` [here](https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler/resolve/main/x4-upscaler-ema.ckpt).
-- Use it with 🧨 diffusers (_coming soon_)
+- Use it with 🧨 [`diffusers`](https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler#Examples)
 
 
 ## Model Details
@@ -35,6 +35,42 @@ In addition to the textual input, it receives a `noise_level` as an input parame
           pages     = {10684-10695}
       }
 
+
+## Examples
+
+Using the [🤗's Diffusers library](https://github.com/huggingface/diffusers) to run Stable Diffusion 2 in a simple and efficient manner.
+
+```bash
+pip install --upgrade git+https://github.com/huggingface/diffusers.git transformers accelerate scipy
+```
+
+```python
+import requests
+from PIL import Image
+from io import BytesIO
+from diffusers import StableDiffusionUpscalePipeline
+import torch
+
+# load model and scheduler
+model_id = "stabilityai/stable-diffusion-x4-upscaler"
+pipeline = StableDiffusionUpscalePipeline.from_pretrained(model_id, revision="fp16", torch_dtype=torch.float16)
+pipeline = pipeline.to("cuda")
+
+# let's download an  image
+url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd2-upscale/low_res_cat.png"
+response = requests.get(url)
+low_res_img = Image.open(BytesIO(response.content)).convert("RGB")
+low_res_img = low_res_img.resize((128, 128))
+
+upscaled_image = pipeline(low_res_img).images[0]
+upscaled_image.save("upsampled_cat.png")
+```
+
+**Notes**:
+- Despite not being a dependency, we highly recommend you to install [xformers](https://github.com/facebookresearch/xformers) for memory efficient attention (better performance)
+- If you have low GPU RAM available, make sure to add a `pipe.enable_attention_slicing()` after sending it to `cuda` for less VRAM usage (to the cost of speed)
+
+
 # Uses
 
 ## Direct Use