Update README.md

README.md

@@ -14,7 +14,7 @@ This `stable-diffusion-2-depth` model is resumed from [stable-diffusion-2-base](
 ![image](https://huggingface.co/stabilityai/stable-diffusion-2-depth/resolve/main/depth2image.png)
 
 - Use it with the [`stablediffusion`](https://github.com/Stability-AI/stablediffusion) repository: download the `512-depth-ema.ckpt` [here](https://huggingface.co/stabilityai/stable-diffusion-2-depth/resolve/main/512-depth-ema.ckpt).
-- Use it with 🧨 diffusers (_coming soon_)
+- Use it with 🧨 [`diffusers`](#examples)
 
 ## Model Details
 - **Developed by:** Robin Rombach, Patrick Esser
@@ -34,6 +34,41 @@ This `stable-diffusion-2-depth` model is resumed from [stable-diffusion-2-base](
           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 -U git+https://github.com/huggingface/transformers.git
+pip install -U git+https://github.com/huggingface/diffusers.git accelerate ftfy scipy
+```
+Running the pipeline (if you don't swap the scheduler it will run with the default DDIM, in this example we are swapping it to EulerDiscreteScheduler):
+
+```python
+import torch
+import requests
+from PIL import Image
+from diffusers import StableDiffusionDepth2ImgPipeline
+
+pipe = StableDiffusionDepth2ImgPipeline.from_pretrained(
+   "stabilityai/stable-diffusion-2-depth",
+   torch_dtype=torch.float16,
+).to("cuda")
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+init_image = Image.open(requests.get(url, stream=True).raw)
+
+prompt = "two tigers"
+n_propmt = "bad, deformed, ugly, bad anotomy"
+image = pipe(prompt=prompt, image=init_image, negative_prompt=n_propmt, strength=0.7).images[0]
+```
+
+**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