diff --git a/docs/source/training/text_inversion.mdx b/docs/source/training/text_inversion.mdx
index 8c53421e21..82cb12902f 100644
--- a/docs/source/training/text_inversion.mdx
+++ b/docs/source/training/text_inversion.mdx
@@ -74,7 +74,7 @@ Run the following command to authenticate your token
 huggingface-cli login
 ```
 
-If you have already cloned the repo, then you won't need to go through these steps. You can simple remove the `--use_auth_token` arg from the following command.
+If you have already cloned the repo, then you won't need to go through these steps.
 
 <br>
 
@@ -87,7 +87,7 @@ export MODEL_NAME="CompVis/stable-diffusion-v1-4"
 export DATA_DIR="path-to-dir-containing-images"
 
 accelerate launch textual_inversion.py \
-  --pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
+  --pretrained_model_name_or_path=$MODEL_NAME \
   --train_data_dir=$DATA_DIR \
   --learnable_property="object" \
   --placeholder_token="<cat-toy>" --initializer_token="toy" \
diff --git a/examples/dreambooth/README.md b/examples/dreambooth/README.md
index e6dbf9667e..9d78c11282 100644
--- a/examples/dreambooth/README.md
+++ b/examples/dreambooth/README.md
@@ -32,7 +32,7 @@ Run the following command to authenticate your token
 huggingface-cli login
 ```
 
-If you have already cloned the repo, then you won't need to go through these steps. You can simple remove the `--use_auth_token` arg from the following command.
+If you have already cloned the repo, then you won't need to go through these steps.
 
 <br>
 
@@ -46,7 +46,7 @@ export INSTANCE_DIR="path-to-instance-images"
 export OUTPUT_DIR="path-to-save-model"
 
 accelerate launch train_dreambooth.py \
-  --pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
   --instance_data_dir=$INSTANCE_DIR \
   --output_dir=$OUTPUT_DIR \
   --instance_prompt="a photo of sks dog" \
@@ -71,7 +71,7 @@ export CLASS_DIR="path-to-class-images"
 export OUTPUT_DIR="path-to-save-model"
 
 accelerate launch train_dreambooth.py \
-  --pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
   --instance_data_dir=$INSTANCE_DIR \
   --class_data_dir=$CLASS_DIR \
   --output_dir=$OUTPUT_DIR \
@@ -101,7 +101,7 @@ export CLASS_DIR="path-to-class-images"
 export OUTPUT_DIR="path-to-save-model"
 
 accelerate launch train_dreambooth.py \
-  --pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
   --instance_data_dir=$INSTANCE_DIR \
   --class_data_dir=$CLASS_DIR \
   --output_dir=$OUTPUT_DIR \
diff --git a/examples/dreambooth/train_dreambooth.py b/examples/dreambooth/train_dreambooth.py
index 740724c490..e507fcbdca 100644
--- a/examples/dreambooth/train_dreambooth.py
+++ b/examples/dreambooth/train_dreambooth.py
@@ -158,14 +158,6 @@ def parse_args():
     parser.add_argument("--adam_epsilon", type=float, default=1e-08, help="Epsilon value for the Adam optimizer")
     parser.add_argument("--max_grad_norm", default=1.0, type=float, help="Max gradient norm.")
     parser.add_argument("--push_to_hub", action="store_true", help="Whether or not to push the model to the Hub.")
-    parser.add_argument(
-        "--use_auth_token",
-        action="store_true",
-        help=(
-            "Will use the token generated when running `huggingface-cli login` (necessary to use this script with"
-            " private models)."
-        ),
-    )
     parser.add_argument("--hub_token", type=str, default=None, help="The token to use to push to the Model Hub.")
     parser.add_argument(
         "--hub_model_id",
@@ -341,7 +333,7 @@ def main():
         if cur_class_images < args.num_class_images:
             torch_dtype = torch.float16 if accelerator.device.type == "cuda" else torch.float32
             pipeline = StableDiffusionPipeline.from_pretrained(
-                args.pretrained_model_name_or_path, use_auth_token=args.use_auth_token, torch_dtype=torch_dtype
+                args.pretrained_model_name_or_path, torch_dtype=torch_dtype
             )
             pipeline.set_progress_bar_config(disable=True)
 
@@ -389,20 +381,12 @@ def main():
     if args.tokenizer_name:
         tokenizer = CLIPTokenizer.from_pretrained(args.tokenizer_name)
     elif args.pretrained_model_name_or_path:
-        tokenizer = CLIPTokenizer.from_pretrained(
-            args.pretrained_model_name_or_path, subfolder="tokenizer", use_auth_token=args.use_auth_token
-        )
+        tokenizer = CLIPTokenizer.from_pretrained(args.pretrained_model_name_or_path, subfolder="tokenizer")
 
     # Load models and create wrapper for stable diffusion
-    text_encoder = CLIPTextModel.from_pretrained(
-        args.pretrained_model_name_or_path, subfolder="text_encoder", use_auth_token=args.use_auth_token
-    )
-    vae = AutoencoderKL.from_pretrained(
-        args.pretrained_model_name_or_path, subfolder="vae", use_auth_token=args.use_auth_token
-    )
-    unet = UNet2DConditionModel.from_pretrained(
-        args.pretrained_model_name_or_path, subfolder="unet", use_auth_token=args.use_auth_token
-    )
+    text_encoder = CLIPTextModel.from_pretrained(args.pretrained_model_name_or_path, subfolder="text_encoder")
+    vae = AutoencoderKL.from_pretrained(args.pretrained_model_name_or_path, subfolder="vae")
+    unet = UNet2DConditionModel.from_pretrained(args.pretrained_model_name_or_path, subfolder="unet")
 
     if args.gradient_checkpointing:
         unet.enable_gradient_checkpointing()
@@ -589,9 +573,7 @@ def main():
     # Create the pipeline using using the trained modules and save it.
     if accelerator.is_main_process:
         pipeline = StableDiffusionPipeline.from_pretrained(
-            args.pretrained_model_name_or_path,
-            unet=accelerator.unwrap_model(unet),
-            use_auth_token=args.use_auth_token,
+            args.pretrained_model_name_or_path, unet=accelerator.unwrap_model(unet)
         )
         pipeline.save_pretrained(args.output_dir)
 
diff --git a/examples/textual_inversion/README.md b/examples/textual_inversion/README.md
index 4e3873024e..0976e73496 100644
--- a/examples/textual_inversion/README.md
+++ b/examples/textual_inversion/README.md
@@ -39,7 +39,7 @@ Run the following command to authenticate your token
 huggingface-cli login
 ```
 
-If you have already cloned the repo, then you won't need to go through these steps. You can simple remove the `--use_auth_token` arg from the following command.
+If you have already cloned the repo, then you won't need to go through these steps. 
 
 <br>
 
@@ -52,7 +52,7 @@ export MODEL_NAME="CompVis/stable-diffusion-v1-4"
 export DATA_DIR="path-to-dir-containing-images"
 
 accelerate launch textual_inversion.py \
-  --pretrained_model_name_or_path=$MODEL_NAME --use_auth_token \
+  --pretrained_model_name_or_path=$MODEL_NAME \
   --train_data_dir=$DATA_DIR \
   --learnable_property="object" \
   --placeholder_token="<cat-toy>" --initializer_token="toy" \
diff --git a/examples/textual_inversion/textual_inversion.py b/examples/textual_inversion/textual_inversion.py
index 253063e793..5b5ba9a207 100644
--- a/examples/textual_inversion/textual_inversion.py
+++ b/examples/textual_inversion/textual_inversion.py
@@ -136,14 +136,6 @@ def parse_args():
     parser.add_argument("--adam_weight_decay", type=float, default=1e-2, help="Weight decay to use.")
     parser.add_argument("--adam_epsilon", type=float, default=1e-08, help="Epsilon value for the Adam optimizer")
     parser.add_argument("--push_to_hub", action="store_true", help="Whether or not to push the model to the Hub.")
-    parser.add_argument(
-        "--use_auth_token",
-        action="store_true",
-        help=(
-            "Will use the token generated when running `huggingface-cli login` (necessary to use this script with"
-            " private models)."
-        ),
-    )
     parser.add_argument("--hub_token", type=str, default=None, help="The token to use to push to the Model Hub.")
     parser.add_argument(
         "--hub_model_id",
@@ -371,9 +363,7 @@ def main():
     if args.tokenizer_name:
         tokenizer = CLIPTokenizer.from_pretrained(args.tokenizer_name)
     elif args.pretrained_model_name_or_path:
-        tokenizer = CLIPTokenizer.from_pretrained(
-            args.pretrained_model_name_or_path, subfolder="tokenizer", use_auth_token=args.use_auth_token
-        )
+        tokenizer = CLIPTokenizer.from_pretrained(args.pretrained_model_name_or_path, subfolder="tokenizer")
 
     # Add the placeholder token in tokenizer
     num_added_tokens = tokenizer.add_tokens(args.placeholder_token)
@@ -393,15 +383,9 @@ def main():
     placeholder_token_id = tokenizer.convert_tokens_to_ids(args.placeholder_token)
 
     # Load models and create wrapper for stable diffusion
-    text_encoder = CLIPTextModel.from_pretrained(
-        args.pretrained_model_name_or_path, subfolder="text_encoder", use_auth_token=args.use_auth_token
-    )
-    vae = AutoencoderKL.from_pretrained(
-        args.pretrained_model_name_or_path, subfolder="vae", use_auth_token=args.use_auth_token
-    )
-    unet = UNet2DConditionModel.from_pretrained(
-        args.pretrained_model_name_or_path, subfolder="unet", use_auth_token=args.use_auth_token
-    )
+    text_encoder = CLIPTextModel.from_pretrained(args.pretrained_model_name_or_path, subfolder="text_encoder")
+    vae = AutoencoderKL.from_pretrained(args.pretrained_model_name_or_path, subfolder="vae")
+    unet = UNet2DConditionModel.from_pretrained(args.pretrained_model_name_or_path, subfolder="unet")
 
     # Resize the token embeddings as we are adding new special tokens to the tokenizer
     text_encoder.resize_token_embeddings(len(tokenizer))
diff --git a/src/diffusers/pipelines/stable_diffusion/README.md b/src/diffusers/pipelines/stable_diffusion/README.md
index 91930d89d4..47c38acbdb 100644
--- a/src/diffusers/pipelines/stable_diffusion/README.md
+++ b/src/diffusers/pipelines/stable_diffusion/README.md
@@ -28,16 +28,12 @@ download the weights with `git lfs install; git clone https://huggingface.co/Com
 
 ### Using Stable Diffusion without being logged into the Hub.
 
-If you want to download the model weights using a single Python line, you need to pass the token
-to `use_auth_token` or be logged in via `huggingface-cli login`. 
-For more information on access tokens, please refer to [this section](https://huggingface.co/docs/hub/security-tokens) of the documentation.
-
-Assuming your token is stored under YOUR_TOKEN, you can download the stable diffusion pipeline as follows:
+If you want to download the model weights using a single Python line, you need to be logged in via `huggingface-cli login`. 
 
 ```python
 from diffusers import DiffusionPipeline
 
-pipeline = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", use_auth_token=YOUR_TOKEN)
+pipeline = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
 ```
 
 This however can make it difficult to build applications on top of `diffusers` as you will always have to pass the token around. A potential way to solve this issue is by downloading the weights to a local path `"./stable-diffusion-v1-4"`: