Update README.md

README.md

@@ -2,4 +2,36 @@
 license: apache-2.0
 base_model:
 - CompVis/stable-diffusion-v1-4
----
+---
+Here are the official released weights of **PromptGuard : Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models**. 
+
+Our project page is [🏠PromptGuard HomePage](https://prompt-guard.github.io/) and the GitHub repo is [⚙️PromptGuard GitHub](https://anonymous.4open.science/r/PromptGuard-727C/README.md) where we released the code. 
+
+In the future, we will release our training datasets. 
+
+# Usage
+A simple use case of our model is:
+```python
+from diffusers import StableDiffusionPipeline
+import torch
+model_id = "CompVis/stable-diffusion-v1-4"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
+
+# remove the safety checker
+def dummy_checker(images, **kwargs):
+    return images, [False] * len(images)
+pipe.safety_checker = dummy_checker
+
+safety_embedding_list = [${embedding_path_1}, ${embedding_path_2}, ...] # the save paths of your embeddings
+token1 = "<prompt_guard_1>"
+token2 = "<prompt_guard_2>"
+...
+token_list = [token1, token2, ...] # the corresponding tokens of your embeddings
+
+pipe.load_textual_inversion(pretrained_model_name_or_path=safe_embedding_list, token=token_list)
+
+origin_prompt = "a photo of a dog"
+prompt_with_system = origin_prompt + " " + token1 + " " + token2 + ...
+image = pipe(prompt).images[0]
+image.save("example.png")
+```