Update README.md

README.md

@@ -50,7 +50,28 @@ Note: The non-commercial variants of this model are explicitly not intended to b
 * Research on generative models.
 
 ## Usage
-We recommend using the MosaicML Diffusion Repo to finetune / train the model: https://github.com/mosaicml/diffusion . Example finetuning code coming soon. See the Gradio Demo [Here](https://github.com/mosaicml/diffusion/blob/main/scripts/gradio_demo.py)
+We recommend using the MosaicML Diffusion Repo to finetune / train the model: https://github.com/mosaicml/diffusion. 
+Example finetuning code coming soon. 
+
+### Spaces demo
+Try the model demo on [Hugging Face Spaces](https://huggingface.co/spaces/common-canvas/CommonCanvas)
+
+### Inference with 🧨 diffusers
+
+```py
+from diffusers import StableDiffusionXLPipeline
+pipe = StableDiffusionXLPipeline.from_pretrained(
+    "common-canvas/CommonCanvas-XLC", 
+    custom_pipeline="multimodalart/sdxl_perturbed_attention_guidance", #read more at https://huggingface.co/multimodalart/sdxl_perturbed_attention_guidance
+    torch_dtype=torch.float16
+).to(device)
+
+prompt = "a cat sitting in a car seat"
+image = pipe(prompt, num_inference_steps=25).images[0]    
+```
+### Inference with ComfyUI / AUTOMATIC1111 
+
+[Download safetensors ⬇️](https://huggingface.co/common-canvas/CommonCanvas-XLC/resolve/main/commoncanvas_xl_c.safetensors?download=true)
 
 ## Evaluation/Validation
 We validated the model against Stability AI’s SD2 model and compared human user study